Search

Your search keyword '"Faculty of Electrical Engineering and Computing [Zagreb] (FER)"' showing total 12 results
Start Over Author "Faculty of Electrical Engineering and Computing [Zagreb] (FER)" Topic 020201 artificial intelligence & image processing
12 results on '"Faculty of Electrical Engineering and Computing [Zagreb] (FER)"'

1. Sparse weakly supervised models for object localization in road environment

Author

Siniša Šegvić, Valentina Zadrija, Jakob Verbeek, Josip Krapac, Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, 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]), ANR-16-CE23-0006,Deep_in_France,Réseaux de neurones profonds pour l'apprentissage(2016), and ANR-11-LABX-0025,PERSYVAL-lab,Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique(2011)

Subjects
Normalization (statistics), Computer science, Scale-invariant feature transform, 02 engineering and technology, Weak supervision, Overfitting, Image (mathematics), Object localization, Sparse models, Convolutional features, 0202 electrical engineering, electronic engineering, information engineering, Representation (mathematics), Geographic information system (GIS), Fisher Vectors, business.industry, Perspective (graphical), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Object localization Weak supervision Fisher vectors Sparse models Convolutional features Geographic information system (GIS) OpenStreetMap, 020207 software engineering, Percentage point, Pattern recognition, OpenStreetMap, Signal Processing, Metric (mathematics), 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software
Abstract

We propose a novel weakly supervised localization method based on Fisher-embedding of low-level features (CNN, SIFT), and model sparsity at the component level. Fisher-embedding provides an interesting alternative to raw low-level features, since it allows fast and accurate scoring of image subwindows with a model trained on entire images. Model sparsity reduces overfitting and enables fast evaluation. We also propose two new techniques for improving performance when our method is combined with nonlinear normalizations of the aggregated Fisher representation of the image. These techniques are (i) intra-component metric normalization and (ii) first-order approximation to the score of a normalized image representation. We evaluate our weakly supervised localization method on real traffic scenes acquired from driver’s perspective. The method dramatically improves the localization AP over the dense non-normalized Fisher vector baseline (16 percentage points for zebra crossings, 21 percentage points for traffic signs) and leads to a huge gain in execution speed (91 × for zebra crossings, 74 × for traffic signs).

Published
2018

2. Accurate Equivalent-Circuit Descriptions of Thin Glide-Symmetric Corrugated Metasurfaces

Author

Zvonimir Sipus, Oscar Quevedo-Teruel, Guido Valerio, Anthony Grbic, Laboratoire d'Electronique et Electromagnétisme (L2E), Université Pierre et Marie Curie - Paris 6 (UPMC), Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, Department of Electrical Engineering and Computer Science (EECS), University of Michigan [Ann Arbor], University of Michigan System-University of Michigan System, Department of Electromagnetic Engineering [Stockholm], Royal Institute of Technology [Stockholm] (KTH ), and ANR-16-CE24-0030,HOLeYMETA,Modélisation et Conception de Métasurfaces Creuses(2016)

Subjects
Floquet theory, Materials science, transverse reso- nance method, Equivalent circuit, homogenization, transverse resonance method, dispersive analysis, corrugated surfaces, metasurfaces, planar lenses, glide symmetry, Band gap, Physics::Optics, 02 engineering and technology, Homogenization (chemistry), law.invention, Planar, Optics, law, 0202 electrical engineering, electronic engineering, information engineering, Electrical and Electronic Engineering, business.industry, 020206 networking & telecommunications, Parallel plate, [SPI.ELEC]Engineering Sciences [physics]/Electromagnetism, 020201 artificial intelligence & image processing, Index Terms-Equivalent circuit, business, Waveguide
Abstract

International audience; Thin artificial surfaces that act as high frequency bandgap structures have been recently studied for the design of gap waveguides, hard surfaces, and planar lenses. Here, we propose a circuit-based method to analyze glide-symmetric corrugated metasurfaces that are embedded in a thin parallel plate waveguide. Our closed-form solution is based on rigorous analytical derivations. It achieves remarkable agreement with full-wave solvers, even when the waveguide thickness is extremely thin. In contrast, classical homogenization approaches are shown to be inaccurate for thin waveguides due to the interaction of higher order Floquet modes between the surfaces. Numerical results validate our theoretical analysis and show the utility of the proposed method.

