|
| Sabrina Tollari Maître de conférences / Associate professor Sorbonne Université
UMR CNRS 7606 - LIP6
sabrina.tollari@lip6.fr
Tel.: 01 44 27 87 49, Fax: 01 44 27 70 00 | | Campus Pierre et Marie Curie Boite courrier 169 4 place Jussieu 75252 PARIS cedex 05 Couloir 26-00, Bureau 508
|
Research
- Theme: Image indexing and retrieval by combining visual and textual informations
Thème: Indexation et recherche d'images par combinaison d'informations textuelles et visuelles
- Keywords: Web image indexing and retrieval, semantic gap, feature selection (LDA, MMD), automatic image annotation, visual concept detection
Mots clés : indexation et recherche d'images web, fossé sémantique, sélection des dimensions (LDA, MMD), annotation automatique d'images, détection de concepts visuels
- Projects: Projet DIGITEO RELIR 2010-2013, ANR MDCA AVEIR 2007-2009
- Evaluation campaigns: ImageCLEF 2008-2010, ImagEVAL 2006
Content-based (using only visual features) and text-based (using only textual features) image retrieval are two different approaches to retrieve images.
A middle approach consists to combine text and visual information in the same framework. My work takes place in this context and includes image annotation [1], visual concept detection and filtering [2] [3], early and late fusion of text and image features [4] [5] [6], visual feature selection [7] [8], image classification [9] and diversity [10] [11].
Publications sort by year, type, year&type, theme
International Journal
- David Buffoni, Sabrina Tollari, Patrick Gallinari,
"A Learning to Rank framework applied to text-image retrieval",
Multimedia Tools and Applications,
Volume 60, Number 1, pages 161-180, 2012
[DOI] [BIB]
- Hervé Glotin, Sabrina Tollari, Pascale Giraudet,
"Shape reasoning on mis-segmented and mis-labeled objects using approximated Fisher criterion",
Computers & Graphics,
Special Issue Shape Reasoning and Understanding, Elsevier, Vol 30, No. 2, pages 177-184, April 2006
[DOI] [BIB]
- Sabrina Tollari, Hervé Glotin, Jacques Le Maitre,
"Enhancement of Textual Images Classification using Segmented Visual Contents for Image Search Engine",
Multimedia Tools and Applications,
Vol.25, No.3, pages 405-417, March 2005
[PDF] [DOI] [BIB]
International Conference
- Sabrina Tollari, Marcin Detyniecki, Christophe Marsala, Ali Fakeri-Tabrizi, Massih-Reza Amini, Patrick Gallinari,
"Exploiting Visual Concepts to Improve Text-Based Image Retrieval",
European Conference on Information Retrieval (ECIR),
LNCS 5478, pages 701-705, Toulouse, April 2009
[DOI] [PDF] [BIB]
- Sabrina Tollari, Hervé Glotin,
"Learning optimal visual features from web sampling in online image retrieval",
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),
Las Vegas, USA, pages 1229-1232, March 2008
[POSTER] [DOI] [BIB]
- David Buffoni, Sabrina Tollari, Patrick Gallinari,
"The importance of the depth for text-image selection strategy in Learning to Rank",
European Conference on Information Retrieval (ECIR 2011),
Dublin, April 2011
[DOI] [POSTER] [BIB]
- Jiang Bu, Song-Yang Lao, Liang Bai, Sabrina Tollari, Christophe Marsala,
"Real-time Billboard Trademark Detection and Recognition in Sports Video",
International Conference on Information and Multimedia Technology (ICIMT 2010),
Hong-Kong, December 2010
[BIB]
- Jiang Bu, Song-Yang Lao, Liang Bai, Sabrina Tollari, Christophe Marsala,
"Goalmouth Detection in Field-Ball Game Video Using Fuzzy Decision Tree",
International Conference on Image and Graphics,
Xi'an, China, September 2009
[DOI] [BIB]
- Sabrina Tollari, Hervé Glotin,
"Web Image Retrieval on ImagEVAL: Evidences on visualness and textualness concept dependency in fusion model",
