Search

Your search keyword '"Xerox Company"' showing total 170 results
Start Over Author "Xerox Company"
170 results on '"Xerox Company"'

1. Many‐body effects in x‐ray photoemission and high‐Tc superconductivity of cuprate superconductors

Author

Central Research Laboratories, Matsushita Electric Industrial Company, Ltd., Yakumo‐Nakamachi 3‐1‐1, Moriguchi, Osaka 570, Japan, Fuji Xerox Company, Ltd., Takematsu 1600, Minami‐Ashigara, Kanagawa 250‐01, Japan, Faculty of Engineering, University of Tokyo, Hongo 7‐3‐1, Bunkyo, Tokyo 113, Japan, Kohiki, Shigemi, Sakai, Masahiro, Mizuno, Koichi, hayashi, Shigenori, Enokihara, Akira, Setsune, Kentaro, Fukushima, Sei, Gohshi, Yohichi, Central Research Laboratories, Matsushita Electric Industrial Company, Ltd., Yakumo‐Nakamachi 3‐1‐1, Moriguchi, Osaka 570, Japan, Fuji Xerox Company, Ltd., Takematsu 1600, Minami‐Ashigara, Kanagawa 250‐01, Japan, Faculty of Engineering, University of Tokyo, Hongo 7‐3‐1, Bunkyo, Tokyo 113, Japan, Kohiki, Shigemi, Sakai, Masahiro, Mizuno, Koichi, hayashi, Shigenori, Enokihara, Akira, Setsune, Kentaro, Fukushima, Sei, and Gohshi, Yohichi

Abstract

type:Journal Article, Many-body effects in Cu 2p x-ray photoemission of Bi2Sr2CaxCu1-xO6+2x (x=0,1,2), La2-xSrxCuO4 (x=0,0.13), and ErBa2Cu3O7-x,y (x

Published
2017

2. U.S. Department of Energy Selects PARC to Develop Low-Cost CO2 Sensors.

Author

PARC, a Xerox Company

Subjects
CARBON dioxide detectors, INDOOR air quality, SORBENTS, MANAGEMENT
Abstract

The article reports that the U.S. Department of Energy (DOE) has selected research & development (R&D) and technology company Palo Alto Research Center (PARC) to develop to develop low-cost carbon dioxide (CO2) sensors. Topics discussed include the use of sensors to indoor air quality and energy efficiency; the low-cost, printed sorbent to be developed by PARC for DOE; and the views of Clinton Smith, lead PARC researcher on the project, on it.

Published
2018

4. Activity representation with motion hierarchies

Author

Adrien Gaidon, Zaid Harchaoui, Cordelia Schmid, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Microsoft Research - Inria Joint Centre (MSR - INRIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Microsoft Research Laboratory Cambridge-Microsoft Corporation [Redmond, Wash.], Computer Vision, Xerox Research Centre Europe [Meylan], Xerox Company-Xerox Company, ERC_Allegro, MSR-Inria, AXES, ANR, ANR-11-LABX-0025,PERSYVAL-lab,Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique(2011), European Project: 269980,EC:FP7:ICT,FP7-ICT-2009-6,AXES(2011), European Project: 320559,EC:FP7:ERC,ERC-2012-ADG_20120216,ALLEGRO(2013), and European Project: 216886,EC:FP7:ICT,FP7-ICT-2007-1,PASCAL2(2008)

Subjects
Context (language use), 02 engineering and technology, Video analysis, Action recognition, Activity recognition, Artificial Intelligence, Spectral clustering, 0202 electrical engineering, electronic engineering, information engineering, Cluster analysis, Mathematics, Binary tree, business.industry, Kernel methods, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020206 networking & telecommunications, Pattern recognition, Tree (data structure), Kernel method, Pattern recognition (psychology), 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, Motion decomposition, Software
Abstract

Complex activities, e.g. pole vaulting, are composed of a variable number of sub-events connected by complex spatio-temporal relations, whereas simple actions can be represented as sequences of short temporal parts. In this paper, we learn hierarchical representations of activity videos in an unsupervised manner. These hierarchies of mid-level motion components are data-driven decompositions specific to each video. We introduce a spectral divisive clustering algorithm to efficiently extract a hierarchy over a large number of tracklets (i.e. local trajectories). We use this structure to represent a video as an unordered binary tree. We model this tree using nested histograms of local motion features. We provide an efficient positive definite kernel that computes the structural and visual similarity of two hierarchical decompositions by relying on models of their parent---child relations. We present experimental results on four recent challenging benchmarks: the High Five dataset (Patron-Perez et al., High five: recognising human interactions in TV shows, 2010), the Olympics Sports dataset (Niebles et al., Modeling temporal structure of decomposable motion segments for activity classification, 2010), the Hollywood 2 dataset (Marszalek et al., Actions in context, 2009), and the HMDB dataset (Kuehne et al., HMDB: A large video database for human motion recognition, 2011). We show that per-video hierarchies provide additional information for activity recognition. Our approach improves over unstructured activity models, baselines using other motion decomposition algorithms, and the state of the art.

Published
2014
Full Text
View/download PDF

5. The Global High Frequency Radar Network

Author

Charles-Antoine Guérin, Jian-Wu Lai, Siriluk Prukpitikul, Kevin Bartlett, Annalisa Griffa, Peter Rogowski, Simone Cosoli, Brian Whitehouse, Thomas Cook, Carlo Mantovani, Lisa Hazard, Emma Reyes, Eric Terrill, John L. Largier, Enrique Álvarez Fanjul, Mark Otero, Julien Mader, Jack Harlan, Birgit Hansen, Sang Ho Lee, Jorge Sanchez, Stephan T. Grilli, Lorenzo Corgnati, Scott Glenn, Pablo Lorente, Doug George, Kelly Johanna Saavedra-Matta, Lucy R. Wyatt, Anna Rubio, Naoto Ebuchi, X. Flores-Vidal, Hugh Roarty, Dept Ecol Evol Biol, Univ California SC (EEB-UCSC), University of California [Santa Cruz] (UCSC), University of California-University of California, School of Mathematics and Statistics [Sheffield] (SoMaS), University of Sheffield [Sheffield], Organismo publico puertos del estado, AZTI-Tecnalia, Marine Research Division, Istituto di Science Marine (ISMAR ), Consiglio Nazionale delle Ricerche (CNR), Istituto di Scienze Marine [Genova] (ISMAR), Consiglio Nazionale delle Ricerche (CNR)-Consiglio Nazionale delle Ricerche (CNR), SOCIB Balearic Islands Coastal Ocean Observing and Forecasting System, Organismo P\'{u}blico Puertos del Estado (PdE), Institut méditerranéen d'océanologie (MIO), Institut de Recherche pour le Développement (IRD)-Aix Marseille Université (AMU)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université de Toulon (UTLN), Xerox Research Centre Europe [Meylan], Xerox Company, Royal School of Library and Information Science (RSLIS), University of Copenhagen = Københavns Universitet (KU), University of Rhode Island (URI), University of California [Santa Cruz] (UC Santa Cruz), University of California (UC)-University of California (UC), National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR), National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR)-National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR), Institut de Recherche pour le Développement (IRD)-Aix Marseille Université (AMU)-Institut national des sciences de l'Univers (INSU - CNRS)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), and University of Copenhagen = Københavns Universitet (UCPH)

Subjects
0106 biological sciences, remote sensing, high frequency radar, ocean currents, waves, tsunami, boundary currents, ocean observing system, lcsh:QH1-199.5, 010504 meteorology & atmospheric sciences, Meteorology, Ocean Engineering, lcsh:General. Including nature conservation, geographical distribution, Aquatic Science, Oceanography, 01 natural sciences, law.invention, law, 14. Life underwater, Radar, lcsh:Science, [SDU.ENVI]Sciences of the Universe [physics]/Continental interfaces, environment, 0105 earth and related environmental sciences, Water Science and Technology, [SDU.OCEAN]Sciences of the Universe [physics]/Ocean, Atmosphere, Global and Planetary Change, Coastal hazards, 010604 marine biology & hydrobiology, Ocean current, Data sharing, Ocean dynamics, Ocean surface topography, 13. Climate action, Remote sensing (archaeology), Environmental science, lcsh:Q, Group on Earth Observations
Abstract

Academic, government, and private organizations from around the globe have established High Frequency radar (hereinafter, HFR) networks at regional or national levels. Partnerships have been established to coordinate and collaborate on a single global HFR network (http://global-hfradar.org/ ). These partnerships were established in 2012 as part of the Group on Earth Observations (GEO) to promote HFR technology and increase data sharing among operators and users. The main product of HFR networks are continuous maps of ocean surface currents within 200 km of the coast at high spatial (1-6 km) and temporal resolution (hourly or higher). Cutting-edge remote sensing technologies are becoming a standard component for ocean observing systems, contributing to the paradigm shift towards ocean monitoring. In 2017 the Global HFR Network was recognized by the Joint Technical WMO-IOC Commission for Oceanography and Marine Meteorology (JCOMM) as an observing network of the Global Ocean Observing System (GOOS). In this paper we will discuss the development of the network as well as establishing goals for the future. The U.S. High Frequency Radar Network (HFRNet) has been in operation for over thirteen years, with radar data being ingested from 31 organizations including measurements from Canada and Mexico. HFRNet currently holds a collection from over 150 radar installations totaling millions of records of surface ocean velocity measurements. During the past 10 years in Europe, HFR networks have been showing steady growth with over 60 stations currently deployed and many in the planning stage. In Asia and Oceania countries, more than 110 radar stations are in operation. HFR technology can be found in a wide range of applications: for marine safety, oil spill response, tsunami warning, pollution assessment, coastal zone management, tracking environmental change, numerical model simulation of 3-dimensional circulation, and research to generate new understanding of coastal ocean dynamics, depending mainly on each country's coastal sea characteristics. These radar networks are examples of national inter-agency and inter-institutional partnerships for improving oceanographic research and operations. As global partnerships grow, these collaborations and improved data sharing enhances our ability to respond to regional, national, and global environmental and management issues.

Published
2019
Full Text
View/download PDF

6. Is Rep 529 real-time PCR suitable for diagnosis of toxoplasmosis in patients infected with non-type II strains in Northern America?