Published
2017

3. Time-Domain Response Simulation of Incident Field Coupling to Transmission Lines

Author

Adrijan Baric, Sjoerd Oprt Land, Tvrtko Mandic, Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, ESEO - RF-EMC (RF-EMC), ESEO-Tech, and Université Bretagne Loire (UBL)-Université Bretagne Loire (UBL)

Subjects
Electromagnetic field, Field (physics), Acoustics, 02 engineering and technology, 01 natural sciences, [SPI]Engineering Sciences [physics], Transmission line, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, convolution, Impulse response, 010302 applied physics, Physics, Coupling, transmission lines, EM field coupling, Transverse plane, [SPI.ELEC]Engineering Sciences [physics]/Electromagnetism, Electric power transmission, TEM cell, incident electromagnetic field, 020201 artificial intelligence & image processing, measurements, EM field coupling, incident electromagnetic field, transient analysis, Voltage
Abstract

International audience; This paper presents an analysis of time-domain electromagnetic (EM) field coupling to transmission lines. The time-domain 3D EM simulation of the field-to-line coupling system is performed using the uniform plane wave excitation defined by the broadband Gaussian pulse. An analytic background is given to justify usage of the simulated time-domain response as an impulse response of the field-to-line coupling system. The simulated impulse response relates the induced voltages at the transmission line terminals to the EM plane wave excitation. By knowing the impulse response it is possible to predict induced terminal voltages for arbitrarily defined time-domain EM fields. This approach is validated by measurements of the EM field coupling in a transverse electromagnetic mode (TEM) cell and on a printed circuit board (PCB) transmission lines. Very good agreement is obtained between the measured results and results obtained by the convolution for various orientations of the transmission lines and various load impedances.

Published
2019

4. Improving Side-Channel Analysis Through Semi-supervised Learning

Author

Karlo Knezevic, Annelie Heuser, Tania Richmond, Alan Jovic, Stjepan Picek, Delft University of Technology (TU Delft), Centre National de la Recherche Scientifique (CNRS), Threat Analysis and Mitigation for Information Security (TAMIS), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-LANGAGE ET GÉNIE LOGICIEL (IRISA-D4), 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)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-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)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, Bilgin, Begül, Fischer, Jean-Bernard, 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)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-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)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique)

Subjects
Profiling (computer programming), business.industry, Computer science, Side-channel analysis, Profiled attacks, Machine learning, Semi-supervised learning, Pattern recognition, Context (language use), 02 engineering and technology, Semi-supervised learning, 020202 computer hardware & architecture, Set (abstract data type), [INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR], Naive Bayes classifier, Multilayer perceptron, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, Noise (video), Side channel attack, business, Computer Science::Cryptography and Security
Abstract

International audience; The profiled side-channel analysis represents the most powerful category of side-channel attacks. In this context, the security eval-uator (i.e., attacker) gains access to a profiling device to build a precise model which is used to attack another device in the attacking phase. Mostly, it is assumed that the attacker has significant capabilities in the profiling phase, whereas the attacking phase is very restricted. We step away from this assumption and consider an attacker restricted in the profiling phase, while the attacking phase is less limited. We propose the concept of semi-supervised learning for side-channel analysis, where the attacker uses a small number of labeled measurements from the profiling phase as well as the unlabeled measurements from the attacking phase to build a more reliable model. Our results show that the semi-supervised concept significantly helps the template attack (TA) and its pooled version (TAp). More specifically, for low noise scenario, the results for machine learning techniques and TA are often improved when only a small number of measurements is available in the profiling phase, while there is no significant difference in scenarios where the supervised set is large enough for reliable classification. For high noise scenario, TAp and multilayer perceptron results are improved for the majority of inspected dataset sizes, while for high noise scenario with added countermeasures, we show a small improvement for TAp, Naive Bayes and multilayer per-ceptron approaches for most inspected dataset sizes. Current results go in favor of using semi-supervised learning, especially self-training approach, in side-channel attacks.

Published
2019

5. The Curse of Class Imbalance and Conflicting Metrics with Machine Learning for Side-channel Evaluations

Author

Picek, Stjepan, Heuser, Annelie, Jovic, Alan, Bhasin, Shivam, Regazzoni, Francesco, Delft University of Technology (TU Delft), Threat Analysis and Mitigation for Information Security (TAMIS), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-LANGAGE ET GÉNIE LOGICIEL (IRISA-D4), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-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)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-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)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Faculty of Informatics [Lugano], Università della Svizzera italiana = University of Italian Switzerland (USI), 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)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-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)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Temasek Laboratories @ NTU, 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)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique)

