Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Bahjat Safadi"'
Publikováno v:
Pattern Analysis and Applications. 23:27-44
Multimedia documents indexing systems performances have been improved significantly in recent years, especially after the involvement of deep learning approaches. However, this progress remains insufficient with the evolution of users' needs that bec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::18f9bb6abd11a367e449a73ecd1fc3c8
https://doi.org/10.1007/s10044-018-0761-9
https://doi.org/10.1007/s10044-018-0761-9
Autor:
Georges Quénot, Efrain-Leonardo Gutierrez-Gomez, Bahjat Safadi, Mateusz Budnik, Denis Pellerin
Publikováno v:
Multimedia Tools and Applications
Multimedia Tools and Applications, Springer Verlag, 2016, 76 (9), pp.11941-11958. ⟨10.1007/s11042-016-4240-2⟩
Multimedia Tools and Applications, Springer Verlag, 2016, 76 (9), pp.11941-11958. ⟨10.1007/s11042-016-4240-2⟩
published online; International audience; In this paper, we compare " traditional " engineered (hand-crafted) features (or descriptors) and learned features for content-based indexing of image or video documents. Learned (or semantic) features are ob
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40c1e8ce1d45389daaf907af19a7c66e
https://doi.org/10.1007/s11042-016-4240-2
https://doi.org/10.1007/s11042-016-4240-2
Publikováno v:
14th International Workshop on Content-Based Multimedia Indexing (CBMI)
14th International Workshop on Content-Based Multimedia Indexing (CBMI), Jun 2016, Bucarest, Romania. pp.1-6, ⟨10.1109/CBMI.2016.7500247⟩
CBMI
14th International Workshop on Content-Based Multimedia Indexing (CBMI), Jun 2016, Bucarest, Romania. pp.1-6, ⟨10.1109/CBMI.2016.7500247⟩
CBMI
International audience; This paper describes a method for querying lifelog data from visual content and from metadata associated with the recorded images. Our approach mainly relies on mapping the query terms to visual concepts computed on the Lifelo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::92851b5301ce4006046e7e856f7cb046
https://hal.archives-ouvertes.fr/hal-01572659
https://hal.archives-ouvertes.fr/hal-01572659
Autor:
Hervé Le Borgne, Philippe Gosselin, David Picard, Miriam Redi, Bernard Mérialdo, Boris Mansencal, Jenny Benois-Pineau, Stéphane Ayache, Abdelkader Hamadi, Bahjat Safadi, Nadia Derbas, Mateusz Budnik, Georges Quénot, Boyang Gao, Chao Zhu, Yuxing Tang, Emmanuel Dellandrea, Charles-Edmond Bichot, Liming Chen, alexandre benoit, Patrick Lambert, Tiberius Strat
Publikováno v:
Proceedings of TRECVid
Proceedings of TRECVid, Nov 2015, Gaithersburg, MD, United States
HAL
Proceedings of TRECVid, Nov 2015, Gaithersburg, MD, United States
HAL
International audience; The IRIM group is a consortium of French teams supported by the GDR ISIS and working on Multimedia Indexing and Retrieval. This paper describes its participation to the TRECVID 2015 semantic indexing (SIN). Our approach uses a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::b2d17ffc2cee5ec496b11f53a21cff69
https://hal.archives-ouvertes.fr/hal-01233398/document
https://hal.archives-ouvertes.fr/hal-01233398/document
Publikováno v:
13th International Workshop on Content-Based Multimedia Indexing (CBMI)
13th International Workshop on Content-Based Multimedia Indexing (CBMI), Jun 2015, Prague, Czech Republic
CBMI
13th International Workshop on Content-Based Multimedia Indexing (CBMI), Jun 2015, Prague, Czech Republic
CBMI
International audience; In this paper, we compare "traditional" engineered (hand-crafted) features (or descriptors) and learned features for content-based semantic indexing of video documents. Learned (or semantic) features are obtained by training c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e4ad3b449904e346fa267665680697cf
