Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
This work addresses the problem of action recognition from skeletal data for applications like human-computer interaction, but it is incremental as it builds on existing GCN methods with a novel prototype-based approach.
The paper tackles the challenge of distinguishing similar actions in skeleton-based action recognition by focusing on fine-grained motion details of local skeleton components, achieving state-of-the-art performance on multiple benchmark datasets such as NTU RGB+D, NTU RGB+D 120, Kinetics-Skeleton, and FineGYM.
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.