Subjects
lcsh:Computer engineering. Computer hardware, lcsh:T58.5-58.64, lcsh:Information technology, Imbalanced datasets, 010401 analytical chemistry, 020206 networking & telecommunications, lcsh:TK7885-7895, Profiled side-channel attacks, 02 engineering and technology, 01 natural sciences, 0104 chemical sciences, 020202 computer hardware & architecture, [INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR], 0202 electrical engineering, electronic engineering, information engineering, Computer science and engineering [Engineering], 020201 artificial intelligence & image processing, Synthetic examples, Metrics, Profiled Side-Channel Attacks, Imbalanced Datasets, SMOTE
Abstract

We concentrate on machine learning techniques used for profiled sidechannel analysis in the presence of imbalanced data. Such scenarios are realistic and often occurring, for instance in the Hamming weight or Hamming distance leakage models. In order to deal with the imbalanced data, we use various balancing techniques and we show that most of them help in mounting successful attacks when the data is highly imbalanced. Especially, the results with the SMOTE technique are encouraging, since we observe some scenarios where it reduces the number of necessary measurements more than 8 times. Next, we provide extensive results on comparison of machine learning and side-channel metrics, where we show that machine learning metrics (and especially accuracy as the most often used one) can be extremely deceptive. This finding opens a need to revisit the previous works and their results in order to properly assess the performance of machine learning in side-channel analysis., IACR Transactions on Cryptographic Hardware and Embedded Systems, Volume 2019, Issue 1

Published
2018

6. Side-channel analysis and machine learning: A practical perspective

Author

Annelie Heuser, Domagoj Jakobovic, Nele Mentens, Simone A. Ludwig, Alan Jovic, Sylvain Guilley, Stjepan Picek, Computer Security and Industrial Cryptography [KU Leuven] (ESAT-COSIC), Department of Electrical Engineering [KU Leuven] (KU-ESAT), Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven)-Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), IMEC (IMEC), Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), Threat Analysis and Mitigation for Information Security (TAMIS), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-LANGAGE ET GÉNIE LOGICIEL (IRISA-D4), 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)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-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)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, Computer Science Department [Dakota] (North Dakota State University), North Dakota State University (NDSU), Télécom ParisTech, Secure-IC S.A.S, Institut Mines-Télécom [Paris] (IMT), 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)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Université de Bretagne Sud (UBS)-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)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-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)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1)

Subjects
business.industry, Computer science, Online machine learning, 02 engineering and technology, computer.software_genre, Machine learning, 020202 computer hardware & architecture, [INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR], 0202 electrical engineering, electronic engineering, information engineering, side-channel analysis, machine learning techniques, profiling, parameter tuning, data mining, 020201 artificial intelligence & image processing, Artificial intelligence, Data mining, Side channel attack, business, computer, ComputingMilieux_MISCELLANEOUS
Abstract

The field of side-channel analysis has made significant progress over time. Side-channel analysis is now used in practice in design companies as well as in test laboratories, and the security of products against side-channel attacks has significantly improved. However, there are still some remaining issues to be solved for side-channel analysis to become more effective. Side-channel analysis consists of two steps, commonly referred to as identification and exploitation. The identification consists of understanding the leakage and building suitable models. The exploitation consists of using the identified leakage models to extract the secret key. In scenarios where the model is poorly known, it can be approximated in a profiling phase. There, machine learning techniques are gaining value. In this paper, we conduct extensive analysis of several machine learning techniques, showing the importance of proper parameter tuning and training. In contrast to what is perceived as common knowledge in unrestricted scenarios, we show that some machine learning techniques can significantly outperform template attacks when properly used. We therefore stress that the traditional worst case security assessment of cryptographic implementations, that mainly includes template attacks, might not be accurate enough. Besides that, we present a new measure called the Data Confusion Factor that can be used to assess how well machine learning techniques will perform on a certain dataset.

Published
2017

7. 3D Structured Light Scanner on the Smartphone

Author

Simone Gasparini, Tomislav Petković, Matea Đonlić, Vincent Angladon, Tomislav Pribanić, Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, Real Expression Artificial Life (IRIT-REVA), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Institut National Polytechnique (Toulouse) (Toulouse INP), Project PHC COGITO 33059RF '3D RECONSTRUCTION WITH SMARPHONES', Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Sveučilište u Zagrebu (CROATIA), Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France), Campilho, A., Karray, F., and Institut National Polytechnique de Toulouse - INPT (FRANCE)

Subjects
structured light, Scanner, Computer science, pseudorandom dots pattern, 02 engineering and technology, smartphone, Speckle pattern, Computer graphics (images), 0202 electrical engineering, electronic engineering, information engineering, Traitement du signal et de l'image, Computer vision, 3D reconstruction, Projection (set theory), Pseudorandom number generator, business.industry, Structured light, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Smartphone, Pseudorandom dots pattern, Standard type, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

International audience; In the recent years turning smartphones into 3D reconstruction devices has been greatly investigated. Different 3D reconstruction concepts have been proposed, and one of the most popular is based on IR projection of a pseu-dorandom dots (speckle) pattern. We demonstrate our idea how a pseudoran-dom dots pattern can be used and we also present an active approach applying a structured light (SL) scanning on the smartphone. SL has a number of advantages compared to other 3D reconstruction concepts and likewise our smartphone implementation inherits the same advantages compared to other smartphone based solutions. The shown qualitative and quantitative results demonstrate the comparable outcome with the standard type SL scanner.

