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

TL;DR

This paper introduces ProtoGCN, a GCN-based model that captures fine-grained local motion patterns in skeleton sequences to improve the differentiation of similar actions, achieving state-of-the-art results.

Contribution

The paper proposes ProtoGCN, a novel prototype-based GCN model that emphasizes local skeleton dynamics for enhanced action recognition.

Findings

Achieves state-of-the-art performance on multiple benchmarks

Effectively distinguishes similar actions using prototype contrast

Demonstrates the importance of local motion details

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.