Author

Pomares, Christelle, Estran, Remy, Press, Cynthia J, Bera, Aaron, Ramirez, Raymund, Montoya, Jose G, Robert Gangneux, Florence, Centre méditerranéen de médecine moléculaire (C3M), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Université Côte d'Azur (UCA)-Institut National de la Santé et de la Recherche Médicale (INSERM), Ecole Supérieure de Commerce de Paris (ESCP Europe), Palo Alto Research Center (PARC), Xerox Company, Institut de recherche en santé, environnement et travail (Irset), Université d'Angers (UA)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-École des Hautes Études en Santé Publique [EHESP] (EHESP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Structure Fédérative de Recherche en Biologie et Santé de Rennes ( Biosit : Biologie - Santé - Innovation Technologique ), École des Hautes Études en Santé Publique [EHESP] (EHESP), Philippe Foundation, Recherche et Développement en Pathologie Infectieuse et Tropicale, Association des Amis de la Faculté de Médecine, Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Côte d'Azur (UCA), and Université d'Angers (UA)-Université de Rennes (UR)-École des Hautes Études en Santé Publique [EHESP] (EHESP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Structure Fédérative de Recherche en Biologie et Santé de Rennes ( Biosit : Biologie - Santé - Innovation Technologique )

Subjects
qPCR, diagnosis, Rep 529, [SDV]Life Sciences [q-bio], Toxoplasma gondii, atypical genotype, B1, ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2019
Full Text
View/download PDF

7. 'Sentiment Aware Map' : exploration cartographique de points d’intérêt via l’analyse de sentiments au niveau des aspects

Author

Calapodescu, Ioan, Brun, Caroline, Nikoulina, Vassilina, Aït-Mokhtar, Salah, Naver Labs Europe [Meylan], THALIM - Théorie et histoire des arts et des littératures de la modernité - UMR 7172 (THALIM), Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Université Sorbonne Nouvelle - Paris 3, Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole (GETALP ), Laboratoire d'Informatique de Grenoble (LIG ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Xerox Research Centre Europe [Meylan], Xerox Company, Morin, Emmanuel, Rosset, Sophie, Zweigenbaum, Pierre, Université Sorbonne Nouvelle - Paris 3-Centre National de la Recherche Scientifique (CNRS)-Département Arts - ENS Paris, École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École normale supérieure - Paris (ENS Paris), and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)

Subjects
recherche cartographique, visualisation et filtrage de points d’interêts, Analyse de sentiments au niveau des aspects, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract

Cet article décrit un prototype dédié à la recherche cartographique de points d’interêts (PIs) sur la base de scores de sentiments au niveau des aspects, extraits sur des commentaires utilisateur. Ce système comprend un composant “état de l’art” d’analyse de sentiments au niveau des aspects, qui extrait les polarités des opinions utilisateur relatives aux aspects spécifiques des points d’interêts. Les polarités sont agrégées afin d’associer des évaluations aux PIs. L’utilisateur peut chercher, filtrer, réordonner et visualiser les PIs sur une carte en fonction d’aspects particuliers. Des profils de recherche multiples peuvent être définis via des préférences sur ces aspects.

Published
2019

8. Label-Embedding for Image Classification

Author

Zeynep Akata, Zaid Harchaoui, Florent Perronnin, Cordelia Schmid, Xerox Research Centre Europe [Meylan], Xerox Company, Apprentissage de modèles à partir de données massives (Thoth ), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Inria Grenoble - Rhône-Alpes, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
FOS: Computer and information sciences, Label Embedding, Linear programming, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, 010501 environmental sciences, Machine learning, computer.software_genre, 01 natural sciences, Text mining, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, 0105 earth and related environmental sciences, Training set, Image Classification, Contextual image classification, business.industry, Applied Mathematics, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Computational Theory and Mathematics, Embedding, Zero-Shot Learning, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, Attributes, business, computer, Software
Abstract

Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded in the space of attribute vectors. We introduce a function that measures the compatibility between an image and a label embedding. The parameters of this function are learned on a training set of labeled samples to ensure that, given an image, the correct classes rank higher than the incorrect ones. Results on the Animals With Attributes and Caltech-UCSD-Birds datasets show that the proposed framework outperforms the standard Direct Attribute Prediction baseline in a zero-shot learning scenario. Label embedding enjoys a built-in ability to leverage alternative sources of information instead of or in addition to attributes, such as e.g. class hierarchies or textual descriptions. Moreover, label embedding encompasses the whole range of learning settings from zero-shot learning to regular learning with a large number of labeled examples., Comment: IEEE TPAMI preprint

Published
2016
Full Text
View/download PDF

9. STATISTICALLY ASSISTED FLUID IMAGE REGISTRATION ALGORITHM - SAFIRA

Author

Xavier Pennec, Agatha D. Lee, Paul M. Thompson, Natasha Lepore, C. Brun, Katie L. McMahon, Margaret J. Wright, Marina Barysheva, Yi-Yu Chou, Greig I. de Zubicaray, Xerox Research Centre Europe [Meylan], Xerox Company, Laboratory of Neuro Imaging [Los Angeles] (LONI), University of California [Los Angeles] (UCLA), University of California-University of California, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Centre for Magnetic Resonance [Brisbanne], University of Queensland [Brisbane], Queensland Institute of Medical Research, and University of California (UC)-University of California (UC)

Subjects
education.field_of_study, Ground truth, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Covariance matrix, business.industry, Population, Image registration, Covariance, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Article, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Vector field, Computer vision, Algorithm design, Artificial intelligence, Tensor, business, education, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithm, ComputingMilieux_MISCELLANEOUS, Mathematics
Abstract

In this paper, we develop and validate a new Statistically Assisted Fluid Registration Algorithm (SAFIRA) for brain images. A non-statistical version of this algorithm was first implemented in [2] and re-formulated using Lagrangian mechanics in [3]. Here we extend this algorithm to 3D: given 3D brain images from a population, vector fields and their corresponding deformation matrices are computed in a first round of registrations using the non-statistical implementation. Covariance matrices for both the deformation matrices and the vector fields are then obtained and incorporated (separately or jointly) in the regularizing (i.e., the non-conservative Lagrangian) terms, creating four versions of the algorithm. We evaluated the accuracy of each algorithm variant using the manually labeled LPBA40 dataset, which provides us with ground truth anatomical segmentations. We also compared the power of the different algorithms using tensor-based morphometry-a technique to analyze local volumetric differences in brain structure- applied to 46 3D brain scans from healthy monozygotic twins.

Published
2018
Full Text
View/download PDF

10. BEST INDIVIDUAL TEMPLATE SELECTION FROM DEFORMATION TENSOR MINIMIZATION

Author

C. Brun, Arthur W. Toga, M. Meredith, Marina Barysheva, Margaret J. Wright, Katie L. McMahon, Yi-Yu Chou, Xavier Pennec, Paul M. Thompson, G.I. de Zubicaray, Natasha Lepore, Agatha D. Lee, Laboratory of Neuro Imaging [Los Angeles] (LONI), University of California [Los Angeles] (UCLA), University of California (UC)-University of California (UC), Xerox Research Centre Europe [Meylan], Xerox Company, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Centre for Magnetic Resonance [Brisbanne], University of Queensland [Brisbane], Queensland Institute of Medical Research, and University of California-University of California

Subjects
education.field_of_study, Similarity (geometry), business.industry, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Cumulative distribution function, Population, Monozygotic twin, Pattern recognition, computer.software_genre, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Article, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Voxel, Metric (mathematics), Null distribution, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Computer vision, Tensor, Artificial intelligence, business, education, computer, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, ComputingMilieux_MISCELLANEOUS, Mathematics
Abstract

We study the influence of the choice of template in tensor- based morphometry. Using 3D brain MR images from 10 monozygotic twin pairs, we defined a tensor-based distance in the log-Euclidean framework [1] between each image pair in the study. Relative to this metric, twin pairs were found to be closer to each other on average than random pairings, consistent with evidence that brain structure is under strong genetic control. We also computed the intraclass correlation and associated permutation p-value at each voxel for the determinant of the Jacobian matrix of the transformation. The cumulative distribution function (cdf) of the p-values was found at each voxel for each of the templates and compared to the null distribution. Surprisingly, there was very little difference between CDFs of statistics computed from analyses using different templates. As the brain with least log-Euclidean deformation cost, the mean template defined here avoids the blurring caused by creating a synthetic image from a population, and when selected from a large population, avoids bias by being geometrically centered, in a metric that is sensitive enough to anatomical similarity that it can even detect genetic affinity among anatomies.

Published
2018
Full Text
View/download PDF

11. SMILK, linking natural language and data from the web

Author

Elena Cabrio, Molka Tounsi Dhouib, Fabien Gandon, Cédric Lopez, Catherine Faron-Zucker, Frédéric Segond, Exploration et exploitation de données textuelles (TEXTE), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Web-Instrumented Man-Machine Interactions, Communities and Semantics (WIMMICS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S - SPARKS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA), Xerox Research Centre Europe [Meylan], and Xerox Company

Subjects
media_common.quotation_subject, Natural language processing, 02 engineering and technology, Art, Web of data, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Artificial Intelligence, Linked Data, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, Ontologies, 020201 artificial intelligence & image processing, Humanities, Software, media_common
Abstract

National audience; As part of the SMILK Joint Lab, we studied the use of Natural Language Processing to: (1) enrich knowledge bases and link data on the web, and conversely (2) use this linked data to contribute to the improvement of text analysis and the annotation of textual content, and to support knowledge extraction. The evaluation focused on brand-related information retrieval in the field of cosmetics. This article describes each step of our approach: the creation of ProVoc, an ontology to describe products and brands; the automatic population of a knowledge base mainly based on ProVoc from heterogeneous textual resources; and the evaluation of an application which that takes the form of a browser plugin providing additional knowledge to users browsing the web.; Le laboratoire commun SMILK avait pour double sujet d'étude l'utilisation du traitement automatique du langage naturel pour aider à la construction et au liage de données sur le web et, à l'inverse, l'utilisation de ces données liées du web sémantique pour aider à l'analyse des textes et venir en appui de l'extraction de connaissances et l'annotation de contenus textuels. L'évaluation de nos travaux s'est focalisée sur la recherche d'informations portant sur des marques, plus particulièrement dans le domaine de la cosmétique. Cet article décrit chaque étape de notre approche : la conception de ProVoc, une ontologie pour décrire les produits et marques ; le peuplement automatique d'une base de connaissances reposant notamment sur ProVoc à partir de ressources textuelles hétérogènes; et l'évaluation d'une application prenant la forme d'un plugin de navigateur proposant des connaissances supplémentaires aux utilisateurs naviguant sur le web.

