GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jiang, Lei, Yang, Weixin, Zhang, Xin, Ni, Hao
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916260774674432
author Jiang, Lei
Yang, Weixin
Zhang, Xin
Ni, Hao
author_facet Jiang, Lei
Yang, Weixin
Zhang, Xin
Ni, Hao
contents Skeleton-based action recognition (SAR) in videos is an important but challenging task in computer vision. The recent state-of-the-art (SOTA) models for SAR are primarily based on graph convolutional neural networks (GCNs), which are powerful in extracting the spatial information of skeleton data. However, it is yet clear that such GCN-based models can effectively capture the temporal dynamics of human action sequences. To this end, we propose the G-Dev layer, which exploits the path development -- a principled and parsimonious representation for sequential data by leveraging the Lie group structure. By integrating the G-Dev layer, the hybrid G-DevLSTM module enhances the traditional LSTM to reduce the time dimension while retaining high-frequency information. It can be conveniently applied to any temporal graph data, complementing existing advanced GCN-based models. Our empirical studies on the NTU60, NTU120 and Chalearn2013 datasets demonstrate that our proposed GCN-DevLSTM network consistently improves the strong GCN baseline models and achieves SOTA results with superior robustness in SAR tasks. The code is available at https://github.com/DeepIntoStreams/GCN-DevLSTM.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15212
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition
Jiang, Lei
Yang, Weixin
Zhang, Xin
Ni, Hao
Computer Vision and Pattern Recognition
Skeleton-based action recognition (SAR) in videos is an important but challenging task in computer vision. The recent state-of-the-art (SOTA) models for SAR are primarily based on graph convolutional neural networks (GCNs), which are powerful in extracting the spatial information of skeleton data. However, it is yet clear that such GCN-based models can effectively capture the temporal dynamics of human action sequences. To this end, we propose the G-Dev layer, which exploits the path development -- a principled and parsimonious representation for sequential data by leveraging the Lie group structure. By integrating the G-Dev layer, the hybrid G-DevLSTM module enhances the traditional LSTM to reduce the time dimension while retaining high-frequency information. It can be conveniently applied to any temporal graph data, complementing existing advanced GCN-based models. Our empirical studies on the NTU60, NTU120 and Chalearn2013 datasets demonstrate that our proposed GCN-DevLSTM network consistently improves the strong GCN baseline models and achieves SOTA results with superior robustness in SAR tasks. The code is available at https://github.com/DeepIntoStreams/GCN-DevLSTM.
title GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.15212