no code implementations • ICCV 2023 • Xi Wei, Zhangxiang Shi, Tianzhu Zhang, Xiaoyuan Yu, Lei Xiao
Scene boundary detection breaks down long videos into meaningful story-telling units and plays a crucial role in high-level video understanding.
no code implementations • 2 Dec 2021 • Bei Tong, Xiaoyuan Yu
Transformer is a potentially powerful architecture for vision tasks.
no code implementations • 25 Nov 2021 • Xin Li, Xin Jin, Jun Fu, Xiaoyuan Yu, Bei Tong, Zhibo Chen
Under this brand-new scenario, we propose Distortion Relation guided Transfer Learning (DRTL) for the few-shot RealSR by transferring the rich restoration knowledge from auxiliary distortions (i. e., synthetic distortions) to the target RealSR under the guidance of distortion relation.
1 code implementation • 10 Jul 2021 • Shuyuan Li, Huabin Liu, Rui Qian, Yuxi Li, John See, Mengjuan Fei, Xiaoyuan Yu, Weiyao Lin
The first stage locates the action by learning a temporal affine transform, which warps each video feature to its action duration while dismissing the action-irrelevant feature (e. g. background).
no code implementations • CVPR 2021 • Wenfei Yang, Tianzhu Zhang, Xiaoyuan Yu, Tian Qi, Yongdong Zhang, Feng Wu
To alleviate this problem, we propose a novel Uncertainty Guided Collaborative Training (UGCT) strategy, which mainly includes two key designs: (1) The first design is an online pseudo label generation module, in which the RGB and FLOW streams work collaboratively to learn from each other.