Published
2018
Full Text
View/download PDF

12. SMILK, linking natural language and data from the web

Author

Lopez, C��dric, Dhouib, Molka, Cabrio, Elena, Zucker, Catherine Faron, Gandon, Fabien, Segond, Fr��d��rique, Exploration et exploitation de données textuelles (TEXTE), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Web-Instrumented Man-Machine Interactions, Communities and Semantics (WIMMICS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S - SPARKS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA), Xerox Research Centre Europe [Meylan], Xerox Company, Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Université Nice Sophia Antipolis (... - 2019) (UNS), and COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS)

Subjects
FOS: Computer and information sciences, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Natural language processing, Linked Data, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], Ontologies, Web of data, Information Retrieval (cs.IR), Computer Science - Information Retrieval, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

As part of the SMILK Joint Lab, we studied the use of Natural Language Processing to: (1) enrich knowledge bases and link data on the web, and conversely (2) use this linked data to contribute to the improvement of text analysis and the annotation of textual content, and to support knowledge extraction. The evaluation focused on brand-related information retrieval in the field of cosmetics. This article describes each step of our approach: the creation of ProVoc, an ontology to describe products and brands; the automatic population of a knowledge base mainly based on ProVoc from heterogeneous textual resources; and the evaluation of an application which that takes the form of a browser plugin providing additional knowledge to users browsing the web., in French

Published
2018
Full Text
View/download PDF

13. Symbolic Priors for RNN-based Semantic Parsing

Author

Marc Dymetman, Chunyang Xiao, Claire Gardent, Xerox Research Centre Europe [Meylan], Xerox Company, Natural Language Processing : representations, inference and semantics (SYNALP), Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
FOS: Computer and information sciences, Parsing, Computer Science - Computation and Language, Grammar, Intersection (set theory), Computer science, business.industry, media_common.quotation_subject, 020207 software engineering, 02 engineering and technology, computer.software_genre, Automaton, Recurrent neural network, 0202 electrical engineering, electronic engineering, information engineering, Logical form, 020201 artificial intelligence & image processing, S-attributed grammar, [INFO]Computer Science [cs], Artificial intelligence, business, computer, Computation and Language (cs.CL), Natural language processing, Natural language, media_common
Abstract

Seq2seq models based on Recurrent Neural Networks (RNNs) have recently received a lot of attention in the domain of Semantic Parsing. While in principle they can be trained directly on pairs (natural language utterances, logical forms), their performance is limited by the amount of available data. To alleviate this problem, we propose to exploit various sources of prior knowledge: the well-formedness of the logical forms is modeled by a weighted context-free grammar; the likelihood that certain entities present in the input utterance are also present in the logical form is modeled by weighted finite-state automata. The grammar and automata are combined together through an efficient intersection algorithm to form a soft guide (“background”) to the RNN.We test our method on an extension of the Overnight dataset and show that it not only strongly improves over an RNN baseline, but also outperforms non-RNN models based on rich sets of hand-crafted features.

Published
2018
Full Text
View/download PDF

14. Accuracy of using natural language processing methods for identifying healthcare-associated infections

Author

Stéfan Jacques Darmoni, Frédérique Segond, Nastassia Tvardik, Ivan Kergourlay, M.-H. Metzger, André Bittar, Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU), Equipe Traitement de l'information en Biologie Santé (TIBS - LITIS), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Xerox Research Centre Europe [Meylan], Xerox Company, and ANR-12-TECS-0006,SYNODOS,SYstème de Normalisation et d'Organisation de Données médicales textuelles pour l'Observation en Santé(2012)

Subjects
Healthcare associated infections, Adult, medicine.medical_specialty, animal structures, 020205 medical informatics, Epidemiology, computerized, Specialty, Nice, Health Informatics, 02 engineering and technology, Decision support systems, Healthcare-associated infections, computer.software_genre, Sensitivity and Specificity, Hospitals, University, 03 medical and health sciences, Clinical, 0302 clinical medicine, Intensive care, 0202 electrical engineering, electronic engineering, information engineering, medicine, Electronic Health Records, Humans, [INFO]Computer Science [cs], 030212 general & internal medicine, computer.programming_language, Cross Infection, business.industry, Digestive surgery, Medical record, Natural language processing, Medical records systems, virus diseases, University hospital, 3. Good health, Intensive Care Units, Artificial intelligence, business, computer, Algorithms
Abstract

Objective There is a growing interest in using natural language processing (NLP) for healthcare-associated infections (HAIs) monitoring. A French project consortium, SYNODOS, developed a NLP solution for detecting medical events in electronic medical records for epidemiological purposes. The objective of this study was to evaluate the performance of the SYNODOS data processing chain for detecting HAIs in clinical documents. Materials and methods The collection of textual records in these hospitals was carried out between October 2009 and December 2010 in three French University hospitals (Lyon, Rouen and Nice). The following medical specialties were included in the study: digestive surgery, neurosurgery, orthopedic surgery, adult intensive-care units. Reference Standard surveillance was compared with the results of automatic detection using NLP. Sensitivity on 56 HAI cases and specificity on 57 non-HAI cases were calculated. Results The accuracy rate was 84% (n = 95/113). The overall sensitivity of automatic detection of HAIs was 83.9% (CI 95%: 71.7–92.4) and the specificity was 84.2% (CI 95%: 72.1–92.5). The sensitivity varies from one specialty to the other, from 69.2% (CI 95%: 38.6–90.9) for intensive care to 93.3% (CI 95%: 68.1–99.8) for orthopedic surgery. The manual review of classification errors showed that the most frequent cause was an inaccurate temporal labeling of medical events, which is an important factor for HAI detection. Conclusion This study confirmed the feasibility of using NLP for the HAI detection in hospital facilities. Automatic HAI detection algorithms could offer better surveillance standardization for hospital comparisons.

Published
2018
Full Text
View/download PDF

15. LCR-Net: Localization-Classification-Regression for Human Pose

Author

Philippe Weinzaepfel, Cordelia Schmid, Grégory Rogez, Apprentissage de modèles à partir de données massives (Thoth ), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Xerox Research Centre Europe [Meylan], Xerox Company, Amazon_gift, European Project: 320559,EC:FP7:ERC,ERC-2012-ADG_20120216,ALLEGRO(2013), Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Inria Grenoble - Rhône-Alpes, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Contextual image classification, Computer science, business.industry, Initialization, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, 02 engineering and technology, 3D pose estimation, Real image, Regression, Articulated body pose estimation, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, Classifier (UML), Pose
Abstract

International audience; We propose an end-to-end architecture for joint 2D and 3D human pose estimation in natural images. Key to our approach is the generation and scoring of a number of pose proposals per image, which allows us to predict 2D and 3D pose of multiple people simultaneously. Hence, our approach does not require an approximate localization of the humans for initialization. Our architecture, named LCR-Net, contains 3 main components: 1) the pose proposal generator that suggests potential poses at different locations in the image; 2) a classifier that scores the different pose proposals ; and 3) a regressor that refines pose proposals both in 2D and 3D. All three stages share the convolutional feature layers and are trained jointly. The final pose estimation is obtained by integrating over neighboring pose hypotheses , which is shown to improve over a standard non maximum suppression algorithm. Our approach significantly outperforms the state of the art in 3D pose estimation on Human3.6M, a controlled environment. Moreover, it shows promising results on real images for both single and multi-person subsets of the MPII 2D pose benchmark.

Published
2017
Full Text
View/download PDF

16. Human Action Localization with Sparse Spatial Supervision

Author

Weinzaepfel, Philippe, Martin, Xavier, Schmid, Cordelia, Xerox Research Centre Europe [Meylan], Xerox Company, Apprentissage de modèles à partir de données massives (Thoth ), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), ERC_Allegro, MSR-Inria, Google_Research_Award, Facebook_Research_Award, ANR-11-LABX-0025,PERSYVAL-lab,Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique(2011), European Project: 320559,EC:FP7:ERC,ERC-2012-ADG_20120216,ALLEGRO(2013), Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Inria Grenoble - Rhône-Alpes, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Abstract

We introduce an approach for spatio-temporal human action localization using sparse spatial supervision. Our method leverages the large amount of annotated humans available today and extracts human tubes by combining a state-of-the-art human detector with a tracking-by-detection approach. Given these high-quality human tubes and temporal supervision, we select positive and negative tubes with very sparse spatial supervision, i.e., only one spatially annotated frame per instance. The selected tubes allow us to effectively learn a spatio-temporal action detector based on dense trajectories or CNNs. We conduct experiments on existing action localization benchmarks: UCF-Sports, J-HMDB and UCF-101. Our results show that our approach, despite using sparse spatial supervision, performs on par with methods using full supervision, i.e., one bounding box annotation per frame. To further validate our method, we introduce DALY (Daily Action Localization in YouTube), a dataset for realistic action localization in space and time. It contains high quality temporal and spatial annotations for 3.6k instances of 10 actions in 31 hours of videos (3.3M frames). It is an order of magnitude larger than existing datasets, with more diversity in appearance and long untrimmed videos.

Published
2017

17. Testing for Associations between Loci and Environmental Gradients Using Latent Factor Mixed Models

Author

Eric Frichot, Sean D. Schoville, Guillaume Bouchard, Olivier François, Techniques de l'Ingénierie Médicale et de la Complexité - Informatique, Mathématiques et Applications, Grenoble - UMR 5525 (TIMC-IMAG), VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Joseph Fourier - Grenoble 1 (UJF), Xerox Research Centre Europe [Meylan], Xerox Company, Biologie Computationnelle et Mathématique (TIMC-IMAG-BCM), VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Joseph Fourier - Grenoble 1 (UJF)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Joseph Fourier - Grenoble 1 (UJF), and ANR-11-LABX-0025,PERSYVAL-lab,Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique(2011)

Subjects
FOS: Computer and information sciences, environmental correlations, 0106 biological sciences, Mixed model, Population, Population genetics, Computational biology, Environment, Biology, Statistics - Computation, 010603 evolutionary biology, 01 natural sciences, 03 medical and health sciences, latent factor models, Genetic variation, Methods, Genetics, Humans, Selection, Genetic, Gene–environment interaction, Quantitative Biology - Populations and Evolution, education, Molecular Biology, Computation (stat.CO), Ecology, Evolution, Behavior and Systematics, 030304 developmental biology, Local adaptation, 0303 health sciences, education.field_of_study, [SDV.GEN.GPO]Life Sciences [q-bio]/Genetics/Populations and Evolution [q-bio.PE], Polymorphism, Genetic, genome scans, Natural selection, Ecology, Populations and Evolution (q-bio.PE), Genetic Variation, population structure, Models, Theoretical, Random effects model, Adaptation, Physiological, Genetics, Population, FOS: Biological sciences, Gene-Environment Interaction, Algorithms, local adaptation
Abstract

Adaptation to local environments often occurs through natural selection acting on a large number of loci, each having a weak phenotypic effect. One way to detect these loci is to identify genetic polymorphisms that exhibit high correlation with environmental variables used as proxies for ecological pressures. Here, we propose new algorithms based on population genetics, ecological modeling, and statistical learning techniques to screen genomes for signatures of local adaptation. Implemented in the computer program "latent factor mixed model" (LFMM), these algorithms employ an approach in which population structure is introduced using unobserved variables. These fast and computationally efficient algorithms detect correlations between environmental and genetic variation while simultaneously inferring background levels of population structure. Comparing these new algorithms with related methods provides evidence that LFMM can efficiently estimate random effects due to population history and isolation-by-distance patterns when computing gene-environment correlations, and decrease the number of false-positive associations in genome scans. We then apply these models to plant and human genetic data, identifying several genes with functions related to development that exhibit strong correlations with climatic gradients., Comment: 29 pages with 8 pages of Supplementary Material (V2 revised presentation and results part)

