Zobrazeno 1 - 10
of 178
pro vyhledávání: '"Yu-Wing Tai"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-14
Segmenting highly-overlapping image objects is challenging, because there is typically no distinction between real object contours and occlusion boundaries on images. Unlike previous instance segmentation methods, we model image formation as a compos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ebf27d30114c6099e2c64f9e3139275c
https://doi.org/10.1109/tpami.2023.3246174
https://doi.org/10.1109/tpami.2023.3246174
Publikováno v:
International Journal of Computer Vision. 130:2532-2552
The key challenge of sequence representation learning is to capture the long-range temporal dependencies. Typical methods for supervised sequence representation learning are built upon recurrent neural networks to capture temporal dependencies. One p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6db84ac7d2cffcb3badf557ea9b3d2ba
https://doi.org/10.1007/s11263-022-01648-y
https://doi.org/10.1007/s11263-022-01648-y
Publikováno v:
International Journal of Computer Vision. 130:1440-1458
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da2317bc5067d26a5924ccdd093eaaff
https://doi.org/10.1007/s11263-022-01583-y
https://doi.org/10.1007/s11263-022-01583-y
In this work, we address the task of SDR videos to HDR videos(SDRTV-to-HDRTV). Previous approaches use global feature modulation for SDRTV-to-HDRTV. Feature modulation scales and shifts the features in the original feature space, which has limited ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::858e319e5ea239b7c66194b3c1c01aa3
http://arxiv.org/abs/2207.00319
http://arxiv.org/abs/2207.00319
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::399010b03696a4e92ff88f112cd64f3a
https://doi.org/10.1109/cvprw56347.2022.00111
https://doi.org/10.1109/cvprw56347.2022.00111
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
This paper introduces a new matting task called human instance matting (HIM), which requires the pertinent model to automatically predict a precise alpha matte for each human instance. Straightforward combination of closely related techniques, namely
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ca3f9ddfbd1513dcf3ce407a24ec7fb
https://doi.org/10.1109/cvpr52688.2022.00267
https://doi.org/10.1109/cvpr52688.2022.00267
Autor:
Takashi Isobe, Xu Jia, Xin Tao, Changlin Li, Ruihuang Li, Yongjie Shi, Jing Mu, Huchuan Lu, Yu-Wing Tai
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation. However, such temporal modeling techniques increase the model com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c20978c9f26250083b30c622cff20da4
https://doi.org/10.1109/cvpr52688.2022.01689
https://doi.org/10.1109/cvpr52688.2022.01689
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Human-Object Interaction (HOI) detection plays a core role in activity understanding. Though recent two/one-stage methods have achieved impressive results, as an essential step, discovering interactive human-object pairs remains challenging. Both one
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f67483a31ec0666481eca7ec637a4fd
https://doi.org/10.1109/cvpr52688.2022.01948
https://doi.org/10.1109/cvpr52688.2022.01948
Autor:
Andres Romero, Angela Castillo, Jose Abril-Nova, Radu Timofte, Ritwik Das, Sanchit Hira, Zhihong Pan, Min Zhang, Baopu Li, Dongliang He, Tianwei Lin, Fu Li, Chengyue Wu, Xianming Liu, Xinying Wang, Yi Yu, Jie Yang, Rengang Li, Yaqian Zhao, Zhenhua Guo, Baoyu Fan, Xiaochuan Li, Runze Zhang, Zeyu Lu, Junqin Huang, Gang Wu, Junjun Jiang, Jiayin Cai, Changlin Li, Xin Tao, Yu-Wing Tai, Xiaoqiang Zhou, Huaibo Huang
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8458607215ab265c974f3103a666da4
https://doi.org/10.1109/cvprw56347.2022.00124
https://doi.org/10.1109/cvprw56347.2022.00124
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 42:232-245
While conventional calibrated photometric stereo methods assume that light intensities and sensor exposures are known or unknown but identical across observed images, this assumption easily breaks down in practical settings due to individual light bu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fb66f41e59ec9b3d408f9d7250bcba6a
https://doi.org/10.1109/tpami.2018.2873295
https://doi.org/10.1109/tpami.2018.2873295