 Idempotent Unsupervised Representation Learning for Skeleton-Based
Action RecognitionEuropean Conference on Computer Vision (ECCV), 2024 |
 Collaboratively Self-supervised Video Representation Learning for Action RecognitionIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2024 |
 STEPs: Self-Supervised Key Step Extraction and Localization from
Unlabeled Procedural VideosIEEE International Conference on Computer Vision (ICCV), 2023 |
 Multimodal Emotion Recognition with Modality-Pairwise Unsupervised
Contrastive LossInternational Conference on Pattern Recognition (ICPR), 2022 |
 SLIC: Self-Supervised Learning with Iterative Clustering for Human
Action VideosComputer Vision and Pattern Recognition (CVPR), 2022 |
 Self-Supervised Learning for Videos: A SurveyACM Computing Surveys (ACM CSUR), 2022 |