Published
2013
Full Text
View/download PDF

18. DeepMatching: Hierarchical Deformable Dense Matching

Author

Philippe Weinzaepfel, Zaid Harchaoui, Cordelia Schmid, Jerome Revaud, Xerox Research Centre Europe [Meylan], Xerox Company, Apprentissage de modèles à partir de données massives (Thoth ), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), ERC_Allegro, MSR-Inria, AXES, ANR-11-LABX-0025,PERSYVAL-lab,Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique(2011), European Project: 320559,EC:FP7:ERC,ERC-2012-ADG_20120216,ALLEGRO(2013), European Project: 269980,EC:FP7:ICT,FP7-ICT-2009-6,AXES(2011), Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Inria Grenoble - Rhône-Alpes, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
FOS: Computer and information sciences, deep convolutional neural networks (CNN), Computer science, Computer Vision and Pattern Recognition (cs.CV), Computation, Computer Science - Computer Vision and Pattern Recognition, Optical flow, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, optical flow, Artificial Intelligence, Robustness (computer science), Motion estimation, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Blossom algorithm, business.industry, Detector, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Robotics, Non-rigid matching, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Affine transformation, Artificial intelligence, business, Software
Abstract

International audience; We introduce a novel matching algorithm, called DeepMatching, to compute dense correspondences between images. DeepMatching relies on a hierarchical, multi-layer, correlational architecture designed for matching images and was inspired by deep convolutional approaches. The proposed matching algorithm can handle non-rigid deformations and repetitive textures and efficiently determines dense correspondences in the presence of significant changes between images. We evaluate the performance of DeepMatching, in comparison with state-of-the-art matching algorithms, on the Mikolajczyk (Mikolajczyk et al. A comparison of affine region detectors, 2005), the MPI-Sintel (Butler et al. A naturalistic open source movie for optical flow evaluation, 2012) and the Kitti (Geiger et al. Vision meets robotics: The KITTI dataset, 2013) datasets. DeepMatching outperforms the state-of-the-art algorithms and shows excellent results in particular for repetitive textures. We also apply DeepMatching to the computation of optical flow, called DeepFlow, by integrating it in the large displacement optical flow (LDOF) approach of Brox and Malik (Large displacement optical flow: descriptor matching in variational motion estimation, 2011). Additional robustness to large displacements and complex motion is obtained thanks to our matching approach. DeepFlow obtains competitive performance on public benchmarks for optical flow estimation.

Published
2016
Full Text
View/download PDF

19. A solid state highly emissive Cu(i) metallacycle: promotion of cuprophilic interactions at the excited states

Author

Vivian Wing-Wah Yam, Karine Costuas, L. Le Polles, Sloane Evariste, M. El Sayed Moussa, B. Le Guennic, Hok-Lai Wong, Laura Le Bras, Claire Roiland, Christophe Lescop, Institut des Sciences Chimiques de Rennes (ISCR), Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de Chimie de Rennes-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES), Palo Alto Research Center (PARC), Xerox Company, Institut d'électronique fondamentale (IEF), Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Ecole Nationale Supérieure de Chimie de Rennes (ENSCR)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Ecole Nationale Supérieure de Chimie de Rennes (ENSCR)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Quantum chemical, 010405 organic chemistry, Chemistry, Metals and Alloys, Solid-state, Quantum yield, General Chemistry, Metallacycle, [CHIM.INOR]Chemical Sciences/Inorganic chemistry, 010402 general chemistry, Photochemistry, 01 natural sciences, Catalysis, 0104 chemical sciences, Surfaces, Coatings and Films, Electronic, Optical and Magnetic Materials, Excited state, Materials Chemistry, Ceramics and Composites, Emission spectrum, Luminescence, ComputingMilieux_MISCELLANEOUS
Abstract

The straightforward synthesis of a new Cu(I) metal-rich small metallacycle is presented. This compound is luminescent in the solid state with an emission quantum yield of 72% at room temperature and displays a pronounced reversible red-shift of its emission spectra upon cooling. Quantum chemical calculations reveal that these properties are governed by important geometrical relaxations that imply the formation of cuprophilic interactions at the excited states.

Published
2016
Full Text
View/download PDF

20. Results of the Sequence PredIction ChallengE (SPiCe): a Competition on Learning the Next Symbol in a Sequence

Author

Balle, Borja, Eyraud, Rémi, Luque, Franco, Quattoni, Ariadna, Verwer, Sicco, Computing Department [Lancaster], Lancaster University, Laboratoire d'informatique Fondamentale de Marseille (LIF), Aix Marseille Université (AMU)-École Centrale de Marseille (ECM)-Centre National de la Recherche Scientifique (CNRS), éQuipe AppRentissage et MultimediA [Marseille] (QARMA), Aix Marseille Université (AMU)-École Centrale de Marseille (ECM)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-École Centrale de Marseille (ECM)-Centre National de la Recherche Scientifique (CNRS), Universidad Nacional de Córdoba [Argentina], Consejo Nacional de Investigaciones Científicas y Técnicas [Buenos Aires] (CONICET), Xerox Research Centre Europe [Meylan], Xerox Company, Delft University of Technology (TU Delft), Centre National de la Recherche Scientifique (CNRS)-École Centrale de Marseille (ECM)-Aix Marseille Université (AMU), Centre National de la Recherche Scientifique (CNRS)-École Centrale de Marseille (ECM)-Aix Marseille Université (AMU)-Centre National de la Recherche Scientifique (CNRS)-École Centrale de Marseille (ECM)-Aix Marseille Université (AMU), and Eyraud, Rémi

Subjects
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG]
Abstract

International audience; The Sequence PredIction ChallengE (SPiCe) is an on-line competition that took place between March and July 2016. Each of the 15 problems was made of a set of whole sequences as training sample, a validation set of prefixes, and a test set of prefixes. The aim was to submit a ranking of the 5 most probable symbols to be the next symbol of each prefix.

Published
2016

21. Sequence-based Structured Prediction for Semantic Parsing

Author

Claire Gardent, Chunyang Xiao, Marc Dymetman, Xerox Research Centre Europe [Meylan], Xerox Company, Natural Language Processing : representations, inference and semantics (SYNALP), Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Sequence, Parsing, Artificial neural network, Computer science, Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing), 02 engineering and technology, 010501 environmental sciences, computer.software_genre, 01 natural sciences, Prefix, TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES, ACM: H.: Information Systems, Symbol (programming), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, [INFO]Computer Science [cs], Structured prediction, Representation (mathematics), Algorithm, computer, Encoder, 0105 earth and related environmental sciences
Abstract

International audience; We propose an approach for semantic parsing that uses a recurrent neural network to map a natural language question into a logical form representation of a KB query. Building on recent work by (Wang et al., 2015), the interpretable logical forms, which are structured objects obeying certain constraints, are enumerated by an underlying grammar and are paired with their canonical realizations. In order to use sequence prediction, we need to sequentialize these logical forms. We compare three sequentializations: a direct linearization of the logical form, a linearization of the associated canonical realization, and a sequence consisting of derivation steps relative to the underlying grammar. We also show how grammatical constraints on the derivation sequence can easily be integrated inside the RNN-based sequential predictor. Our experiments show important improvements over previous results for the same dataset, and also demonstrate the advantage of incorporating the grammatical constraints.

Published
2016
Full Text
View/download PDF

22. Orthogonality regularizer for question answering

Author

Marc Dymetman, Guillaume Bouchard, Chunyang Xiao, Claire Gardent, Xerox Research Centre Europe [Meylan], Xerox Company, University College of London [London] (UCL), Natural Language Processing : representations, inference and semantics (SYNALP), Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Orthogonality (programming), business.industry, Computer science, 02 engineering and technology, Space (commercial competition), Knowledge base, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Benchmark (computing), Question answering, Object type, Embedding, [INFO]Computer Science [cs], 020201 artificial intelligence & image processing, Artificial intelligence, business, Lying
Abstract

International audience; Learning embeddings of words and knowledge base elements is a promising approach for open domain question answering. Based on the remark that relations and entities are distinct object types lying in the same embedding space, we analyze the benefit of adding a regularizer favoring the embeddings of entities to be orthogonal to those of relations. The main motivation comes from the observation that modifying the embeddings using prior knowledge often helps performance. The experiments show that incorporating the regularizer yields better results on a challenging question answering benchmark.

Published
2016
Full Text
View/download PDF

23. Aggregating Local Image Descriptors into Compact Codes

Author

Herve Jegou, Cordelia Schmid, Jorge Sanchez, Patrick Pérez, Florent Perronnin, Matthijs Douze, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Xerox Research Centre Europe [Meylan], Xerox Company, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Service Expérimentation et Développement (SED [Grenoble]), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Technicolor R & I [Cesson Sévigné], Technicolor, QUAERO, ANR-07-BLAN-0328,GAIA,Géométrie Algorithmique Informationnelle et Applications(2007), European Project: 216529,EC:FP7:ICT,FP7-ICT-2007-1,PINVIEW(2008), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, and SED [Grenoble]

Subjects
Fisher kernel, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, image retrieval, image search, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Image retrieval, Mathematics, Multi-core processor, business.industry, Applied Mathematics, Dimensionality reduction, Search engine indexing, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Byte, 020207 software engineering, Pattern recognition, Visualization, Computational Theory and Mathematics, Kernel (image processing), 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software, indexing
Abstract

International audience; This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage. We first present and evaluate different ways of aggregating local image descriptors into a vector and show that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. We then jointly optimize dimensionality reduction and indexing in order to obtain a precise vector comparison as well as a compact representation. The evaluation shows that the image representation can be reduced to a few dozen bytes while preserving high accuracy. Searching a 100 million image dataset takes about 250 ms on one processor core.

Published
2012
Full Text
View/download PDF

24. Local Convolutional Features with Unsupervised Training for Image Retrieval

Author

Julien Mairal, Cordelia Schmid, Matthijs Douze, Mattis Paulin, Florent Perronin, Zaid Harchaoui, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Xerox Research Centre Europe [Meylan], Xerox Company, ERC_Allegro, ANR_Macaron, CNRS_Mastodons_Titan, Xerox Research Center Europe, ANR-14-CE23-0003,MACARON,Apprentissage statistique à grande échelle et applications(2014), and European Project: 320559,EC:FP7:ERC,ERC-2012-ADG_20120216,ALLEGRO(2013)

Subjects
Computer science, business.industry, InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Scale-invariant feature transform, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, 02 engineering and technology, Machine learning, computer.software_genre, Automatic image annotation, Kernel (image processing), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Visual Word, Artificial intelligence, business, computer, Image retrieval
Abstract

International audience; Patch-level descriptors underlie several important computer vision tasks, such as stereo-matching or content-based image retrieval. We introduce a deep convolutional architecture that yields patch-level descriptors, as an alternative to the popular SIFT descriptor for image retrieval. The proposed family of descriptors, called Patch-CKN, adapt the recently introduced Convolutional Kernel Network (CKN), an unsupervised framework to learn convolutional architectures. We present a comparison framework to benchmark current deep convolutional approaches along with Patch-CKN for both patch and image retrieval, including our novel ``RomePatches'' dataset. Patch-CKN descriptors yield competitive results compared to supervised CNNs alternatives on patch and image retrieval.

