Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Hengshuang Zhao"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-14
We introduce a new image segmentation task, called Entity Segmentation (ES), which aims to segment all visual entities (objects and stuffs) in an image without predicting their semantic labels. By removing the need of class label prediction, the mode
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::875cee8ebda6e1b89803ee702c3290fe
https://doi.org/10.1109/tpami.2022.3227513
https://doi.org/10.1109/tpami.2022.3227513
The computational complexity of transformers limits it to be widely deployed onto frameworks for visual recognition. Recent work [9] significantly accelerates the network processing speed by reducing the resolution at the beginning of the network, ho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f122db4cf17ce28d6d791ab1ca62aeeb
https://doi.org/10.1109/tpami.2022.3231725
https://doi.org/10.1109/tpami.2022.3231725
Autor:
Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Yukang Chen, Lu Qi, Liwei Wang, Zeming Li, Jian Sun, Jiaya Jia
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence.
In this paper, we present a conceptually simple, strong, and efficient framework for fully- and weakly-supervised panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff in a unifi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02d390c167688eccc5dc8c2debc9aa5e
https://pubmed.ncbi.nlm.nih.gov/35994543
https://pubmed.ncbi.nlm.nih.gov/35994543
Autor:
Minzhe Liu, Qiang Zhou, Hengshuang Zhao, Jianing Li, Yuan Du, Kurt Keutzer, Li Du, Shanghang Zhang
Publikováno v:
2022 International Conference on Robotics and Automation (ICRA).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::208e0536aeee61c372804f444ad9bc80
https://doi.org/10.1109/icra46639.2022.9811638
https://doi.org/10.1109/icra46639.2022.9811638
Autor:
Zhuotao Tian, Pengguang Chen, Xin Lai, Li Jiang, Shu Liu, Hengshuang Zhao, Bei Yu, Ming-Chang Yang, Jiaya Jia
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence.
Strong semantic segmentation models require large backbones to achieve promising performance, making it hard to adapt to real applications where effective real-time algorithms are needed. Knowledge distillation tackles this issue by letting the small
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15b920e7c1ad49d472abae29e9ea503d
https://pubmed.ncbi.nlm.nih.gov/35294341
https://pubmed.ncbi.nlm.nih.gov/35294341
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198113
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51b904cb11d46d40abba29cbb4cc033c
https://doi.org/10.1007/978-3-031-19812-0_18
https://doi.org/10.1007/978-3-031-19812-0_18
Autor:
Xin Lai, Zhuotao Tian, Xiaogang Xu, Yingcong Chen, Shu Liu, Hengshuang Zhao, Liwei Wang, Jiaya Jia
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198267
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::edff6490ab7c3eb1cf816f60a46982c9
https://doi.org/10.1007/978-3-031-19827-4_22
https://doi.org/10.1007/978-3-031-19827-4_22
Remote photoplethysmography (rPPG), which aims at measuring heart activities and physiological signals from facial video without any contact, has great potential in many applications (e.g., remote healthcare and affective computing). Recent deep lear
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80e6d96a4fab2f7ca7ff7efa98d2f491
http://arxiv.org/abs/2111.12082
http://arxiv.org/abs/2111.12082
Publikováno v:
CVPR
Semantic segmentation has made tremendous progress in recent years. However, satisfying performance highly depends on a large number of pixel-level annotations. Therefore, in this paper, we focus on the semi-supervised segmentation problem where only
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::082ba46e2e683a74d0ffa5af8e273bb2
https://doi.org/10.1109/cvpr46437.2021.00126
https://doi.org/10.1109/cvpr46437.2021.00126
Publikováno v:
IJCAI
Face anti-spoofing (FAS) plays a vital role in securing face recognition systems. Recently, central difference convolution (CDC) has shown its excellent representation capacity for the FAS task via leveraging local gradient features. However, aggrega
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7a1a424398a7afaeb3c12bd821005ff2
http://arxiv.org/abs/2105.01290
http://arxiv.org/abs/2105.01290