ACM International Conference on Image and Video Retrieval (ACM CIVR),
pages 65-72, Amsterdam, The Netherlands, July 2007
[PPT] [DOI] [BIB]
- Sabrina Tollari, Hervé Glotin,
"LDA versus MMD Approximation on Mislabeled Images for Keyword Dependant Selection of Visual Features and their Heterogeneity",
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP),
Vol. II, pages 413-416, Toulouse, France, May 2006
[POSTER] [DOI] [BIB]
- Hervé Glotin, Sabrina Tollari, Pascale Giraudet,
"Approximation of Linear Discriminant Analysis for Word Dependent Visual Features Selection",
Advanced Concepts for Intelligent Vision Systems (ACIVS),
LNCS 3708, Springer, pages 170-177, Antwerp, Belgium, September 2005
[FLY] [POSTER] [DOI] [BIB]
Book Chapter
- Hichem Sahbi, Xi Li, Sabrina Tollari, Hervé Glotin, Philippe Mulhem, Ali Fakeri-Tabrizi, Zhao Zhong-Qiu, Patrick Gallinari,
"Apprentissage automatique pour l'annotation d'images",
Sémantique et multimodalité en analyse de l'information,
pages 367-381, 2011
[Book] [BIB]
- Ali Fakeri-Tabrizi, Sabrina Tollari, Nicolas Usunier, Patrick Gallinari,
"Improving Image Annotation in Imbalanced Classification Problems with Ranking SVM",
Multilingual Information Access Evaluation Vol. II Multimedia Experiments,
LNCS 6242/2010, pages 291-294, 10th Workshop of the Cross-Language Evaluation Forum, CLEF 2009, Corfu, Greece, Revised Selected Papers 2010
[DOI] [BIB]
- Sabrina Tollari, Philippe Mulhem, Marin Ferecatu, Hervé Glotin, Marcin Detyniecki, Patrick Gallinari, Hichem Sahbi, Zhong-Qiu Zhao,
"A Comparative Study of Diversity Methods for Hybrid Text and Image Retrieval Approaches",
Evaluating Systems for Multilingual and Multimodal Information Access,
LNCS 5706/2009, pages 585-592, 9th Workshop of the Cross-Language Evaluation Forum, CLEF 2008: Aarhus, Denmark, Revised Selected Papers 2009
[DATA] [PDF] [DOI] [BIB]
- Sabrina Tollari, Marcin Detyniecki, Ali Fakeri-Tabrizi, Christophe Marsala, Massih-Reza Amini, Patrick Gallinari,
"Using Visual Concepts and Fast Visual Diversity to Improve Image Retrieval",
Evaluating Systems for Multilingual and Multimodal Information Access,
LNCS 5706/2009, pages 577-584, 9th Workshop of the Cross-Language Evaluation Forum, CLEF 2008: Aarhus, Denmark, Revised Selected Papers 2009
[PDF] [DOI] [BIB]
International Workshop
- Sabrina Tollari, Marcin Detyniecki, Ali Fakeri-Tabrizi, Massih-Reza Amini, Patrick Gallinari,
"UPMC/LIP6 at ImageCLEFphoto 2008: on the exploitation of visual concepts (VCDT)",
QUAERO/ImageCLEF Workshop on Multimedia Information Retrieval Evaluation,
Aarhus, Denmark, September 2008
[PPT] [BIB]
- Christian Kuoman, Sabrina Tollari, Marcin Detyniecki,
"Using tree of concepts and hierarchical reordering for diversity in image retrieval",
International Workshop on Content-Based Multimedia Indexing (CBMI 2013),
Veszprém, Hungary, June 2013
[DOI] [BIB]
- Sabrina Tollari, Hervé Glotin,
"WISTI: a simple efficient Textuo-Visual Web Image Retrieval model - Specifications and Benchmarks",
Workshop ImagEVAL in conjonction with ACM CIVR2007,
Amsterdam, The Netherlands, July 2007
[PDF] [BIB]
- Hervé Glotin, Sabrina Tollari,
"Fast Image Auto-annotation with Visual Vector Approximation Clusters",
Workshop on Content-Based Multimedia Indexing (CBMI),
Riga, Latvia, June 2005
[PDF] [POSTER] [DATA] [BIB]
- Sabrina Tollari, Hervé Glotin, Jacques Le Maitre,
"Enhancement of Textual Images Classification using their Global and Local Visual Contents",
OOIS 2003 Workshop on Metadata and Adaptability in Web-based Information Systems (MAWIS),
pages 71-83, Geneva, Switzerland, September 2003
[PDF] [BIB]
Working Note
- Ali Fakeri-Tabrizi, Sabrina Tollari, Nicolas Usunier, Patrick Gallinari,
"UPMC/LIP6 at ImageCLEFannotation 2010",