Published
2015
Full Text
View/download PDF

25. Adaptation par enrichissement terminologique en traduction automatique statistique fondée sur la génération et le filtrage de bi-segments virtuels

Author

Servan, Christophe, Dymetman, Marc, Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole (GETALP), Laboratoire d'Informatique de Grenoble (LIG), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), Xerox Research Centre Europe [Meylan], Xerox Company, ATALA, ANR-14-CE24-0016,KEHATH,Méthodes qualité avancées pour la post-édition de traduction automatique(2014), and European Project: 287755,EC:FP7:ICT,FP7-ICT-2011-7,TRANSLECTURES(2011)

Subjects
[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, contexte phrastique, Génération Automatique de Texte, Traduction Automatique Statistique, terminologie bilingue
Abstract

National audience; Nous proposons des travaux préliminaires sur une approche permettant d'ajouter des termes bilingues à un système de Traduction Automatique Statistique (TAS) à base de segments.Ces termes sont, non seulement, inclus individuellement, mais aussi avec des contextes induits autour de ces mots. Tout d'abord nous générons ces contextes en généralisant des motifs (ou patrons) observés pour des mots de même nature syntaxique dans un corpus bilingue. Enfin, nous filtrons les contextes qui n'atteignent pas un certain seuil de confiance, à l'aide d'une méthode de sélection de bi-segments inspirée d'une approche de sélection de données, précédemment appliquée à des textes bilingues alignés.

Published
2015

26. Annotation methods to develop and evaluate an expert system based on natural language processing in electronic medical records

Author

Quentin, Gicquel, Nastassia, Tvardik, Côme, Bouvry, Ivan, Kergourlay, André, Bittar, Frédérique, Segond, Stefan, Darmoni, Marie-Hélène, Metzger, Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU), Equipe Traitement de l'information en Biologie Santé (TIBS - LITIS), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Xerox Research Centre Europe [Meylan], Xerox Company, Laboratoire de Biométrie et Biologie Evolutive - UMR 5558 (LBBE), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Centre National de la Recherche Scientifique (CNRS), ANR-12-TECS-0006,SYNODOS,SYstème de Normalisation et d'Organisation de Données médicales textuelles pour l'Observation en Santé(2012), Université Le Havre Normandie (ULH), Normandie Université (NU)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA), and Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Université Le Havre Normandie (ULH)

Subjects
Knowledge bases, Natural language processing, Data mining/methods, Pattern Recognition, Automated, Vocabulary controlled, Expert systems, Terminology as topic, Vocabulary, Controlled, Electronic health records/classification, Pattern recognition, Machine learning, Data Mining, Electronic Health Records, [INFO]Computer Science [cs]
Abstract

International audience; The objective of the SYNODOS collaborative project was to develop a generic IT solution, combining a medical terminology server, a semantic analyser and a knowledge base. The goal of the project was to generate meaningful epidemiological data for various medical domains from the textual content of French medical records. In the context of this project, we built a care pathway oriented conceptual model and corresponding annotation method to develop and evaluate an expert system's knowledge base. The annotation method is based on a semi-automatic process, using a software application (MedIndex). This application exchanges with a cross-lingual multi-termino-ontology portal. The annotator selects the most appropriate medical code proposed for the medical concept in question by the multi-termino-ontology portal and temporally labels the medical concept according to the course of the medical event. This choice of conceptual model and annotation method aims to create a generic database of facts for the secondary use of electronic health records data.

Published
2015

27. Explicit embeddings for nearest neighbor search with Mercer kernels

Author

Hervé Jégou, Rémi Gribonval, Patrick Pérez, Florent Perronnin, Anthony Bourrier, GIPSA - Vision and Brain Signal Processing (GIPSA-VIBS), Département Images et Signal (GIPSA-DIS), Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio (PANAMA), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Technicolor [Cesson Sévigné], Technicolor, Xerox Research Centre Europe [Meylan], Xerox Company, Creating and exploiting explicit links between multimedia fragments (LinkMedia), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-MEDIA ET INTERACTIONS (IRISA-D6), Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)

Subjects
Statistics and Probability, Explicit embeddings, Nearest neighbor search, Machine learning, computer.software_genre, Margin (machine learning), Encoding (memory), Mathematics, Euclidean space, business.industry, Applied Mathematics, Nearest Neighbor search, Condensed Matter Physics, Euclidean distance, Modeling and Simulation, Kernel (statistics), [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], Embedding, Mercer kernels, Geometry and Topology, Computer Vision and Pattern Recognition, Artificial intelligence, Fixed-radius near neighbors, business, computer, Algorithm
Abstract

International audience; Many approximate nearest neighbor search algorithms operate under memory constraints, by computing short signatures for database vectors while roughly keeping the neighborhoods for the distance of interest. Encoding procedures designed for the Euclidean distance have attracted much attention in the last decade.In the case where the distance of interest is based on a Mercer kernel, we propose a simple, yet effective two-step encoding scheme: first, compute an explicit embedding to map the initial space into a Euclidean space; second, apply an encoding step designed to work with the Euclidean distance. Comparing this simple baseline with existing methods relying on implicit encoding, we demonstrate better search recall for similar code sizes with the chi-square kernel in databases comprised of visual descriptors, outperforming concurrent state-of-the-art techniques by a large margin.

Published
2015
Full Text
View/download PDF

28. A Methodological Framework for Socio-Cognitive Analyses of Collaborative Design of Open Source Software

Author

Dilan Mahendran, Jean-Marie Burkhardt, Françoise Détienne, Warren Sack, Flore Barcellini, Nicolas Ducheneaut, University of California [Santa Cruz] (UC Santa Cruz), University of California (UC), Cognition and Cooperation in Design (EIFFEL2), Inria Paris-Rocquencourt, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Conservatoire National des Arts et Métiers [CNAM] (CNAM), HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM), Palo Alto Research Center (PARC), Xerox Company, Laboratoire d'Ergonomie Informatique (LEI), Université Paris Descartes - Paris 5 (UPD5), Department of Mathematics [Berkeley], University of California [Berkeley] (UC Berkeley), University of California (UC)-University of California (UC), Institut National de Recherche en Informatique et en Automatique (Inria), University of California [Santa Cruz] (UCSC), University of California, University of California [Berkeley], University of California-University of California, University of California [Santa Cruz] ( UCSC ), Cognition and Cooperation in Design ( EIFFEL2 ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Conservatoire National des Arts et Métiers [CNAM] ( CNAM ), Palo Alto Research Center ( PARC ), Laboratoire d'Ergonomie Informatique ( LEI ), and Université Paris Descartes - Paris 5 ( UPD5 )

Subjects
FOS: Computer and information sciences, General Computer Science, Computer science, Computer Science - Human-Computer Interaction, Open Source, 02 engineering and technology, Socio-cognitive, Human-Computer Interaction (cs.HC), [SHS]Humanities and Social Sciences, World Wide Web, Software, Empirical research, [ INFO.INFO-HC ] Computer Science [cs]/Human-Computer Interaction [cs.HC], Empirical Studies, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], business.industry, Methodology, Software Development, Software development, 020207 software engineering, Data science, Variety (cybernetics), Visualization, Design process, The Internet, business
Abstract

Open Source Software (OSS) development challenges traditional software engineering practices. In particular, OSS projects are managed by a large number of volunteers, working freely on the tasks they choose to undertake. OSS projects also rarely rely on explicit system-level design, or on project plans or schedules. Moreover, OSS developers work in arbitrary locations and collaborate almost exclusively over the Internet, using simple tools such as email and software code tracking databases (e.g. CVS). All the characteristics above make OSS development akin to weaving a tapestry of heterogeneous components. The OSS design process relies on various types of actors: people with prescribed roles, but also elements coming from a variety of information spaces (such as email and software code). The objective of our research is to understand the specific hybrid weaving accomplished by the actors of this distributed, collective design process. This, in turn, challenges traditional methodologies used to understand distributed software engineering: OSS development is simply too "fibrous" to lend itself well to analysis under a single methodological lens. In this paper, we describe the methodological framework we articulated to analyze collaborative design in the Open Source world. Our framework focuses on the links between the heterogeneous components of a project's hybrid network. We combine ethnography, text mining, and socio-technical network analysis and visualization to understand OSS development in its totality. This way, we are able to simultaneously consider the social, technical, and cognitive aspects of OSS development. We describe our methodology in detail, and discuss its implications for future research on distributed collective practices.

Published
2006
Full Text
View/download PDF

29. Revisiting the Fisher vector for fine-grained classification

Author

Naila Murray, Philippe-Henri Gosselin, Hervé Jégou, Florent Perronnin, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Xerox Research Centre Europe [Meylan], Xerox Company, Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, and Gosselin, Philippe-Henri

Subjects
Contextual image classification, Computer science, business.industry, Fisher kernel, Search engine indexing, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, Fisher vector, 02 engineering and technology, Machine learning, computer.software_genre, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Artificial Intelligence, Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, computer, Software
Abstract

Wining method of Fine-grain image classification challenge 2013.Late combination of two indexing and classification strategies.Good practices for fine grain image classification.Key features: descriptors filtering, spatial coordinates coding, active learning. This paper describes the joint submission of Inria and Xerox to their joint participation to the FGCOMP'2013 challenge. Although the proposed system follows most of the standard Fisher classification pipeline, we describe a few key features and good practices that significantly improve the accuracy when specifically considering fine-grain classification tasks. In particular, we consider the late fusion of two systems both based on Fisher vectors, but for which we choose drastically design choices that make them very complementary. Moreover, we propose a simple yet effective filtering strategy, which significantly boosts the performance for several class domains.

Published
2014

30. Comparison of Data Selection Techniques for the Translation of Video Lectures

Author

Wuebker, Joern, Ney, Hermann, Martínez-Villaronga, Adrià, Giménez Pastor, Adrián, Juan Císcar, Alfonso, Servan, Christophe, Dymetman, Marc, Mirkin, Shashar, Department of Computer Science [Aachen], Rheinisch-Westfälische Technische Hochschule Aachen (RWTH), Universitat Politècnica de València (UPV), Xerox Research Centre Europe [Meylan], Xerox Company, AMTA, European Project: 287755,EC:FP7:ICT,FP7-ICT-2011-7,TRANSLECTURES(2011), Servan, Christophe, Transcription and Translation of Video Lectures - TRANSLECTURES - - EC:FP7:ICT2011-11-01 - 2014-10-31 - 287755 - VALID, and Rheinisch-Westfälische Technische Hochschule Aachen University (RWTH)

Subjects
[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, Statistical machine translation, Translation quality, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, LENGUAJES Y SISTEMAS INFORMATICOS, Data selection techniques, Domain Adaptation, Speech translation
Abstract

[EN] For the task of online translation of scientific video lectures, using huge models is not possible. In order to get smaller and efficient models, we perform data selection. In this paper, we perform a qualitative and quantitative comparison of several data selection techniques, based on cross-entropy and infrequent n-gram criteria. In terms of BLEU, a combination of translation and language model cross-entropy achieves the most stable results. As another important criterion for measuring translation quality in our application, we identify the number of out-ofvocabulary words. Here, infrequent n-gram recovery shows superior performance. Finally, we combine the two selection techniques in order to benefit from both their strengths., The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement no 287755 (transLectures), and the Spanish MINECO Active2Trans (TIN2012-31723) research project.

