Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Xuetao Feng"'
Publikováno v:
IEEE Transactions on Multimedia. :1-13
Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the learned new visual features to be directly compared with the old feat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::13763076dd216a268e5fb5d99b9cf6f3
https://doi.org/10.1109/tmm.2022.3219680
https://doi.org/10.1109/tmm.2022.3219680
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ce67b189ff310d7f1dd20b03945670bc
https://doi.org/10.1109/iccv48922.2021.01166
https://doi.org/10.1109/iccv48922.2021.01166
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::413c527c21a35d0e78fe20c3cc0edc22
https://doi.org/10.1109/iccv48922.2021.01076
https://doi.org/10.1109/iccv48922.2021.01076
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::04714385eccbf70702842cb2bf45677f
https://doi.org/10.1109/iccv48922.2021.00971
https://doi.org/10.1109/iccv48922.2021.00971
Publikováno v:
CVPR
Recently, person re-identification (ReID) has vastly benefited from the surging waves of data-driven methods. However, these methods are still not reliable enough for real-world deployments, due to the insufficient generalization capability of the mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::73f3937d991cc503a1dabee03a02fb89
https://doi.org/10.1109/cvpr46437.2021.00216
https://doi.org/10.1109/cvpr46437.2021.00216
Autor:
Xuetao Feng, Zhen Lei, Xiangyu Zhu, Ming Tang, Xiang Yan, Zhiwei Liu, Yan Wang, Lu Yang, Jinqiao Wang, Guibo Zhu
Publikováno v:
ACM Multimedia
3D human pose and shape recovery from a monocular RGB image is a challenging task. Existing learning based methods highly depend on weak supervision signals, e.g. 2D and 3D joint location, due to the lack of in-the-wild paired 3D supervision. However
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f5dbfbe0266eceb3ed77e845a9757c6
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030504359
ICCS (7)
ICCS (7)
Fire alarm is crucial for safety of life and property in many scenes. A good fire alarm system should be small-sized, low-cost and effective to prevent fire accidents from happening. In this paper we introduce a smart fire alarm system used in kitche
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40c82cb3403dd85b4f0edfc6dc58633a
https://doi.org/10.1007/978-3-030-50436-6_26
https://doi.org/10.1007/978-3-030-50436-6_26
Publikováno v:
IEEE Transactions on Multimedia. :1-1
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::769d895f510fb73359fcb2c9d3242d16
https://doi.org/10.1109/tmm.2022.3146775
https://doi.org/10.1109/tmm.2022.3146775
Publikováno v:
ICIP
Unconstrained face recognition under varying views is one of the most challenging tasks, since the difference in appearances caused by poses may be even larger than that due to identity. In this paper, we exploit and analyze a novel pose normalizatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ffe34c2831e1fd08531c50bbf2e288e
https://doi.org/10.1109/icip.2015.7351080
https://doi.org/10.1109/icip.2015.7351080
Publikováno v:
ICIP
Trajectory-based features have become popular for action recognition and achieve the state-of-the-art results on a variety of datasets. In this paper, we propose a novel framework to improve the performance of action recognition. Specifically, we fir
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5905f3c7acee8d0daaac609d8aba2521
https://doi.org/10.1109/icip.2015.7351552
https://doi.org/10.1109/icip.2015.7351552