.png){kind=icon}
.png){kind=icon}
Return
Cross-stream contrastive learning for self-supervised skeleton-based action recognition
.png){kind=icon}
OA
AI
DOI：10.1016/j.imavis.2023.104689.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Self-supervised skeleton-based action recognition enjoys a rapid growth along with the development of contras-tive learning. The existing methods rely on imposing invariance to augmentations of 3D skeleton within a single data stream, which merely leverages the easy positive pairs and limits the ability to explore the complicated movement patterns. In this paper, we advocate that the defect of single-stream contrast and the lack of necessary feature transformation are responsible for easy positives, and therefore propose a Cross-Stream Contrastive Learning framework for skeleton-based action Representation learning (CSCLR). Specifically, the proposed CSCLR not only utilizes intra-stream contrast pairs, but introduces inter-stream contrast pairs as hard samples to formulate a better representation learning. Besides, to further exploit the potential of positive pairs and in-crease the robustness of self-supervised representation learning, we propose a Positive Feature Transformation (PFT) strategy which adopts feature-level manipulation to increase the variance of positive pairs. To validate the effectiveness of our method, we conduct extensive experiments on three benchmark datasets NTU-RGB + D 60, NTU-RGB + D 120 and PKU-MMD. Experimental results show that our proposed CSCLR exceeds the state-of-the-art methods on a diverse range of evaluation protocols. (c) 2023 Published by Elsevier B.V.
Keywords:
Self-supervised learning
Contrastive learning
Skeleton-based action recognition
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.2
Papers:
4.0K
Citations:
6.7K