CdCLR: Clip- Driven Contrastive Learning for Skeleton-Based Action Recognition

被引:1
作者
Gao, Rong [1 ]
Liu, Xin [1 ,2 ]
Yang, Jingyu [1 ]
Yue, Huanjing [1 ]
机构
[1] Tianjin Univ, Sch Elect & Informat Engn, Tianjin, Peoples R China
[2] Lappeenranta Lahti Univ Technol LUT, Comp Vision & Pattern Recognit Lab, Lappeenranta, Finland
来源
2022 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP) | 2022年
基金
中国国家自然科学基金;
关键词
Unsupervised skeleton-based action recognition; contrastive learning; sequence supervision; deep learning;
D O I
10.1109/VCIP56404.2022.10008837
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this study, we propose a Clip-Driven Contrastive Learning for Skeleton- Based Action Recognition (CdCLR). Instead of considering sequences as instances, CdCLR extracts clips from the sequences as new instances. Aim to implement inherent supervision-guided contrastive learning through joint optimal training of sequences discrimination, clips discrimination, and order verification. Mining abundant positive/negative pairs inside sequence while learning inter- and intra-sequence semantic representations. Extensive experiments on the NTU RGB+D 60, UCLA and iMiGUE datasets present that CdCLR exhibits superior performance under various evaluation protocols and reaches state-of-the-art. Our code is available at https://github.comlErich-G/CdCLR/.
引用
收藏
页数:5
相关论文
共 35 条
[21]   NTU RGB plus D: A Large Scale Dataset for 3D Human Activity Analysis [J].
Shahroudy, Amir ;
Liu, Jun ;
Ng, Tian-Tsong ;
Wang, Gang .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :1010-1019
[22]  
Shi H., 2022, IEEE INTELL SYST
[23]  
Shi Henglin, 2018, BMVC, P165
[24]   Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition [J].
Shi, Lei ;
Zhang, Yifan ;
Cheng, Jian ;
Lu, Hanqing .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :12018-12027
[25]   An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition [J].
Si, Chenyang ;
Chen, Wentao ;
Wang, Wei ;
Wang, Liang ;
Tan, Tieniu .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :1227-1236
[26]   PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition [J].
Su, Kun ;
Liu, Xiulong ;
Shlizerman, Eli .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :9628-9637
[27]  
Tanfous A. B., 2022, WACV, P2888
[28]   Skeleton-Contrastive 3D Action Representation Learning [J].
Thoker, Fida Mohammad ;
Doughty, Hazel ;
Snoek, Cees G. M. .
PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, :1655-1663
[29]  
van den Oord Aaron, 2018, CoRR, DOI 10.48550/arxiv.1807.03748
[30]   Cross-view Action Modeling, Learning and Recognition [J].
Wang, Jiang ;
Nie, Xiaohan ;
Xia, Yin ;
Wu, Ying ;
Zhu, Song-Chun .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :2649-2656