Published
2014

31. Data Selection for Compact Adapted SMT Models

Author

Mirkin, Shachar, Besacier, Laurent, Xerox Research Centre Europe [Meylan], Xerox Company, Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole (GETALP), Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Institut Universitaire de France (IUF), and Ministère de l'Education nationale, de l’Enseignement supérieur et de la Recherche (M.E.N.E.S.R.)

Subjects
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract

International audience; Data selection is a common technique for adapting statistical translation models for a specific domain, which has been shown to both improve translation quality and to reduce model size. Selection relies on some in-domain data, of the same domain of the texts expected to be translated. Selecting the sentence-pairs that are most similar to the in-domain data from a pool of parallel texts has been shown to be effective; yet, this approach holds the risk of resulting in a limited coverage, when necessary n-grams that do appear in the pool are less similar to in-domain data that is available in advance. Some methods select additional data based on the actual text that needs to be translated. While useful, this is not always a practical scenario. In this work we describe an extensive exploration of data selection techniques over Arabic to French datasets, and propose methods to address both similarity and coverage considerations while maintaining a limited model size.

Published
2014

32. Selection itérative de transformations pour la classification d'images

Author

Paulin, Mattis, Revaud, Jérôme, Harchaoui, Zaid, Perronnin, Florent, Schmid, Cordelia, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Xerox Research Centre Europe [Meylan], and Xerox Company

Subjects
exemples virtuels, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Sélection de variables, classification d'images
Abstract

National audience; En classification d'images, une stratégie efficace pour apprendre un classifieur invariant à certaines transformations consiste à augmenter l'échantillon d'apprentissage par le même ensemble d'exemples mais auxquels les transformations ont été appliquées. Néanmoins, lorsque l'ensemble des transformations possibles est grand, il peut s'avérer difficile de sélectionner un petit nombre de transformations pertinentes parmi elles tout en conservant une taille d'échantillon d'apprentissage raisonnable. optimal. En effet, toutes les transformations n'apportent pas le même impact sur la performance ; certains peuvent même dégrader la performance. Nous proposons un algorithme de sélection automatique de transformations : à chaque itération, la transformation qui donne le plus grand gain en performance est sélectionnée. Nous évaluons notre approche sur les images de la compétition ImageNet 2010 et améliorons la performance en top-5 accuracy de 70.1% à 74.9%.

Published
2014

33. Transformation Pursuit for Image Classification

Author

Zaid Harchaoui, Cordelia Schmid, Jerome Revaud, Florent Perronnin, Mattis Paulin, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Xerox Research Centre Europe [Meylan], Xerox Company, ERC_Allegro, AXES, ANR-11-LABX-0025,PERSYVAL-lab,Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique(2011), ANR-12-CORD-0016,FIRE-ID,Reconnaissance à grain fin dans les grandes bases de données d'images(2012), European Project: 320559,EC:FP7:ERC,ERC-2012-ADG_20120216,ALLEGRO(2013), and European Project: 269980,EC:FP7:ICT,FP7-ICT-2009-6,AXES(2011)

Subjects
Training set, Contextual image classification, Selection (relational algebra), business.industry, Training time, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Machine learning, computer.software_genre, Image (mathematics), Transformation (function), Simple (abstract algebra), Artificial intelligence, Noise (video), business, computer, Mathematics
Abstract

International audience; A simple approach to learning invariances in image classification consists in augmenting the training set with transformed versions of the original images. However, given a large set of possible transformations, selecting a compact subset is challenging. Indeed, all transformations are not equally informative and adding uninformative transformations increases training time with no gain in accuracy. We propose a principled algorithm – Image Transformation Pursuit (ITP) – for the automatic selection of a compact set of transformations. ITP works in a greedy fashion, by selecting at each iteration the one that yields the highest accuracy gain. ITP also allows to efficiently explore complex transformations, that combine basic transformations. We report results on two public benchmarks: the CUB dataset of bird images and the ImageNet 2010 challenge. Using Fisher Vector representations, we achieve an improvement from 28.2% to 45.2% in top-1 accuracy on CUB, and an improvement from 70.1% to 74.9% in top-5 accuracy on ImageNet. We also show significant improvements for deep convnet features: from 47.3% to 55.4% on CUB and from 77.9% to 81.4% on ImageNet.

Published
2014
Full Text
View/download PDF

34. Instance classification with prototype selection

Author

Hervé Jégou, Florent Perronnin, Josip Krapac, Teddy Furon, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Xerox Research Centre Europe [Meylan], Xerox Company, Xerox Research Center Europe, ANR-12-CORD-0016,FIRE-ID,Reconnaissance à grain fin dans les grandes bases de données d'images(2012), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique

Subjects
Contextual image classification, business.industry, Computer science, media_common.quotation_subject, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Feature selection, Fisher vector, Classification scheme, Pattern recognition, Machine learning, computer.software_genre, Logos Bible Software, Hamming embedding, ComputingMethodologies_PATTERNRECOGNITION, Voting, Artificial intelligence, business, computer, Selection (genetic algorithm), media_common
Abstract

International audience; We address the problem of instance classification: our goal is to annotate images with tags corresponding to objects classes which exhibit small intra-class variations such as logos, products or landmarks. We propose a novel algorithm for the selection of class-specific prototypes which are used in a voting-based classification scheme. We show significant improvements over two state-of-the-art methods, namely the Fisher vector and Hamming Embedding, on two challenging methods of logos and vehicles.

Published
2014
Full Text
View/download PDF

35. Fast and Efficient Estimation of Individual Ancestry Coefficients

Author

Théo Trouillon, Eric Frichot, Guillaume Bouchard, François Mathieu, Olivier François, Techniques de l'Ingénierie Médicale et de la Complexité - Informatique, Mathématiques et Applications, Grenoble - UMR 5525 (TIMC-IMAG), VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Joseph Fourier - Grenoble 1 (UJF), Biologie Computationnelle et Mathématique (TIMC-IMAG-BCM), VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Joseph Fourier - Grenoble 1 (UJF)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Joseph Fourier - Grenoble 1 (UJF), Xerox Research Centre Europe [Meylan], Xerox Company, This work has been partially supported by the LabExPERSYVAL-Lab(ANR-11-LABX-0025-01), ANR-11-LABX-0025,PERSYVAL-lab,Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique(2011), Francois, Olivier, and Laboratoires d'excellence - Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique - - PERSYVAL-lab2011 - ANR-11-LABX-0025 - LABX - VALID

Subjects
Time Factors, Genotype, Genomic data, Population, Large population, MESH: Plants, MESH: Population Groups, Inference, MESH: Genetics, Population, MESH: Algorithms, Biology, Investigations, Bioinformatics, Non-negative matrix factorization, MESH: Genotype, MESH: Software, Software, Gene Frequency, Population Groups, Genetics, MESH: Gene Frequency, Humans, education, Genetic Association Studies, MESH: Genetic Association Studies, Estimation, education.field_of_study, Likelihood Functions, MESH: Humans, [SDV.GEN.GPO]Life Sciences [q-bio]/Genetics/Populations and Evolution [q-bio.PE], Computer program, business.industry, MESH: Time Factors, Computational Biology, Plants, Genetics, Population, [SDV.GEN.GPO] Life Sciences [q-bio]/Genetics/Populations and Evolution [q-bio.PE], MESH: Likelihood Functions, business, Algorithm, Algorithms, MESH: Computational Biology
Abstract

Inference of individual ancestry coefficients, which is important for population genetic and association studies, is commonly performed using computer-intensive likelihood algorithms. With the availability of large population genomic data sets, fast versions of likelihood algorithms have attracted considerable attention. Reducing the computational burden of estimation algorithms remains, however, a major challenge. Here, we present a fast and efficient method for estimating individual ancestry coefficients based on sparse nonnegative matrix factorization algorithms. We implemented our method in the computer program sNMF and applied it to human and plant data sets. The performances of sNMF were then compared to the likelihood algorithm implemented in the computer program ADMIXTURE. Without loss of accuracy, sNMF computed estimates of ancestry coefficients with runtimes ∼10–30 times shorter than those of ADMIXTURE.

Published
2014

36. Translation project adaptation for MT-enhanced computer assisted translation

Author

Nicola Bertoldi, Mauro Cettolo, Marcello Federico, Christophe Servan, Loïc Barrault, Holger Schwenk, Fondazione Bruno Kessler [Trento, Italy] (FBK), Laboratoire d'Informatique de l'Université du Mans (LIUM), Le Mans Université (UM), Xerox Research Centre Europe [Meylan], Xerox Company, and European Project: 287688,EC:FP7:ICT,FP7-ICT-2011-7,MATECAT(2011)

Subjects
Linguistics and Language, Computer science, 02 engineering and technology, computer.software_genre, Language and Linguistics, German, 030507 speech-language pathology & audiology, 03 medical and health sciences, Translation project, Artificial Intelligence, Robustness (computer science), 0202 electrical engineering, electronic engineering, information engineering, Language industry, business.industry, Information technology, Transfer-based machine translation, language.human_language, [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, language, Computer-assisted translation, 020201 artificial intelligence & image processing, Artificial intelligence, Computational linguistics, 0305 other medical science, business, computer, Software, Natural language processing
Abstract

The effective integration of MT technology into computer-assisted translation tools is a challenging topic both for academic research and the translation industry. In particular, professional translators consider the ability of MT systems to adapt to the feedback provided by them to be crucial. In this paper, we propose an adaptation scheme to tune a statistical MT system to a translation project using small amounts of post-edited texts, like those generated by a single user in even just one day of work. The same scheme can be applied on a larger scale in order to focus general purpose models towards the specific domain of interest. We assess our method on two domains, namely information technology and legal, and four translation directions, from English to French, Italian, Spanish and German. The main outcome is that our adaptation strategy can be very effective provided that the seed data used for adaptation is `close enough' to the remaining text to be translated; otherwise, MT quality neither improves nor worsens, thus showing the robustness of our method.

Published
2014
Full Text
View/download PDF

37. Inria+Xerox@FGcomp: Boosting the Fisher vector for fine-grained classification

Author

Gosselin, Philippe-Henri, Murray, Naila, Jégou, Hervé, Perronnin, Florent, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Xerox Research Centre Europe [Meylan], Xerox Company, INRIA, Xerox Research Center Europe, ANR-12-CORD-0016,FIRE-ID,Reconnaissance à grain fin dans les grandes bases de données d'images(2012), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Jégou, Hervé, and Contenus et Interactions - Reconnaissance à grain fin dans les grandes bases de données d'images - - FIRE-ID2012 - ANR-12-CORD-0016 - CONTINT - VALID

Subjects
[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Abstract

This report describes the joint submission of Inria and Xerox to their participation to the FGCOMP 2013 challenge. Although the proposed system follows most of the standard Fisher classification pipeline, we describe several key features and good practices that improve the accuracy when specifically considering fine-grained classification tasks. In particular, we consider the late fusion of two systems both based on Fisher vectors, but that employ drastically different design choices that make them very complementary. Moreover, we show that a simple yet effective filtering strategy significantly boosts the performance for several class domains.

