Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Zebiao Zheng"'
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2bdbdf197732f26e3d58f7282c99a90e
https://doi.org/10.1109/iccv48922.2021.00270
https://doi.org/10.1109/iccv48922.2021.00270
Publikováno v:
CVPR
Recent works on two-stage cross-domain detection have widely explored the local feature patterns to achieve more accurate adaptation results. These methods heavily rely on the region proposal mechanisms and ROI-based instance-level features to design
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bc7909ddbcc1cc39112999ad4473b029
https://doi.org/10.1109/cvpr46437.2021.01239
https://doi.org/10.1109/cvpr46437.2021.01239
Publikováno v:
CVPR
Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline. Whilst adversarial adaptation significantly enhances the tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59a088afff83392ce9ce845cb3310880
Publikováno v:
Communications in Computer and Information Science ISBN: 9789811316500
Taking the characteristic value as the core, a population abnormality detection algorithm is used to process the crowd surveillance video. Using density detection, the density of the population is first obtained. Object-based feature extraction is us
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2ea3663db34bc8b5bfe5dbba9052a11
https://doi.org/10.1007/978-981-13-1651-7_43
https://doi.org/10.1007/978-981-13-1651-7_43