Search

Showing total 5 results
Start Over Topic [info.info-it]computer science [cs]/information theory [cs.it] Topic recherche d'information Publication Year Range Last 10 years Publisher ieee
5 results

1. Video spatio-temporal filtering based on cameras and target objects trajectories - Videosurveillance forensic framework

Author

André Péninou, Florence Sèdes, Dana Codreanu, Institut National Polytechnique de Toulouse - INPT (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Systèmes d’Informations Généralisées (IRIT-SIG), 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, and Université Toulouse - Jean Jaurès (UT2J)

Subjects
Geodesic, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Set (abstract data type), Videosurveillance systems, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Selection (linguistics), Computer vision, Théorie de l'information, Metadata, Interpretation (logic), business.industry, Forensic tool, Spatio-temporal queries, Recherche d'information, 16. Peace & justice, Temporal filtering, [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT], [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], Trajectory, Transit network, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

International audience; This paper presents our work about assisting video-surveillance agents in the search for particular video scenes of interest in transit network. This work has been developed based on requirements defined within different projects with the French National Police in a forensic goal. The video-surveillance agent inputs a query in the form of a hybrid trajectory (date, time, locations expressed with regards to different reference systems) and potentially some visual descriptions of the scene. The query processing starts with the interpretation of the hybrid trajectory and continues with a selection of a set of cameras likely to have filmed the spatial trajectory. The main contributions of this paper are: (1) a definition of the hybrid trajectory query concept, trajectory that is constituted of geometrical and symbolic segments represented with regards to different reference systems (e.g., Geodesic system, road network), (2) a spatio-temporal filtering framework based on a spatio-temporal modeling of the transit network and associated cameras.

Published
2015

2. Document Re-ranking Based on Topic-Comment Structure

Author

Josiane Mothe, Liana Ermakova, Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), École supérieure du professorat et de l'éducation - Toulouse Midi-Pyrénées (ESPE Toulouse), Université Toulouse - Jean Jaurès (UT2J), Systèmes d’Informations Généralisées (IRIT-SIG), 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, and Institut National Polytechnique de Toulouse - INPT (FRANCE)

Subjects
Computer science, InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL, 02 engineering and technology, computer.software_genre, Ranking (information retrieval), Query expansion, 0202 electrical engineering, electronic engineering, information engineering, Information retrieval, Relevance (information retrieval), Document re-ranking, Document retrieval, tf–idf, Rheme, Information structure, 060201 languages & linguistics, Théorie de l'information, Concept search, business.industry, Topic, Comment, Recherche d'information, 06 humanities and the arts, Document clustering, 16. Peace & justice, [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT], [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0602 languages and literature, Vector space model, ComputingMethodologies_DOCUMENTANDTEXTPROCESSING, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, Natural language processing, Theme
Abstract

International audience; This paper introduces a novel approach for document re-ranking in information retrieval based on topic-comment structure of texts. While most information retrieval models make the assumption that relevant documents are about the query and that aboutness can be captured considering bags of words only, we rather consider a more sophisticated analysis of discourse to capture document relevance by distinguishing the topic of a text from what is said about the topic (comment) in the text. The topic-comment structure of texts is extracted automatically from the first retrieved documents which are then re-ranked so that the top documents are the ones that share their topics with the query. The evaluation on TREC collections shows that the method significantly improves the retrieval performance.

Published
2016

3. A Performance and Profit Oriented Data Replication Strategy for Cloud Systems

Author

Tolga Ayav, Abdelkader Hameurlain, Uras Tos, Riad Mokadem, Şebnem Bora, Optimisation Dynamique de Requêtes Réparties à grande échelle (IRIT-PYRAMIDE), 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, Izmir Institute of Technology (IZTECH), Ege University - EGE (Izmir, Turkey), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Ege University - EGE (TURKEY), Izmir Institute of Technology - IZTECH (TURKEY), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), TR114453, Tos, Uras, Ayav, Tolga, and Izmir Institute of Technology. Computer Engineering

