Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition

20citations
arXiv:2411.18941
20
citations
#401
in CVPR 2025
of 2873 papers
6
Top Authors
4
Data Points

Abstract

In skeleton-based action recognition, a key challenge is distinguishing between actions with similar trajectories of joints due to the lack of image-level details in skeletal representations. Recognizing that the differentiation of similar actions relies on subtle motion details in specific body parts, we direct our approach to focus on the fine-grained motion of local skeleton components. To this end, we introduce ProtoGCN, a Graph Convolutional Network (GCN)-based model that breaks down the dynamics of entire skeleton sequences into a combination of learnable prototypes representing core motion patterns of action units. By contrasting the reconstruction of prototypes, ProtoGCN can effectively identify and enhance the discriminative representation of similar actions. Without bells and whistles, ProtoGCN achieves state-of-the-art performance on multiple benchmark datasets, including NTU RGB+D, NTU RGB+D 120, Kinetics-Skeleton, and FineGYM, which demonstrates the effectiveness of the proposed method. The code is available at https://github.com/firework8/ProtoGCN.

Citation History

Jan 25, 2026
16
Feb 13, 2026
20+4
Feb 13, 2026
20
Feb 13, 2026
20