Zobrazeno 1 - 10
of 232
pro vyhledávání: '"Longhui Wei"'
Publikováno v:
Multimedia Systems. 29:33-48
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f955e6a8ab4d9d82498022f7b843b442
https://doi.org/10.1007/s00530-022-00977-9
https://doi.org/10.1007/s00530-022-00977-9
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:2642-2650
Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to fully-supervised metho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36c13830a8720ce378caf088e110940b
https://doi.org/10.1609/aaai.v36i3.20166
https://doi.org/10.1609/aaai.v36i3.20166
Publikováno v:
International Journal of Computer Vision. 130:820-835
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3fd0edafcc51530016ab2bf6d0c91a2c
https://doi.org/10.1007/s11263-021-01566-5
https://doi.org/10.1007/s11263-021-01566-5
Autor:
Yang Zijie, Huo Xinyue, Xiaopeng Zhang, Lingxi Xie, Chen Xin, Houqiang Li, Li Hao, Qi Tian, Wengang Zhou, Longhui Wei
Publikováno v:
IEEE Transactions on Multimedia. 24:4224-4235
Unsupervised pretraining is of great significance for visual representation. Especially, contrastive learning has achieved great success recently, but existing approaches mostly ignored spatial information which is often crucial for visual representa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e3ada626c8ec4519ff116749f93ec15b
https://doi.org/10.1109/tmm.2021.3115335
https://doi.org/10.1109/tmm.2021.3115335
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:374-387
Person re-identification (ReID) aims at matching identities across disjoint cameras. Its fundamental difficulty lies in associating images across individual cameras, where a key clue, i.e., identity appearance, is prone to the environmental factors o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d827a274bb2e28fcb368606adda1fa0
https://doi.org/10.1109/tcsvt.2021.3058111
https://doi.org/10.1109/tcsvt.2021.3058111
Autor:
Longhui WEI1, Binglin LI2, Xiaoli ZHANG2 xlzhang@nwu.edu.cn, Kai TANG1, Wenwen ZHENG1, Dan CHEN1, Binxia ZHAO1
Publikováno v:
Turkish Journal of Chemistry. 2020, Vol. 44 Issue 1, p249-260. 12p.
Autor:
Yongsheng Liang, Jia-Xing Zhong, Qi Tian, Longhui Wei, Xiujun Shu, Ge Li, Xianghao Zang, Shiliang Zhang, Yaowei Wang
Publikováno v:
Pattern Recognition Letters. 149:17-23
Attention mechanisms have achieved success in video-based person re-identification (re-ID). However, current global attentions tend to focus on the most salient parts, e.g., clothes, and ignore other subtle but valuable cues, e.g., hair, bag, and sho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85d5490c31c4fb98618685c52b5e9ace
https://doi.org/10.1016/j.patrec.2021.05.020
https://doi.org/10.1016/j.patrec.2021.05.020
Autor:
LINGXI XIE, XIN CHEN, KAIFENG BI, LONGHUI WEI, YUHUI XU, LANFEI WANG, ZHENGSU CHEN, AN XIAO, JIANLONG CHANG, XIAOPENG ZHANG, QI TIAN
Publikováno v:
ACM Computing Surveys; Dec2022, Vol. 54 Issue 9, p1-37, 37p
Publikováno v:
Comptes Rendus. Chimie. 23:375-384
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c76d9870fb23e9487ae9a275ecbb474a
https://doi.org/10.5802/crchim.28
https://doi.org/10.5802/crchim.28