SG-CLR: Semantic representation-guided contrastive learning for self-supervised skeleton-based action recognition
Authors:
- Ruyi LiuRLRuyi Liu
- Yi LiuYLYi Liu
- Mengyao WuMWMengyao Wu
- Wentian XinWXWentian Xin
- Qiguang MiaoQMQiguang Miao
- Xiangzeng LiuXLXiangzeng Liu
- Long LiLong Li
- 18 January 2025
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 162
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62272364)
- Key Research and Development Projects of Shaanxi Province (2024GH-ZDXM-47)
- National Major Science and Technology Projects of China (2022ZD0117103)
This publication has 34 references indexed in Scilit:
- Improving self-supervised action recognition from extremely augmented skeleton sequencesPattern Recognition, 2024
- Leveraging spatio-temporal features using graph neural networks for human activity recognitionPattern Recognition, 2024
- Spatiotemporal Progressive Inward-Outward Aggregation Network for skeleton-based action recognitionPattern Recognition, 2024
- Multi-grained clip focus for skeleton-based action recognitionPattern Recognition, 2023
- Sharing-Net: Lightweight feedforward network for skeleton-based action recognition based on information sharing mechanismPattern Recognition, 2023
- Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action RecognitionInformation Sciences, 2021
- Rethinking the Faster R-CNN Architecture for Temporal Action Localization2018
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis2016
- Monocular vision-based iterative pose estimation algorithm from corresponding feature pointsScience China Information Sciences, 2010
- Human Motion Analysis: A ReviewComputer Vision and Image Understanding, 1999