Výsledky vyhledávání - "Tollari, Sabrina"

UPMC at MediaEval 2016 Retrieving Diverse Social Images Task

Autor: Tollari, Sabrina

Publikováno v: MediaEval 2016
MediaEval 2016 Workshop
MediaEval 2016 Workshop, Oct 2016, Hilversum, Netherlands

International audience; In the MediaEval 2016 Retrieving Diverse Social Images Task, we proposed a general framework based on agglomerative hierarchical clustering (AHC). We tested the provided credibility descriptors as a vector input for our AHC. T

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::43071fe46a6e7088f5ea150af44b5126
https://hal.sorbonne-universite.fr/hal-01395045/file/Tollari_MediaEval_2016.pdf

Zobrazit plný text záznamu

WISTI: a simple efficient Textuo-Visual Web Image Retrieval model - Specifications and Benchmarks

Autor: Tollari, Sabrina, Glotin, Hervé

Publikováno v: Workshop ImagEVAL 2006
Workshop ImagEVAL 2006, Jul 2007, France

In this article we specify the textual and visual algorithms that we developed and merged to design a simple efficient Textuo-Visual Web Image Retrieval System that we call WISTI (Web Image Search by Text and Image content). It integrates subband ent

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7d632c7a5a2708c055c84e66d437f03d
https://hal.archives-ouvertes.fr/hal-00199834

Zobrazit plný text záznamu

UPMC at MediaEval 2013: Relevance by Text and Diversity by Visual Clustering

Autor: Kuoman Mamani, Christian Antonio, Tollari, Sabrina, Detyniecki, Marcin

Publikováno v: MediaEval 2013 Multimedia Benchmark Workshop
MediaEval 2013 Multimedia Benchmark Workshop, Oct 2013, Barcelona, Spain

International audience; In the diversity task, our strategy was to, first, try to improve relevance, and then to cluster similar images to improve diversity. We propose a four step framework, based on AHC clustering and different reranking strategies

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::56960031160e3a0500f4e3b71cbd080c
https://hal.sorbonne-universite.fr/hal-00925153

Zobrazit plný text záznamu

Diversité hiérarchique et utilisation d'arbres de concepts pour la recherche d'images

Autor: Kuoman Mamani, Christian Antonio, Tollari, Sabrina, Detyniecki, Marcin

Publikováno v: Conference en Recherche d'Information et Applications (CORIA 2013)
Conference en Recherche d'Information et Applications (CORIA 2013), Apr 2013, Neuchâtel, Suisse

International audience; La recherche d'images est de plus en plus efficace, mais les résultats similaires ont tendance à se regrouper. Dans cet article, nous montrons comment améliorer la diversité des résultats en prenant en compte la nature in

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e686009f91c476a52f71e8f7cbb6b1f1
https://hal.sorbonne-universite.fr/hal-00925132

Zobrazit plný text záznamu

Apprentissage automatique pour l'annotation d'images

Autor: Sahbi, Hichem, Li, Xi, Tollari, Sabrina, Glotin, Hervé, Mulhem, Philippe, Fakeri-Tabrizi, Ali, Zhao, Zhong-Qiu, Gallinari, Patrick

Publikováno v: Sémantique et multimodalité en analyse de l'information
Marine Campedel, Pierre Hoogstoel. Sémantique et multimodalité en analyse de l'information, Hermès-Lavoisier, pp.367-381, 2011, Traité RTA, série Recherche d'information et web, 2-7462-3139-5

Chapitre 11; National audience

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ef9c04fa7704dab704e1a798889aa56f
https://hal.science/hal-00764235

Zobrazit plný text záznamu

A Real-time Billboard Trademark Recognition Algorithm in Sports Video

Autor: Bu, Jiang, Lao, Song-Yang, Bai, Liang, Tollari, Sabrina, Marsala, Christophe

Publikováno v: Acta Automatica Sinica
Acta Automatica Sinica, 2011, 37 (4), pp.418-426. ⟨10.3724/SP.J.1004.2011.00418⟩

International audience; Recently, in the sports video analysis domain, applications like TV commercials can be developed by detecting and recognizing the trademark on the billboard. In this paper, we propose a method for real-time trademark recogniti

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::dbef4331761459f532f3c3f9e75dcd16
https://hal.archives-ouvertes.fr/hal-01172509

Zobrazit plný text záznamu

Exploitation du contenu visuel pour améliorer la recherche textuelle d’images en lignes

Autor: Tollari, Sabrina, Detyniecki, Marcin, Fakeri-Tabrizi, Ali, Marsala, Christophe, Amini, Massih-Reza, Gallinari, Patrick

Les moteurs de recherche d’images sur le web utilisent principalement l’information textuelle associée aux images afin de retrouver les images pertinentes, tandis que le contenu visuel, moins sémantique et plus coûteux en temps de calcul, est

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______1674::c870abe4a642ef734dcb1b09d5e5e800
https://nrc-publications.canada.ca/eng/view/object/?id=7c6481d0-bd9d-42a5-a1c6-6c4b11f14baf

Zobrazit plný text záznamu

UPMC/LIP6 at ImageCLEFannotation 2010

Autor: Fakeri-Tabrizi, Ali, Tollari, Sabrina, Usunier, Nicolas, Gallinari, Patrick

Publikováno v: Working Notes for CLEF 2010 Conference
Working Notes for CLEF 2010 Conference, Sep 2010, Padua, Italy

International audience; In this paper, we present the LIP6 annotation models for the ImageCLEFannotation 2010 task. We study two methods to train and merge the results of different classifiers in order to improve annotation. In particular, we propose

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3fa9224c7a2e60a5c8d960747f07fc9f
https://hal.archives-ouvertes.fr/hal-01288859

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání