Spatio-Temporal Multi-Subgraph GCN for 3D Human Motion Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916546956230656 |
|---|---|
| author | Wang, Jiexin Guo, Yiju Su, Bing |
| author_facet | Wang, Jiexin Guo, Yiju Su, Bing |
| contents | Human motion prediction (HMP) involves forecasting future human motion based on historical data. Graph Convolutional Networks (GCNs) have garnered widespread attention in this field for their proficiency in capturing relationships among joints in human motion. However, existing GCN-based methods tend to focus on either temporal-domain or spatial-domain features, or they combine spatio-temporal features without fully leveraging the complementarity and cross-dependency of these two features. In this paper, we propose the Spatial-Temporal Multi-Subgraph Graph Convolutional Network (STMS-GCN) to capture complex spatio-temporal dependencies in human motion. Specifically, we decouple the modeling of temporal and spatial dependencies, enabling cross-domain knowledge transfer at multiple scales through a spatio-temporal information consistency constraint mechanism. Besides, we utilize multiple subgraphs to extract richer motion information and enhance the learning associations of diverse subgraphs through a homogeneous information constraint mechanism. Extensive experiments on the standard HMP benchmarks demonstrate the superiority of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_00317 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Spatio-Temporal Multi-Subgraph GCN for 3D Human Motion Prediction Wang, Jiexin Guo, Yiju Su, Bing Computer Vision and Pattern Recognition Machine Learning Human motion prediction (HMP) involves forecasting future human motion based on historical data. Graph Convolutional Networks (GCNs) have garnered widespread attention in this field for their proficiency in capturing relationships among joints in human motion. However, existing GCN-based methods tend to focus on either temporal-domain or spatial-domain features, or they combine spatio-temporal features without fully leveraging the complementarity and cross-dependency of these two features. In this paper, we propose the Spatial-Temporal Multi-Subgraph Graph Convolutional Network (STMS-GCN) to capture complex spatio-temporal dependencies in human motion. Specifically, we decouple the modeling of temporal and spatial dependencies, enabling cross-domain knowledge transfer at multiple scales through a spatio-temporal information consistency constraint mechanism. Besides, we utilize multiple subgraphs to extract richer motion information and enhance the learning associations of diverse subgraphs through a homogeneous information constraint mechanism. Extensive experiments on the standard HMP benchmarks demonstrate the superiority of our method. |
| title | Spatio-Temporal Multi-Subgraph GCN for 3D Human Motion Prediction |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2501.00317 |