 Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens
in 3D SpaceNeural Information Processing Systems (NeurIPS), 2022 |
 Self-Supervised Learning for Videos: A SurveyACM Computing Surveys (ACM CSUR), 2022 |
 Does Self-supervised Learning Really Improve Reinforcement Learning from
Pixels?Neural Information Processing Systems (NeurIPS), 2022 |
 SPAct: Self-supervised Privacy Preservation for Action RecognitionComputer Vision and Pattern Recognition (CVPR), 2022 |
 Self-supervised Video-centralised Transformer for Video Face ClusteringIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 |
 Video Transformers: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 |
 SWAT: Spatial Structure Within and Among TokensInternational Joint Conference on Artificial Intelligence (IJCAI), 2021 |
 ParamCrop: Parametric Cubic Cropping for Video Contrastive LearningIEEE transactions on multimedia (IEEE Trans. Multimedia), 2021 |
 Human Action Recognition from Various Data Modalities: A ReviewIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020 |
