Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Dayan Wu"'
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 19:1-22
Hashing has been drawing increasing attention in the task of large-scale image retrieval owing to its storage and computation efficiency, especially the recent asymmetric deep hashing methods. These approaches treat the query and database in an asymm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5fa6b89efef94796f6ea96573565a200
https://doi.org/10.1145/3524021
https://doi.org/10.1145/3524021
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:6914-6926
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2bc22164d26eaf8d3bfa63ee21497a03
https://doi.org/10.1109/tcsvt.2022.3174577
https://doi.org/10.1109/tcsvt.2022.3174577
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_________::464e7b8d36380efd4e05a146780013f5
https://doi.org/10.1109/icassp49357.2023.10095523
https://doi.org/10.1109/icassp49357.2023.10095523
Publikováno v:
Applied Intelligence. 52:14799-14810
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74d39e8a60e62b9289800e5bd7c32496
https://doi.org/10.1007/s10489-022-03349-y
https://doi.org/10.1007/s10489-022-03349-y
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 18:1-23
As a basic component in multimedia applications, object detectors are generally trained on a fixed set of classes that are pre-defined. However, new object classes often emerge after the models are trained in practice. Modern object detectors based o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3a9398b0f0d359e0ff849e8d8a83f049
https://doi.org/10.1145/3472393
https://doi.org/10.1145/3472393
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 18:1-21
Existing video self-supervised learning methods mainly rely on trimmed videos for model training. They apply their methods and verify the effectiveness on trimmed video datasets including UCF101 and Kinetics-400, among others. However, trimmed datase
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2737f1125e1de055394aa46ab0ec6b65
https://doi.org/10.1145/3473342
https://doi.org/10.1145/3473342
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7447ed92160ff695fb44ef31c568442b
https://doi.org/10.1145/3503161.3547958
https://doi.org/10.1145/3503161.3547958
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
The research focus of scene text detection and recognition has shifted to arbitrary shape text in recent years, where the text shape representation is a fundamental problem. An ideal representation should be compact, complete, efficient, and reusable
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3596d696dc7fbc9002c2d6b8e74bb611
https://doi.org/10.1145/3503161.3547882
https://doi.org/10.1145/3503161.3547882
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::93927f5cb3fae813a7534a16bd3dca00
https://doi.org/10.1145/3503161.3548070
https://doi.org/10.1145/3503161.3548070
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae0c36548d2bc3b67ee829de0a74a86b
https://doi.org/10.1145/3503161.3548015
https://doi.org/10.1145/3503161.3548015