CLEF (Notebook Papers/LABs/Workshops),
2010
[PDF] [BIB]
- Hervé Glotin, Ali Fakeri-Tabrizi, Philippe Mulhem, Marin Ferecatu, Zhong-Qiu Zhao, Sabrina Tollari, Georges Quenot, Hichem Sahbi, Emilie Dumont, Patrick Gallinari,
"Comparison of Various AVEIR Visual Concept Detectors with an Index of Carefulness",
CLEF working notes 2009,
2009
[PDF] [BIB]
- Ali Fakeri-Tabrizi, Sabrina Tollari, Ludovic Denoyer, Patrick Gallinari,
"UPMC/LIP6 at ImageCLEFannotation 2009: Large Scale Visual Concept Detection and Annotation",
CLEF working notes 2009,
2009
[PDF] [POSTER] [BOASTER] [BIB]
- Sabrina Tollari, Marcin Detyniecki, Marin Ferecatu, Hervé Glotin, Philippe Mulhem, Massih-Reza Amini, Ali Fakeri-Tabrizi, Patrick Gallinari, Hichem Sahbi, Zhong-Qiu Zhao,
"Consortium AVEIR at ImageCLEFphoto 2008: on the fusion of runs",
Working Notes for the CLEF 2008 workshop,
2008
[PDF] [BIB]
- Sabrina Tollari, Marcin Detyniecki, Ali Fakeri-Tabrizi, Massih-Reza Amini, Patrick Gallinari,
"UPMC/LIP6 at ImageCLEFphoto 2008: on the exploitation of visual concepts (VCDT)",
Working Notes for the CLEF 2008 workshop,
2008
[PDF] [POSTER] [BIB]
- Ali Fakeri-Tabrizi, Massih-Reza Amini, Sabrina Tollari, Patrick Gallinari,
"UPMC/LIP6 at ImageCLEF's WikipediaMM: An Image-Annotation Model for an Image Search-Engine",
Working Notes for the CLEF 2008 workshop,
2008
[PDF] [BIB]
- Christian Kuoman, Sabrina Tollari, Marcin Detyniecki,
"UPMC at MediaEval2013: Relevance by text and diversity by visual clustering",
MediaEval 2013 Workshop,
Barcelon, Spain, October 2013
[PDF] [BIB]
National Journal
- Sabrina Tollari, Marcin Detyniecki, Ali Fakeri-Tabrizi, Christophe Marsala, Massih-Reza Amini, Patrick Gallinari,
"Exploitation du contenu visuel pour améliorer la recherche textuelle d'images en ligne",
RSTI - Document Numérique - 13/2010. Recherche d'information,
pages 187-209, 2010
[Journal] [abstract] [BIB]
- Jiang Bu, Song-Yang Lao, Liang Bai, Sabrina Tollari, Christophe Marsala,
"一种体育视频中广告牌商标的实时识别算法 (A Real-time Billboard Trademark Recognition Algorithm in Sports Video)",
自动化学报(Acta Automatica Sinica),
Vol.37, No.4, pp. 418-426, April 2011
[PDF] [URL] [DOI] [BIB]
- Sabrina Tollari, Hervé Glotin,
"Sélection adaptative des dimensions de l'indexation visuelle d'images mal annotées en fonction du mot recherché",
Ingénierie des Systèmes d'Information (RSTI-ISI),
Numéro Spécial "Passage à l'Echelle", Hermès, Vol. 11/4, pages 55 à 80, Novembre 2006
[DOI] [BIB]
National Conference
- Sabrina Tollari, Marcin Detyniecki, Ali Fakeri-Tabrizi, Christophe Marsala, Massih-Reza Amini, Patrick Gallinari,
"Utilisation de concepts visuels et de la diversité visuelle pour améliorer la recherche d'images",
Actes de Conférence en Recherche d'Informations et Applications (CORIA'09),
Toulon, France, Mai 2009
[PDF] [PPT] [BIB]
- Sabrina Tollari, Hervé Glotin,
"Recherche visuo-textuelle d'images sur le Web améliorée par sélection de la dimension",
Actes de Conférence en Recherche d'Informations et Applications (CORIA'08),
Tregastel, France, Mars 2008
[PDF] [PPT] [BIB]
- Sabrina Tollari, Hervé Glotin,
"Designing Text and Content Based Web Image Retrieval with Online Approximated Feature Selection",
Actes des Journées Bases de Données Avancées (BDA2008),
Guilherand-Granges, France, Octobre 2008
[BIB]
- Christian Kuoman, Sabrina Tollari, Marcin Detyniecki,
"Diversité hiérarchique et utilisation d’arbres de concepts pour la recherché d’images",
Actes de Conférence en Recherche d'Informations et Applications (CORIA'13),
Neuchatel, Suisse, Avril 2013
[PDF] [BIB]
- Sabrina Tollari, Hervé Glotin, Pascale Giraudet,
"Fusion aprés sélection mot-clé dépendante des traits visuels et de leur hétérogénéité par LDA approximée pour filtrer l'indexation d'images",