https://hal.archives-ouvertes.fr/hal-01145623/file/CBMI2015_Budnik.pdf
https://hal.archives-ouvertes.fr/hal-01145623/file/CBMI2015_Budnik.pdf
Autor:
Georges Quénot, Bahjat Safadi
Publikováno v:
13th International Workshop on Content-Based Multimedia Indexing (CBMI)
13th International Workshop on Content-Based Multimedia Indexing (CBMI), Jun 2015, Prague, Czech Republic. pp.1-6, ⟨10.1109/CBMI.2015.7153610⟩
CBMI
13th International Workshop on Content-Based Multimedia Indexing (CBMI), Jun 2015, Prague, Czech Republic. pp.1-6, ⟨10.1109/CBMI.2015.7153610⟩
CBMI
International audience; This paper presents a set of improvements for SVM-based large scale multimedia indexing. The proposed method is particularly suited for the detection of many target concepts at once and for highly imbalanced classes (very infr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f1bf3b0e1cb46d966dd2bff84bb99b3e
https://hal.archives-ouvertes.fr/hal-01230720/file/CBMI2015-Safadi.pdf
https://hal.archives-ouvertes.fr/hal-01230720/file/CBMI2015-Safadi.pdf
Publikováno v:
Multimedia Tools and Applications
Multimedia Tools and Applications, Springer Verlag, 2015, 74 (4), pp.1267-1290. ⟨10.1007/s11042-014-2071-6⟩
Multimedia Tools and Applications, 2015, 74 (4), pp.1267-1290. ⟨10.1007/s11042-014-2071-6⟩
Multimedia Tools and Applications, Springer Verlag, 2015, 74 (4), pp.1267-1290. ⟨10.1007/s11042-014-2071-6⟩
Multimedia Tools and Applications, 2015, 74 (4), pp.1267-1290. ⟨10.1007/s11042-014-2071-6⟩
International audience; In this paper, we propose and evaluate a method for optimizing descriptors used for content-based multimedia indexing and retrieval. A large variety of descriptors are commonly used for this purpose. However, the most efficien
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a0c582efd8793cc331d8d02ac3c3c5a5
https://hal.archives-ouvertes.fr/hal-00981672
https://hal.archives-ouvertes.fr/hal-00981672
Autor:
Nicolas Ballas, Benjamin Labbé, Hervé Le Borgne, Philippe Gosselin, David Picard, Miriam Redi, Bernard Mérialdo, Boris Mansencal, Jenny Benois-Pineau, Stéphane Ayache, Abdelkader Hamadi, Bahjat Safadi, Nadia Derbas, Mateusz Budnik, Georges Quénot, Boyang Gao, Chao Zhu, Yuxing Tang, Emmanuel Dellandrea, Charles-Edmond Bichot, Liming Chen, alexandre benoit, Patrick Lambert, Tiberius Strat
Publikováno v:
Proceedings of TRECVID
Proceedings of TRECVID, Nov 2014, Orlando, United States
HAL
Proceedings of TRECVID, Nov 2014, Orlando, United States
HAL
International audience; The IRIM group is a consortium of French teams supported by the GDR ISIS and working on Multimedia Indexing and Retrieval. This paper describes its participation to the TRECVID 2014 semantic indexing (SIN) and instance search
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ed4041e740eb7803fa868728986335f0
https://hal.archives-ouvertes.fr/hal-01132491
https://hal.archives-ouvertes.fr/hal-01132491
Publikováno v:
ICIP
Currently, popular search engines retrieve documents on the basis of text information. However, integrating the visual information with the text-based search for video and image retrieval is still a hot research topic. In this paper, we propose and e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9fe9ac367cdffc5de37c5188c560a0a1
https://doi.org/10.1109/icip.2014.7025622
https://doi.org/10.1109/icip.2014.7025622
Publikováno v:
ICMR
Currently, popular search engines retrieve documents on the basis of text information. However, integrating the visual information with the text-based search for video and image retrieval is still a hot research topic. In this paper, we propose and e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5eff9ed5dc85f4a1d7c59d398bff8d2
https://doi.org/10.1145/2578726.2578760
https://doi.org/10.1145/2578726.2578760