Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Jean-Yves Audibert"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2011, 33 (4), pp.699-708. ⟨10.1109/TPAMI.2010.198⟩
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33 (4), pp.699-708. ⟨10.1109/TPAMI.2010.198⟩
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2011, 33 (4), pp.699-708. ⟨10.1109/TPAMI.2010.198⟩
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33 (4), pp.699-708. ⟨10.1109/TPAMI.2010.198⟩
International audience; Kernels are functions designed in order to capture resemblance between data and they are used in a wide range of machine learning techniques, including support vector machines (SVMs). In their standard version, commonly used k
Publikováno v:
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing, 2010, 19 (8), pp.2201-2210. ⟨10.1109/TIP.2010.2045714⟩
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2010, 19 (8), pp.2201-2210. ⟨10.1109/TIP.2010.2045714⟩
IEEE Transactions on Image Processing, 2010, 19 (8), pp.2201-2210. ⟨10.1109/TIP.2010.2045714⟩
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2010, 19 (8), pp.2201-2210. ⟨10.1109/TIP.2010.2045714⟩
International audience; This paper presents a novel framework for detecting nonflat abandoned objects by matching a reference and a target video sequences. The reference video is taken by a moving camera when there is no suspicious object in the scen
Autor:
Jean-Yves Audibert, Antoine Salomon
Publikováno v:
Theoretical Computer Science
Theoretical Computer Science, Elsevier, 2014, 519, pp.46-67. ⟨10.1016/j.tcs.2013.09.019⟩
Theoretical Computer Science, 2014, 519, pp.46-67. ⟨10.1016/j.tcs.2013.09.019⟩
Theoretical Computer Science, Elsevier, 2014, 519, pp.46-67. ⟨10.1016/j.tcs.2013.09.019⟩
Theoretical Computer Science, 2014, 519, pp.46-67. ⟨10.1016/j.tcs.2013.09.019⟩
International audience; This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. [2] exhibit a policy such that with probability at
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5122c1f942e502161dab481a8e6c4bbb
https://hal-enpc.archives-ouvertes.fr/hal-01801056
https://hal-enpc.archives-ouvertes.fr/hal-01801056
Publikováno v:
Lecture Notes On Computer Science
11th Asian Conference on Computer Vision (ACCV 2012)
11th Asian Conference on Computer Vision (ACCV 2012), Nov 2012, Daejeon, South Korea. pp.460-473, ⟨10.1007/978-3-642-37331-2_35⟩
Computer Vision – ACCV 2012 ISBN: 9783642373305
ACCV (1)
11th Asian Conference on Computer Vision (ACCV 2012)
11th Asian Conference on Computer Vision (ACCV 2012), Nov 2012, Daejeon, South Korea. pp.460-473, ⟨10.1007/978-3-642-37331-2_35⟩
Computer Vision – ACCV 2012 ISBN: 9783642373305
ACCV (1)
International audience; We propose a robust method to match image feature points taking into account geometric consistency. It is a careful adaptation of the match propagation principle to 4th-order geometric constraints (match quadruple consistency)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a11062e2b5778c879bd97dd7db8f651e
https://hal-enpc.archives-ouvertes.fr/hal-00743044/document
https://hal-enpc.archives-ouvertes.fr/hal-00743044/document
We address online linear optimization problems when the possible actions of the decision maker are represented by binary vectors. The regret of the decision maker is the difference between her realized loss and the best loss she would have achieved b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f82d580021cf466c37a7252c310e74d
http://arxiv.org/abs/1204.4710
http://arxiv.org/abs/1204.4710
Publikováno v:
Pattern Recognition
Pattern Recognition, Elsevier, 2012, 45 (1), pp.333-345. ⟨10.1016/j.patcog.2011.05.017⟩
Pattern Recognition, 2012, 45 (1), pp.333-345. ⟨10.1016/j.patcog.2011.05.017⟩
Pattern Recognition, Elsevier, 2012, 45 (1), pp.333-345. ⟨10.1016/j.patcog.2011.05.017⟩
Pattern Recognition, 2012, 45 (1), pp.333-345. ⟨10.1016/j.patcog.2011.05.017⟩
13 pages; International audience; In this survey, we argue that using structured vocabularies is capital to the success of image annotation. We analyze literature on image annotation uses and user needs, and we stress the need for automatic annotatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::45b7ad2f348bcf26fec959a609eb29b7
https://hal.archives-ouvertes.fr/hal-00624460
https://hal.archives-ouvertes.fr/hal-00624460
Publikováno v:
2011 IEEE International Conference on Computer Vision (ICCV)
ICCV 2011-13th International Conference on Computer Vision
ICCV 2011-13th International Conference on Computer Vision, Nov 2011, Barcelona, Spain. pp.1235-1242, ⟨10.1109/ICCV.2011.6126374⟩
ICCV
ICCV 2011-13th International Conference on Computer Vision
ICCV 2011-13th International Conference on Computer Vision, Nov 2011, Barcelona, Spain. pp.1235-1242, ⟨10.1109/ICCV.2011.6126374⟩
ICCV
International audience; In this work we present a new crowd analysis algorithm powered by behavior priors that are learned on a large database of crowd videos gathered from the Internet. The algorithm works by first learning a set of crowd behavior p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f1df38f326acc843b9810d89dab47bc
https://hal-enpc.archives-ouvertes.fr/hal-00654256/file/ICCV11b.pdf
https://hal-enpc.archives-ouvertes.fr/hal-00654256/file/ICCV11b.pdf
Autor:
Jean-Yves Audibert, Antoine Salomon
Publikováno v:
Proceedings of ALT 2011
ALT'11-Algorithmic Learning Theory
ALT'11-Algorithmic Learning Theory, Oct 2011, Espoo, Finland. in press
Lecture Notes in Computer Science ISBN: 9783642244117
ALT
ALT'11-Algorithmic Learning Theory
ALT'11-Algorithmic Learning Theory, Oct 2011, Espoo, Finland. in press
Lecture Notes in Computer Science ISBN: 9783642244117
ALT
This paper studies the deviations of the regret in a stochastic multi-armed bandit problem.When the total number of plays n is known beforehand by the agent, Audibert et al. (2009) exhibit a policy such that with probability at least 1-1/n, the regre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f377e795c064ae10fcca3c21ebe8bb61
https://hal.archives-ouvertes.fr/hal-00624461
https://hal.archives-ouvertes.fr/hal-00624461
Autor:
Jean-Yves Audibert, Hichem Sahbi
Publikováno v:
ICIP
The exponential growth of social networks (SN) currently makes them the standard way to share and explore data where users put informations (images, text, audio,…) and refer to other contents. This creates connected networks whose links provide val
Publikováno v:
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing, 2010, 19 (8), pp.2211-2220. ⟨10.1109/TIP.2010.2045715⟩
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2010, 19 (8), pp.2211-2220. ⟨10.1109/TIP.2010.2045715⟩
IEEE Transactions on Image Processing, 2010, 19 (8), pp.2211-2220. ⟨10.1109/TIP.2010.2045715⟩
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2010, 19 (8), pp.2211-2220. ⟨10.1109/TIP.2010.2045715⟩
International audience; Given a single image of an arbitrary road, that may not be well-paved, or have clearly delineated edges, or some a priori known color or texture distribution, is it possible for a computer to find this road? This paper address
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e0d2001f92f58b007363a166e5a9470
https://enpc.hal.science/hal-00654397
https://enpc.hal.science/hal-00654397