Subjects
Economic benefit, Data replication, Profit (accounting), Operations research, Computer science, Process (engineering), Performance, Cloud computing, 02 engineering and technology, Computer security, computer.software_genre, Data modeling, 0202 electrical engineering, electronic engineering, information engineering, Théorie de l'information, business.industry, Bandwidth (signal processing), Performance guarantees, Response time, Recherche d'information, 020207 software engineering, Replication (computing), [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT], [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 020201 artificial intelligence & image processing, Profitability index, business, computer
Abstract

13th IEEE International Conference on Ubiquitous Intelligence and Computing, 13th IEEE International Conference on Advanced and Trusted Computing, 16th IEEE International Conference on Scalable Computing and Communications, IEEE International Conference on Cloud and Big Data Computing, IEEE International Conference on Internet of People and IEEE Smart World Congress and Workshops, UIC-ATC-ScalCom-CBDCom-IoP-SmartWorld 2016; UICToulouse; France; 18 July 2016 through 21 July 2016, In today's world, tenants of cloud systems expect timely responses to queries that process ever-increasing sizes of data. However, most cloud providers offer their services without any performance guarantees to their tenants. In this paper we propose a data replication strategy that aims to satisfy performance guarantees for the tenant while ensuring profitability of the cloud provider. Our strategy estimates the response time of the queries, as well as the expenditures that affect the profitability of the cloud provider. The decision of whether to perform replication is determined by the fulfillment of these two criteria. Validity of the proposed strategy is provided by means of a simulation study., TUBITAK

Published
2016

4. Accelerating the update of knowledge base instances by detecting vital information from a document stream

Author

Mohand Boughanem, Nathalie Hernandez, Karen Pinel-Sauvagnat, Rafik Abbes, Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Recherche d’Information et Synthèse d’Information (IRIT-IRIS), 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, MEthodes et ingénierie des Langues, des Ontologies et du DIscours (IRIT-MELODI), Université Toulouse - Jean Jaurès (UT2J), Systèmes d’Informations Généralisées (IRIT-SIG), and Université Toulouse III - Paul Sabatier (UT3)

Subjects
Théorie de l'information, Information retrieval, business.industry, Computer science, Open Knowledge Base Connectivity, 020207 software engineering, Recherche d'information, 02 engineering and technology, Linked data, Knowledge base updating, TREC temporal summarization, Knowledge-based systems, Knowledge base, Knowledge extraction, [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT], Vital information, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, Encyclopedia, 020201 artificial intelligence & image processing, The Internet, business
Abstract

With the growth of Linked Data, updating knowledge bases (KB) is becoming a crucial problem, particularly when representing the knowledge linked to permanently evolving instances. Many approaches have been proposed to extract new knowledge from textual documents in order to update existing KB. These approaches reach maturity but rely on the fact that the adequate corpus is already constructed. In most cases, the considered documents are manually selected which makes an exhaustive update of the KB difficult. In this paper, we propose an original approach to automatically detect from a document stream, pieces of information reporting new knowledge about instances of the KB.

Published
2015

5. Benchmark for OLAP on NoSQL Technologies

Author

Max Chevalier, Mohammed El Malki, Arlind Kopliku, Olivier Teste, Ronan Tournier, Systèmes d’Informations Généralisées (IRIT-SIG), 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, Université Toulouse III - Paul Sabatier (UT3), Capgemini [Toulouse], Capgemini, Université Toulouse - Jean Jaurès (UT2J), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Capgemini (FRANCE), and Institut National Polytechnique de Toulouse - INPT (FRANCE)

Subjects
Théorie de l'information, OLAP, Recherche d'information, NoSQL, Decision support systems, Data Warehouses, Big data, MongoDB, HBase, [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT], [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], H- INFORMATIQUE, Computer Science::Databases
Abstract

International audience; The plethora of data warehouse solutions has created a need comparing these solutions using experimental benchmarks. Existing benchmarks rely mostly on the relational data model and do not take into account other models. In this paper, we propose an extension to a popular benchmark (the Star Schema Benchmark or SSB) that considers non-relational NoSQL models. To avoid data post-processing required for using this data with NoSQL systems, the data is generated in different formats. To exploit at best horizontal scaling, data can be produced in a distributed file system, hence removing disk or partition sizes as limit for the generated dataset. Experimental work proves improved performance of our new benchmark.

Published
2015