Congrès francophone AFRIF-AFIA Reconnaissance des Formes et Intelligence Artificielle (RFIA),
Tours, Janvier 2006
[PDF] [DIGEST] [PPT] [BIB]
- Sabrina Tollari,
"Filtrage de l'indexation textuelle d'une image au moyen du contenu visuel pour un moteur de recherche d'images sur le web",
Actes de Conférence en Recherche d'Informations et Applications (CORIA'05),
pages 261-275, Grenoble, Mars 2005
[PDF] [PPT] [BIB]
- Sabrina Tollari, Hervé Glotin, Jacques Le Maitre,
"Rehaussement de la classification textuelle d'images par leur contenu visuel",
Congrès francophone AFRIF-AFIA Reconnaissance des Formes et Intelligence Artificielle (RFIA),
pages 1383-1392, Toulouse, Janvier 2004
[PDF] [DIGEST] [PPT] [BIB]
National Workshop
- Sabrina Tollari, Hervé Glotin,
"Sélection adaptative des descripteurs visuels et dérivation de métadescripteurs contextuels dépendant du mot-clé pour l'indexation automatique d'images",
Atelier MetSI'05 lié à INFORSID2005,
pages 49-58, Grenoble, Mai 2005
[PDF] [PPT] [BIB]
Master and PhD Thesis
- Sabrina Tollari,
"Indexation et recherche d'images par fusion d'informations textuelles et visuelles (Image indexing and retrieval by combining textual and visual informations)",
thèse de doctorat,
Université du Sud Toulon-Var, soutenue le 24 octobre, 2006
[HTML] [PDF] [PPT] [BIB]
- Sabrina Tollari,
"Rehaussement de la classification textuelle d'une base de données photographiques par son contenu visuel (Heightening of textual classification of a photographic data base by its visual contents)",
mémoire de DEA informatique,
Université du Sud Toulon-Var (DEA de Marseille-Luminy), juin 2003
[HTML] [PDF] [PPT] [BIB]
Other publications
- Sabrina Tollari, Hervé Glotin,
"Image Classification from Mislabeled Database Improved by LDA Approximation of Usual and Heterogeneity Features",
GESTS International Transactions on Computer Science and Engineering,
Vol.23, No.1, pages 172-184, November 2005
[LINK] [BIB]
Research Report
- Sabrina Tollari,
"UPMC/LIP6 at ImageCLEFphoto 2009",
LIP6 Internal Report,
2009
[PDF] [BIB]
- Sabrina Tollari, Hervé Glotin,
"WISTI: Web Image Search by Text and Image content",
internal report LSIS, LSIS.RR.2007.003,
2007
[BIB]
- Sabrina Tollari, Hervé Glotin,
"Keyword dependant selection of visual features and their heterogeneity for image content-based interpretation",
internal report LSIS, LSIS.RR.2005.003 (update 2006),
2005
[PDF] [BIB]
- Sabrina Tollari, Hervé Glotin, Pascale Giraudet,
"Approximation of Linear Fisher Discriminant Analysis for Adaptive Word Dependent Visual Feature Sets Improving Image Auto-annotation",
internal report LSIS, LSIS.RR.2005.002 (update 2006),
2005
[PDF] [BIB]
National Oral Presentation
- Sabrina Tollari,
"Annotation, indexation et recherche d'images par le texte et le contenu visuel",
LORIA, Nancy, 26 June 2009
[PPT]
- Sabrina Tollari,
"Automatic annotation and Visual concept Extraction for Image Retrieval",
Journée "Données et Apprentissage Artificiel" du LIP6, Paris, 23 March 2009
[PDF]
- Sabrina Tollari,
"UPMC/LIP6 at ImageCLEFphoto 2008",
Forum Apprentissage de l'équipe MALIRE, Paris, 23 October 2008
- Sabrina Tollari,
"Recherche combinée texte et image dans ImagEVAL",
Forum Apprentissage de l'équipe MALIRE, Paris, 11 October 2007
- Sabrina Tollari,
"Indexation et recherche d'images par combinaison d'informations textuelles et visuelles",
Séminaire DAPA, Paris, 4 October 2007
[PPT]
Others presentations
Miscellaneous
Teaching
J'effectue mes enseignements au sein de l'UFR d'Ingénierie de la Faculté des Sciences et Ingénierie de Sorbonne Université.
Enseignements 2015-2016
Sites web : L1 Cycle d'integration,
L2/L3 Informatique,
Master Informatique
|