2 papers
cs.CV2022
Self-Supervised Video Representation Learning with Motion-Contrastive Perception
Jinyu Liu, Ying Cheng, Yuejie Zhang +2
Visual-only self-supervised learning has achieved significant improvement in video representation learning. Existing related methods encourage models to learn video representations…
cs.LG2019
Thick-Net: Parallel Network Structure for Sequential Modeling
Yu-Xuan Li, Jin-Yuan Liu, Liang Li +1
Recurrent neural networks have been widely used in sequence learning tasks. In previous studies, the performance of the model has always been improved by either wider or deeper str…