108 citations · 140 across the 10 of their papers we have counts for
5 papers · 1 filter
Towards All-around Knowledge Transferring: Learning From Task-irrelevant Labels
Yinghui Li, Ruiyang Liu, ZiHao Zhang +4
Deep neural models have hitherto achieved significant performances on numerous classification tasks, but meanwhile require sufficient manually annotated data. Since it is extremely…
Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework
Li Tao, Xueting Wang, Toshihiko Yamasaki
We propose a self-supervised method to learn feature representations from videos. A standard approach in traditional self-supervised methods uses positive-negative data pairs to tr…
Motion Representation Using Residual Frames with 3D CNN
Li Tao, Xueting Wang, Toshihiko Yamasaki
Recently, 3D convolutional networks (3D ConvNets) yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost…
Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning
Yiyan Chen, Li Tao, Xueting Wang +1
Conventional video summarization approaches based on reinforcement learning have the problem that the reward can only be received after the whole summary is generated. Such kind of…
Rethinking Motion Representation: Residual Frames with 3D ConvNets for Better Action Recognition
Li Tao, Xueting Wang, Toshihiko Yamasaki
Recently, 3D convolutional networks yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost of which is ve…