Published
2013

38. Attribute-Based Classification with Label-Embedding

Author

Akata, Zeynep, Perronnin, Florent, Harchaoui, Zaid, Schmid, Cordelia, Xerox Research Centre Europe [Meylan], Xerox Company, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Neural Information Processing Systems (NIPS) Foundation, AXES, ANR-12-CORD-0016,FIRE-ID,Reconnaissance à grain fin dans les grandes bases de données d'images(2012), and European Project: 269980,EC:FP7:ICT,FP7-ICT-2009-6,AXES(2011)

Subjects
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Abstract

International audience; Attributes are an intermediate representation whose purpose is to enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded in the space of attribute vectors. We introduce a function which measures the compatibility between an image and a label embedding. The parameters of this function are learned on a training set of labeled samples to ensure that, given an image, the correct class has a higher compatibility than the incorrect ones. Experimental results on two standard image classification datasets are presented, resp. on the Animals With Attributes and on Caltech-UCSD-Birds datasets.

Published
2013

39. Image Classification with the Fisher Vector: Theory and Practice

Author

Thomas Mensink, Jakob Verbeek, Jorge Sanchez, Florent Perronnin, Facultad de Matemática, Astronomía y Física [Cordoba] (FaMAF), Universidad Nacional de Córdoba [Argentina], Xerox Research Centre Europe [Meylan], Xerox Company, Intelligent Systems Lab. (ISLA), University of Amsterdam [Amsterdam] (UvA), Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Amsterdam Machine Learning lab (IVI, FNWI), and Intelligent Sensory Information Systems (IVI, FNWI)

Subjects
IMAGE CLASSIFICATION, Image classification, Fisher kernel, LARGE-SCALE CLASSIFICATION, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Set (abstract data type), [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Artificial Intelligence, Encoding (memory), Product quantization, 0202 electrical engineering, electronic engineering, information engineering, FISHER VECTOR, Large-scale classification, Representation (mathematics), Otras Ciencias de la Computación e Información, Fisher vector, Mathematics, Contextual image classification, business.industry, 020207 software engineering, Pattern recognition, BAG-OF-VISUAL WORDS, Mixture model, Bag-of-words model in computer vision, Computer Science::Computer Vision and Pattern Recognition, Ciencias de la Computación e Información, Pattern recognition (psychology), 020201 artificial intelligence & image processing, Bag-of-Visual words, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software, CIENCIAS NATURALES Y EXACTAS
Abstract

A standard approach to describe an image for classification and retrieval purposes is to extract a set of local patch descriptors, encode them into a high dimensional vector and pool them into an image-level signature. The most common patch encoding strategy consists in quantizing the local descriptors into a finite set of prototypical elements. This leads to the popular Bag-of-Visual words representation. In this work, we propose to use the Fisher Kernel framework as an alternative patch encoding strategy: we describe patches by their deviation from an “universal” generative Gaussian mixture model. This representation, which we call Fisher vector has many advantages: it is efficient to compute, it leads to excellent results even with efficient linear classifiers, and it can be compressed with a minimal loss of accuracy using product quantization. We report experimental results on five standard datasets—PASCAL VOC 2007, Caltech 256, SUN 397, ILSVRC 2010 and ImageNet10K— with up to 9M images and 10K classes, showing that the FV framework is a state-of-the-art patch encoding technique. Fil: Sanchez, Jorge Adrian. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Córdoba. Centro de Investigación y Estudios de Matemática de Córdoba(p); Argentina Fil: Perronnin, Florent . Xerox Research Centre Europe; Francia Fil: Mensink, Thomas. University of Amsterdam. Inteligent Systems Lab Amsterdam; Países Bajos Fil: Verbeek, Jakob. LEAR Team, INRIA Grenoble; Francia

Published
2013
Full Text
View/download PDF

40. Distance-Based Image Classification: Generalizing to new classes at near-zero cost

Author

Jakob Verbeek, Thomas Mensink, Gabriela Csurka, Florent Perronnin, Intelligent Systems Lab. (ISLA), University of Amsterdam [Amsterdam] (UvA), Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Xerox Research Centre Europe [Meylan], Xerox Company, Amsterdam Machine Learning lab (IVI, FNWI), and Intelligent Sensory Information Systems (IVI, FNWI)

Subjects
Computer science, Generalization, 02 engineering and technology, Machine learning, computer.software_genre, 030218 nuclear medicine & medical imaging, k-nearest neighbors algorithm, Pattern Recognition, Automated, 03 medical and health sciences, 0302 clinical medicine, Artificial Intelligence, Image Interpretation, Computer-Assisted, 0202 electrical engineering, electronic engineering, information engineering, Computer Simulation, Image retrieval, Training set, Contextual image classification, business.industry, Applied Mathematics, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Models, Theoretical, Image Enhancement, Support vector machine, Computational Theory and Mathematics, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, Transfer of learning, business, Classifier (UML), computer, Software, Algorithms, Distance based
Abstract

International audience; We study large-scale image classification methods that can incorporate new classes and training images continuously over time at negligible cost. To this end we consider two distance-based classifiers, the k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers, and introduce a new metric learning approach for the latter. We also introduce an extension of the NCM classifier to allow for richer class representations. Experiments on the ImageNet 2010 challenge dataset, which contains over 106 training images of 1,000 classes, show that, surprisingly, the NCM classifier compares favorably to the more flexible k-NN classifier. Moreover, the NCM performance is comparable to that of linear SVMs which obtain current state-of-the-art performance. Experimentally we study the generalization performance to classes that were not used to learn the metrics. Using a metric learned on 1,000 classes, we show results for the ImageNet-10K dataset which contains 10,000 classes, and obtain performance that is competitive with the current state-of-the-art, while being orders of magnitude faster. Furthermore, we show how a zero-shot class prior based on the ImageNet hierarchy can improve performance when few training images are available.

Published
2013
Full Text
View/download PDF

41. Structured Penalties for Log-linear Language Models

Author

Nelakanti, Anil, Archambeau, Cédric, Mairal, Julien, Bach, Francis, Bouchard, Guillaume, Xerox Research Centre Europe [Meylan], Xerox Company, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'informatique de l'école normale supérieure (LIENS), Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS), Statistical Machine Learning and Parsimony (SIERRA), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Paris-Rocquencourt, Institut National de Recherche en Informatique et en Automatique (Inria), Centre National de la Recherche Scientifique (CNRS)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Centre National de la Recherche Scientifique (CNRS)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre Mendès France - Grenoble 2 (UPMF), Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Inria Paris-Rocquencourt, École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS), Département d'informatique de l'École normale supérieure (DI-ENS), and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris)

Subjects
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Abstract

International audience; Language models can be formalized as loglinear regression models where the input features represent previously observed contexts up to a certain length m. The complexity of existing algorithms to learn the parameters by maximum likelihood scale linearly in nd, where n is the length of the training corpus and d is the number of observed features. We present a model that grows logarithmically in d, making it possible to efficiently leverage longer contexts. We account for the sequential structure of natural language using treestructured penalized objectives to avoid overfitting and achieve better generalization.

Published
2013

42. Relationship-Based Business Process Crowdsourcing?

Author

Jacki O'Neill, David Martin, Xerox Research Centre Europe [Meylan], Xerox Company, David Hutchison, Takeo Kanade, Madhu Sudan, Demetri Terzopoulos, Doug Tygar, Moshe Y. Vardi, Gerhard Weikum, Paula Kotzé, Gary Marsden, Gitte Lindgaard, Janet Wesson, Marco Winckler, Josef Kittler, Jon M. Kleinberg, Friedemann Mattern, John C. Mitchell, Moni Naor, Oscar Nierstrasz, C. Pandu Rangan, and Bernhard Steffen

Subjects
Knowledge management, business.industry, Emerging technologies, Business process, 05 social sciences, business process outsourcing, Redress, 02 engineering and technology, Public relations, Crowdsourcing, ethnography, Work (electrical), 020204 information systems, 8. Economic growth, Health care, 0202 electrical engineering, electronic engineering, information engineering, relationship- based crowdsourcing, 0501 psychology and cognitive sciences, [INFO]Computer Science [cs], SWORD, business, 050107 human factors, Digitization
Abstract

Part 1: Long and Short Papers (Continued); International audience; New technologies do not always benefit the worker, especially when harnessed by organisations seeking ever cheaper labour. Crowdsourcing is a technology-enabled way of working which offers the potential to bring work to far flung communities. However, it is something of a double-edged sword and there are many socio-technical and ethical challenges. In the micro-task market crowdsourcing platforms tend to be designed largely for the advantage of the organisation requesting work, rather than the worker. This paper contributes to research calling to redress this balance [2, 6]. It describes the findings of an ethnographic study of an outsourced business process – healthcare form digitization – as performed by workers in-office (India) and @Home (USA). It reveals the complexities of the relationships between worker and organisation and argues that designing some aspects of these relationships into crowdsourcing platforms and applications is as beneficial for the organisation as it is for the worker.

Published
2013
Full Text
View/download PDF

43. ECSCW 2013 Adjunct Proceedings The 13th European Conference on Computer Supported Cooperative Work 21 - 25. September 2013, Paphos, Cyprus

Author

Tommaso Colombino, Myriam Lewkowicz, Matthias Korn, Aarhus University [Aarhus], Xerox Research Centre Europe [Meylan], Xerox Company, TECHnologies pour la Coopération, l’Interaction et les COnnaissances dans les collectifs (Tech-CICO), Institut Charles Delaunay (ICD), and Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS)-Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)

Subjects
business.industry, GeneralLiterature_INTRODUCTORYANDSURVEY, Computer-supported cooperative work, 0202 electrical engineering, electronic engineering, information engineering, Media studies, Medicine, Library science, [SHS.GESTION]Humanities and Social Sciences/Business administration, 020206 networking & telecommunications, 020201 artificial intelligence & image processing, 02 engineering and technology, business, Adjunct
Abstract

This volume presents the adjunct proceedings of ECSCW 2013.While the proceedings published by Springer Verlag contains the core of the technical program, namely the full papers, the adjunct proceedings includes contributions on work in progress, workshops and master classes, demos and videos, the doctoral colloquium, and keynotes, thus indicating what our field may become in the future.