Published
2016

8. Patch-level Spatial Layout for Classification and Weakly Supervised Localization

Author

Josip Krapac, Siniša Šegvić, Jakob Verbeek, Valentina Zadrija, Gall, Juergen, Gehler, Peter, Leibe, Bastian, Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, 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), Juergen Gall, Peter Gehler, and Bastian Leibe

Subjects
Contextual image classification, Computer science, business.industry, Pipeline (computing), ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, 02 engineering and technology, State (functional analysis), object localization, weak supervision, Fisher vectors, Active appearance model, ComputingMethodologies_PATTERNRECOGNITION, Discriminative model, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Pairwise comparison, Visual Word, Artificial intelligence, Representation (mathematics), business
Abstract

International audience; We propose a discriminative patch-level spatial layout model suitable for training with weak supervision. We start from a block-sparse model of patch appearance based on the normalized Fisher vector representation. The appearance model is responsible for i) selecting a discriminative subset of visual words, and ii) identifying distinctive patches assigned to the selected subset. These patches are further filtered by a sparse spatial model operating on a novel representation of pairwise patch layout. We have evaluated the proposed pipeline in image classification and weakly supervised localization experiments on a public traffic sign dataset. The results show significant advantage of the proposed spatial model over state of the art appearance models.

Published
2016

9. Visualization of temporal text collections based on Correspondence Analysis

Author

Jean-Hugues Chauchat, Bojana Dalbelo Bašić, Artur Šilić, Annie Morin, Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, 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), Equipe de Recherche en Ingénierie des Connaissances (ERIC), Université Lumière - Lyon 2 (UL2), suite projet EGIDE Lyon2-Zagreb, 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
Computer science, Text analytics, 02 engineering and technology, Singular Value Decomposition, Correspondence analysis, Clustering, information visualization, singular value decomposition, clustering, text analytics, Information visualization, Text mining, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Artificial Intelligence, Robustness (computer science), 0202 electrical engineering, electronic engineering, information engineering, Cluster analysis, Information retrieval, business.industry, General Engineering, Centroid, 020207 software engineering, Computer Science Applications, Temporal database, Visualization, Data set, 020201 artificial intelligence & image processing, business
Abstract

International audience; In this paper, we present CatViz--Temporally-Sliced Correspondence Analysis Visualization. This novel method visualizes relationships through time and is suitable for large-scale temporal multivariate data. We couple CatViz with clustering methods, whereupon we introduce the concept of final centroid transfer, which enables the correspondence of clusters in time. Although CatViz can be used on any type of temporal data, we show how it can be applied to the task of exploratory visual analysis of text collections. We present a successful concept of employing feature-type filtering to present different aspects of textual data. We performed case studies on large collections of French and English news articles. In addition, we conducted a user study that confirms the usefulness of our method. We present typical tasks of exploratory text analysis and discuss application procedures that an analyst might perform. We believe that CatViz is general and highly applicable to large data sets because of its intuitiveness, effectiveness, and robustness. We expect that it will enable a better understanding of texts in huge historical archives.

Published
2012

10. Towards consolidated presence

Author

Tudor Groza, Antoine Zimmermann, Keith Griffin, Siegfried Handschuh, Owen Friel, Brendan Jennings, Manfred Hauswirth, Ivana Podnar Zarko, Pat Hession, Jérôme Euzenat, Axel Polleres, Digital Enterprise Research Institute (DERI-NUIG), National University of Ireland [Galway] (NUI Galway), Computer mediated exchange of structured knowledge (EXMO), 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 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]), Cisco Systems [Galway], CISCO Systems, Inc, Telecommunications Software & Systems Group (TSSG), Waterford Institute of Technology (WIT), Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, 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)-Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-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), and 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)

Subjects
Collaborative software, Service (systems architecture), Knowledge management, business.industry, Computer science, [INFO.INFO-WB]Computer Science [cs]/Web, 020206 networking & telecommunications, Context (language use), 02 engineering and technology, Semantics, Sketch, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, The Internet, business, Business communication, presence service, XMPP, SIP, Internet presence management
Abstract

hauswirth2010a; International audience; Presence management, i.e., the ability to automatically identify the status and availability of communication partners, is becoming an invaluable tool for collaboration in enterprise contexts. In this paper, we argue for efficient presence management by means of a holistic view of both physical context and virtual presence in online communication channels. We sketch the components for enabling presence as a service integrating both online information as well as physical sensors, discussing benefits, possible applications on top, and challenges of establishing such a service.

