Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Chaoyou Fu"'
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 33:1247-1261
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5630380cd83d6841eea04e88f93ef751
https://doi.org/10.1109/tcsvt.2022.3210002
https://doi.org/10.1109/tcsvt.2022.3210002
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-14
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f3cdb791304a6d793dd3062c4d9fab65
https://doi.org/10.1109/tpami.2022.3227180
https://doi.org/10.1109/tpami.2022.3227180
Publikováno v:
IEEE Transactions on Information Forensics and Security. 16:2218-2231
Face manipulation has shown remarkable advances with the flourish of Generative Adversarial Networks. However, due to the difficulties of controlling structures and textures, it is challenging to model poses and expressions simultaneously, especially
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d25a06eed94a080c4ccfef5ed5a9d60
https://doi.org/10.1109/tifs.2021.3050065
https://doi.org/10.1109/tifs.2021.3050065
Heterogeneous Face Recognition (HFR) aims to match faces across different domains (e.g., visible to near-infrared images), which has been widely applied in authentication and forensics scenarios. However, HFR is a challenging problem because of the l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cddcec37f7ba5184f58728e8067dd00c
http://arxiv.org/abs/2206.04854
http://arxiv.org/abs/2206.04854
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e9500ccd6dea21407bc9ee2aba07740c
https://doi.org/10.1109/cvpr52688.2022.00248
https://doi.org/10.1109/cvpr52688.2022.00248
Publikováno v:
Pattern Recognition. 135:109140
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7e0b662f245f939c42f581408b44efe
https://doi.org/10.1016/j.patcog.2022.109140
https://doi.org/10.1016/j.patcog.2022.109140
Publikováno v:
IJCB
Heterogeneous face recognition (HFR) is quite challenging due to the large discrepancy introduced by cross-domain face images. The limited number of paired face images results in a severe overfitting problem in existing methods. To tackle this issue,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea013b0704cbadda1584f48053119f00
https://doi.org/10.1109/ijcb52358.2021.9484335
https://doi.org/10.1109/ijcb52358.2021.9484335
Publikováno v:
CVPR
We present a new application direction named Pareidolia Face Reenactment, which is defined as animating a static illusory face to move in tandem with a human face in the video. For the large differences between pareidolia face reenactment and traditi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0cf8a2f388e519b3e3c42a83365610c5
https://doi.org/10.1109/cvpr46437.2021.00227
https://doi.org/10.1109/cvpr46437.2021.00227
Publikováno v:
CVPR
Improving the performance of face forgery detectors often requires more identity-swapped images of higher-quality. One core objective of identity swapping is to generate identity-discriminative faces that are distinct from the target while identical
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d4fa895ca4c2adb6337c89e550a33755
https://doi.org/10.1109/cvpr46437.2021.00341
https://doi.org/10.1109/cvpr46437.2021.00341
Visible-Infrared person re-identification (VI-ReID) aims to match cross-modality pedestrian images, breaking through the limitation of single-modality person ReID in dark environment. In order to mitigate the impact of large modality discrepancy, exi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5622ce74371079bc7f09749095d71f7c
http://arxiv.org/abs/2101.08467
http://arxiv.org/abs/2101.08467