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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Hongda, Liu, Yunfan, Ren, Min, Wang, Hao, Wang, Yunlong, Sun, Zhenan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916657623990272
author Liu, Hongda
Liu, Yunfan
Ren, Min
Wang, Hao
Wang, Yunlong
Sun, Zhenan
author_facet Liu, Hongda
Liu, Yunfan
Ren, Min
Wang, Hao
Wang, Yunlong
Sun, Zhenan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18941
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
Liu, Hongda
Liu, Yunfan
Ren, Min
Wang, Hao
Wang, Yunlong
Sun, Zhenan
Computer Vision and Pattern Recognition
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.
title Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.18941