Published
2010

11. Textual features for corpus visualization using correspondence analysis

Author

Sasa Petrovic, Blaž Zupan, Bojana Dalbelo Bašić, Jean-Hugues Chauchat, Annie Morin, Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, 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), Faculty of Computer and Information Science [Ljubljana], University of Ljubljana, Equipe de Recherche en Ingénierie des Connaissances (ERIC), Université Lumière - Lyon 2 (UL2), 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), and 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

Subjects
Text mining, Computer science, text mining, text visualization, letter n-grams, word n-grams, correspondence analysis, Feature vector, media_common.quotation_subject, 02 engineering and technology, computer.software_genre, Correspondence analysis, Theoretical Computer Science, Text visualization, Artificial Intelligence, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], 0202 electrical engineering, electronic engineering, information engineering, ACM: G.: Mathematics of Computing/G.3: PROBABILITY AND STATISTICS/G.3.0: Contingency table analysis, Representation (mathematics), media_common, Letter n-grams, Creative visualization, business.industry, Dimensionality reduction, 05 social sciences, [STAT.TH]Statistics [stat]/Statistics Theory [stat.TH], Visualization, ComputingMethodologies_DOCUMENTANDTEXTPROCESSING, Word n-grams, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, 0509 other social sciences, 050904 information & library sciences, business, Co-occurrence networks, computer, Natural language processing, Word (computer architecture)
Abstract

International audience; Explorative data analysis in text mining essentially relies on effective visualization techniques which can expose hidden relationships among documents and reveal correspondence between documents and their features. In text mining, the documents are most often represented by feature vectors of very high dimensions, requiring dimensionality reduction to obtain visual projections in two- or three-dimensional space. Correspondence analysis is an unsupervised approach that allows for construction of low-dimensional projection space with simultaneous placement of both documents and features, making it ideal for explorative analysis in text mining. Its present use, however, has been limited to word-based features. In this paper, we investigate how this particular document representation compares to the representation with letter n-grams and word n-grams, and find that these alternative representations yield better results in separating documents of different class. We perform our experimental analysis on a bilingual Croatian-English parallel corpus, allowing us to additionally explore the impact of features in different languages on the quality of visualizations.

Published
2009

12. Camera parameter initialization for 3D kinematic systems

Author

Peter Sturm, Tomislav Pribanić, Mario Cifrek, Lončarić, Sven, Babić, Hrvoje, Bellanger, Maurice, Faculty of Electrical Engineering and Computing [Zagreb] (FER), University of Zagreb, Modeling, localization, recognition and interpretation in computer vision (MOVI), Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble (GRAVIR - IMAG), Université Joseph Fourier - Grenoble 1 (UJF)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Inria Grenoble - Rhône-Alpes, and Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Robot calibration, Iterative method, Computer science, Calibration (statistics), 0206 medical engineering, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Initialization, camera calibration, 3D kinematic system, 02 engineering and technology, Iterative reconstruction, Camera auto-calibration, cameras, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, business.industry, 3D reconstruction, Astrophysics::Instrumentation and Methods for Astrophysics, calibration, image reconstruction, 020601 biomedical engineering, [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR], iterative methods, 020201 artificial intelligence & image processing, Artificial intelligence, business, Camera resectioning
Abstract

International audience; 3D scene information can be extracted from images acquired by cameras. Before doing the actual reconstruction, camera calibration has to be done. Reconstruction accuracy is highly dictated by the calibration. Two typical demands, which are not easily simultaneously satisfied, are: calibration has to be done in a fast and convenient manner and yet assure a high degree of reconstruction accuracy. The computational part of calibration usually includes the initialization of camera parameters and refinement based on an initial set of values. The goodness of the initial set greatly affects the refinement procedure in terms of convergence speed and ultimately reconstruction accuracy. This work proposes a new calibration method for 3D kinematic systems. It shortens the commonly used calibration procedure, gives better initial parameter values for the refinement procedure which in turn is supposed to assure faster and safer convergence of the iterative minimization algorithm. Additionally, it is shown that even without parameter refinement the proposed method gives more accurate 3D reconstruction output.

Published
2005

Catalog

Books, media, physical & digital resources
See catalog results