.png){kind=icon}
.png){kind=icon}
Return
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
.png){kind=icon}
OA
AI
DOI：10.1109/TBIOM.2025.3566212.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Traditional approaches in unsupervised or self-supervised learning for skeleton-based action classification have concentrated predominantly on the dynamic aspects of skeletal sequences. Yet, the intricate interaction between the moving and static elements of the skeleton presents a rarely tapped discriminative potential for action classification. This paper introduces a novel measurement, referred to as spatial-temporal joint density (STJD), to quantify such interaction. Tracking the evolution of this density throughout an action can effectively identify a subset of discriminative moving and/or static joints termed prime joints to steer self-supervised learning. A new contrastive learning strategy named STJD-CL is proposed to align the representation of a skeleton sequence with that of its prime joints while simultaneously contrasting the representations of prime and non-prime joints. In addition, a method called STJD-MP is developed by integrating it with a reconstruction-based framework for more effective learning. Experimental evaluations on the NTU RGB+D 60, NTU RGB+D 120, and PKUMMD datasets in various downstream tasks demonstrate that the proposed STJD-CL and STJD-MP improved performance, particularly by 3.5 and 3.6 percentage points over the state-of-the-art contrastive methods on the NTU RGB+D 120 dataset using X-sub and X-set evaluations, respectively. The code is available at STJD.
Keywords:
Skeleton
Contrastive learning
Biometrics
Training
Kernel
Image reconstruction
Density measurement
Representation learning
Hands
Three-dimensional displays
Self-supervised learning
skeleton-based action recognition
spatio-temporal joint density
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
0
Papers:
67
Citations:
0