Zobrazeno 1 - 10
of 98
pro vyhledávání: '"Hervé Jégou"'
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2008 (2007)
This paper first introduces a new set of aggregated state models for soft-input decoding of quasi arithmetic (QA) codes with a termination constraint. The decoding complexity with these models is linear with the sequence length. The aggregation param
Externí odkaz:
https://doaj.org/article/6697d48bd4534d94a0f46415817d6bbc
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1b9a77da07d850bcf2ec6652aabb81cd
https://doi.org/10.1109/icassp49357.2023.10095451
https://doi.org/10.1109/icassp49357.2023.10095451
Publikováno v:
IEEE Transactions on Big Data. 7:535-547
Similarity search finds application in database systems handling complex data such as images or videos, which are typically represented by high-dimensional features and require specific indexing structures. This paper tackles the problem of better ut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::00d12b479f0977e3f0b0f328aed45c07
https://doi.org/10.1109/tbdata.2019.2921572
https://doi.org/10.1109/tbdata.2019.2921572
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200526
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d9abe4f97b4bce2225cbd54f00b2766d
https://doi.org/10.1007/978-3-031-20053-3_30
https://doi.org/10.1007/978-3-031-20053-3_30
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200526
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5257ff9c712cc49efec3e1cec7ec2722
https://doi.org/10.1007/978-3-031-20053-3_29
https://doi.org/10.1007/978-3-031-20053-3_29
Modern approaches for fast retrieval of similar vectors on billion-scaled datasets rely on compressed-domain approaches such as binary sketches or product quantization. These methods minimize a certain loss, typically the mean squared error or other
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f8960c06ea31536a32fcffb38650758
Publikováno v:
ITE Transactions on Media Technology and Applications. 6:2-10
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d5320a8f9fab941d375646cf48528be9
https://doi.org/10.3169/mta.6.2
https://doi.org/10.3169/mta.6.2
Publikováno v:
International Journal of Computer Vision
International Journal of Computer Vision, 2017, pp.1-25. ⟨10.1007/s11263-017-1023-9⟩
International Journal of Computer Vision, 124(3)
International Journal of Computer Vision, 124(3), 287-311. Springer Netherlands
International Journal of Computer Vision, 2017, pp.1-25. ⟨10.1007/s11263-017-1023-9⟩
International Journal of Computer Vision, 124(3)
International Journal of Computer Vision, 124(3), 287-311. Springer Netherlands
This paper considers the problem of localizing actions in videos as a sequences of bounding boxes. The objective is to generate action proposals that are likely to include the action of interest, ideally achieving high recall with few proposals. Our
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c4927878339ecccf1be4f3201122a5d
https://doi.org/10.1007/s11263-017-1023-9
https://doi.org/10.1007/s11263-017-1023-9
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 39:1797-1810
We consider the design of an image representation that embeds and aggregates a set of local descriptors into a single vector. Popular representations of this kind include the bag-of-visual-words, the Fisher vector and the VLAD. When two such image re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::905b125f4fa2341d051cae92ff98bb76
https://doi.org/10.1109/tpami.2016.2615621
https://doi.org/10.1109/tpami.2016.2615621
Publikováno v:
IEEE Transactions on Multimedia. 19:1965-1967
The papers in this special section focus on multimedia data retrieval and classification via large-scale systems. Today, large collections of multimedia data are explosively created in different fields and have attracted increasing interest in the mu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::063c41eb0765c34b37945f97f23b0c56
https://doi.org/10.1109/tmm.2017.2733638
https://doi.org/10.1109/tmm.2017.2733638