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

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/.