Published
2013
Full Text
View/download PDF

44. Privacy in Content-Oriented Networking: Threats and Countermeasures

Author

Abdelberi Chaabane, Ersin Uzun, Emiliano De Cristofaro, Mohamed Ali Kaafar, Privacy Models, Architectures and Tools for the Information Society (PRIVATICS), CITI Centre of Innovation in Telecommunications and Integration of services (CITI), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria), Palo Alto Research Center (PARC), Xerox Company, Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-CITI Centre of Innovation in Telecommunications and Integration of services (CITI), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Inria Lyon

Subjects
Networking and Internet Architecture (cs.NI), FOS: Computer and information sciences, Network architecture, Information privacy, Computer Science - Cryptography and Security, Privacy by Design, Computer Networks and Communications, Computer science, business.industry, Privacy software, Internet privacy, Computer security, computer.software_genre, Networking hardware, Computer Science - Networking and Internet Architecture, [INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR], Scalability, The Internet, business, Cryptography and Security (cs.CR), computer, Software, Anonymity
Abstract

International audience; As the Internet struggles to cope with scalability, mobility, and security issues, new network architectures are being proposed to better accommodate the needs of modern systems and applications. In particular, Content-Oriented Networking (CON) has emerged as a promising next-generation Internet architecture: it sets to decouple content from hosts, at the network layer, by naming data rather than hosts. CON comes with a potential for a wide range of benefits, including reduced congestion and improved delivery speed by means of content caching, simpler configuration of network devices, and security at the data level. However, it remains an interesting open question whether or not, and to what extent, this emerging networking paradigm bears new privacy challenges. In this paper, we provide a systematic privacy analysis of CON and the common building blocks among its various architectural instances in order to highlight emerging privacy threats, and analyze a few potential countermeasures. Finally, we present a comparison between CON and today's Internet in the context of a few privacy concepts, such as, anonymity, censoring, traceability, and confidentiality

Published
2013

45. MRM protein quantification and serum sample classification

Author

Szacherski, Pascal, Gerfault, Laurent, Giovannelli, Jean-François, Giremus, Audrey, Mahé, Pierre, Fortin, Tanguy, Choquet, Geneviève, Klich, Amna, Mercier, Catherine, Roy, Pascal, Salvador, Arnaud, Lemoine, Jérôme, Charrier, Jean-Philippe, Lacroix, Bruno, Grangeat, Pierre, Laboratoire de l'intégration, du matériau au système (IMS), Université Sciences et Technologies - Bordeaux 1-Institut Polytechnique de Bordeaux-Centre National de la Recherche Scientifique (CNRS), Laboratoire Electronique des Systèmes Santé (LE2S), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information (CEA-LETI), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Xerox Research Centre Europe [Meylan], Xerox Company, bioMérieux, BIOMERIEUX, Biomérieux Lyon, Biostatistiques santé, Département biostatistiques et modélisation pour la santé et l'environnement [LBBE], Laboratoire de Biométrie et Biologie Evolutive - UMR 5558 (LBBE), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire de Biométrie et Biologie Evolutive - UMR 5558 (LBBE), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Centre National de la Recherche Scientifique (CNRS), Institut des Sciences Analytiques (ISA), Institut de Chimie du CNRS (INC)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Centre National de la Recherche Scientifique (CNRS), Biomérieux SA - R&D Proteom, bioMérieux SA, Human Genetics Department, Université Sciences et Technologies - Bordeaux 1 (UB)-Institut Polytechnique de Bordeaux-Centre National de la Recherche Scientifique (CNRS), and Université de Lyon-Université de Lyon-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [SDV.BBM.GTP]Life Sciences [q-bio]/Biochemistry, Molecular Biology/Genomics [q-bio.GN], [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

Quantification and classification are key points for differential analysis of proteomic studies and diagnostic tests. A MRM analytical chain is a cascade of molecular events depicted by a graph structure, each node being associated to a molecular state such as protein, peptide or ion and each branch to a molecular processing. Each protein is associated to a set of transition measurements. One key question is how to infer the protein level and the class label. We propose to compare a hierarchical model based Bayesian Hierarchical Inversion combining all transitions and a non-linear processing based on logarithmic transformation of standardized peak value combined with a median filter. Classification performances are evaluated on a colorectal cancer cohort for LFABP and PDI biomarkers.

Published
2013

46. Label-Embedding for Attribute-Based Classification

Author

Zaid Harchaoui, Cordelia Schmid, Zeynep Akata, Florent Perronnin, Xerox Research Centre Europe [Meylan], Xerox Company, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), and Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)

Subjects
Training set, Contextual image classification, business.industry, Computer science, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, 02 engineering and technology, Machine learning, computer.software_genre, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Embedding, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer
Abstract

International audience; Attributes are an intermediate representation, which enables parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded in the space of attribute vectors. We introduce a function which measures the compatibility between an image and a label embedding. The parameters of this function are learned on a training set of labeled samples to ensure that, given an image, the correct classes rank higher than the incorrect ones. Results on the Animals With Attributes and Caltech-UCSD-Birds datasets show that the proposed framework outperforms the standard Direct Attribute Prediction baseline in a zero-shot learning scenario. The label embedding framework offers other advantages such as the ability to leverage alternative sources of information in addition to attributes (e.g. class hierarchies) or to transition smoothly from zero-shot learning to learning with large quantities of data.

Published
2013
Full Text
View/download PDF

47. Image Classification with the Fisher Vector: Theory and Practice

Author

Sanchez, Jorge, Perronnin, Florent, Mensink, Thomas, Verbeek, Jakob, Facultad de Matemática, Astronomía y Física [Cordoba] (FaMAF), Universidad Nacional de Córdoba [Argentina], Xerox Research Centre Europe [Meylan], Xerox Company, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), and INRIA

Subjects
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Abstract

A standard approach to describe an image for classification and retrieval purposes is to extract a set of local patch descriptors, encode them into a high dimensional vector and pool them into an image-level signature. The most common patch encoding strategy consists in quantizing the local descriptors into a finite set of prototypical elements. This leads to the popular Bag-of-Visual words (BOV) representation. In this work, we propose to use the Fisher Kernel framework as an alternative patch encoding strategy: we describe patches by their deviation from an ''universal'' generative Gaussian mixture model. This representation, which we call Fisher Vector (FV) has many advantages: it is efficient to compute, it leads to excellent results even with efficient linear classifiers, and it can be compressed with a minimal loss of accuracy using product quantization. We report experimental results on five standard datasets -- PASCAL VOC 2007, Caltech 256, SUN 397, ILSVRC 2010 and ImageNet10K -- with up to 9M images and 10K classes, showing that the FV framework is a state-of-the-art patch encoding technique.

Published
2013

48. Optimization of power consumption and user impact based on point process modeling of the request sequence

Author

Durand, Jean-Baptiste, Girard, Stéphane, Ciriza, Victor, Donini, Laurent, Modelling and Inference of Complex and Structured Stochastic Systems (MISTIS), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Xerox Research Centre Europe [Meylan], and Xerox Company

Subjects
Hidden Markov chain modelling, Renewal processes, Optimal time out, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Statistical models for request processes, Power management, [STAT.TH]Statistics [stat]/Statistics Theory [stat.TH]
Abstract

International audience; This article addresses the optimal choice of the waiting period (or timeout) that a device should respect before entering sleep mode, so as to optimize a tradeoff between power consumption and user impact. The optimal timeout is inferred by appropriate statistical modeling of the times between user requests. In a test approach, these times are supposed independent, and a constant optimal timeout is inferred accordingly. In a second approach, some dependency is introduced through a hidden Markov chain, which also models specific activity states, like business hours or night periods. This model leads to a statistical framework for computing adaptive optimal timeout values. Different strategies are assessed using real datasets, on the basis of the power consumption, user impact and the frequency of wrong decisions.

Published
2013
Full Text
View/download PDF

49. Large Scale Metric Learning for Distance-Based Image Classification on Open Ended Data Sets

Author

Mensink, T., Verbeek, J., Perronnin, F., Csurka, G., Farinella, G.M., Battiato, S., Cipolla, R, Xerox Research Centre Europe [Meylan], Xerox Company, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Farinella, Giovanni Maria and Battiato, Sebastiano and Cipolla, Roberto, Amsterdam Machine Learning lab (IVI, FNWI), and Intelligent Sensory Information Systems (IVI, FNWI)

Subjects
Contextual image classification, business.industry, 05 social sciences, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, 02 engineering and technology, Machine learning, computer.software_genre, Metric (mathematics), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, 0509 other social sciences, 050904 information & library sciences, business, Image retrieval, Classifier (UML), computer, Mathematics, Distance based
Abstract

International audience; Many real-life large-scale datasets are open-ended and dynamic: new images are continuously added to existing classes, new classes appear over time, and the semantics of existing classes might evolve too. Therefore, we study large-scale image classification methods that can incorporate new classes and training images continuously over time at negligible cost. To this end we consider two distance-based classifiers, the k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers. Since the performance of distance-based classifiers heavily depends on the used distance function, we cast the problem into one of learning a low-rank metric, which is shared across all classes. For the NCM classifier we introduce a new metric learning approach, and we also introduce an extension to allow for richer class representations. Experiments on the ImageNet 2010 challenge dataset, which contains over one million training images of thousand classes, show that, surprisingly, the NCM classifier compares favorably to the more flexible k-NN classifier. Moreover, the NCM performance is comparable to that of linear SVMs which obtain current state-of-the-art performance. Experimentally we study the generalization performance to classes that were not used to learn the metrics. Using a metric learned on 1,000 classes, we show results for the ImageNet-10K dataset which contains 10,000 classes, and obtain performance that is competitive with the current state-of-the-art, while being orders of magnitude faster.

Published
2013
Full Text
View/download PDF

50. Supporting shared representations in collaborative activities: Introduction to the Special issue

Author

Jean-François Boujut, Frederic Roulland, Stefania Castellani, Jutta Willamowski, Conception collaborative (G-SCOP_CC), Laboratoire des sciences pour la conception, l'optimisation et la production (G-SCOP), Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), Xerox Research Centre Europe [Meylan], and Xerox Company

Subjects
0209 industrial biotechnology, Computer science, [SHS.INFO]Humanities and Social Sciences/Library and information sciences, [PHYS.MECA.GEME]Physics [physics]/Mechanics [physics]/Mechanical engineering [physics.class-ph], Human Factors and Ergonomics, 02 engineering and technology, Troubleshooting, Space (commercial competition), Education, World Wide Web, 020901 industrial engineering & automation, Health care, Product design, Emergency management, business.industry, 05 social sciences, General Engineering, 050301 education, Subject (documents), Object (computer science), [SPI.MECA.GEME]Engineering Sciences [physics]/Mechanics [physics.med-ph]/Mechanical engineering [physics.class-ph], Human-Computer Interaction, Hardware and Architecture, Mediation, [SCCO.PSYC]Cognitive science/Psychology, business, 0503 education, Software
Abstract

International audience; In many collaborative activities related to problem framing or solving, shared representations of the subject/object of the work provide some sort of mediation capability to the participants while performing their activity. Particularly the status and history of these shared representations are often central to the activities (O'Neill et al., 2011). Examples of such collaborative activities include online video or music creation, product design, emergency management diagnostics in healthcare, and remote device troubleshooting. Many other examples can be found in domains where an activity is carried out collectively and distributed over time and/or space.

Published
2013
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results