Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916142196457472 |
|---|---|
| author | Medina, Edgar Loh, Leyong Gurung, Namrata Oh, Kyung Hun Heller, Niels |
| author_facet | Medina, Edgar Loh, Leyong Gurung, Namrata Oh, Kyung Hun Heller, Niels |
| contents | Human motion prediction is still an open problem extremely important for autonomous driving and safety applications. Due to the complex spatiotemporal relation of motion sequences, this remains a challenging problem not only for movement prediction but also to perform a preliminary interpretation of the joint connections. In this work, we present a Context-based Interpretable Spatio-Temporal Graph Convolutional Network (CIST-GCN), as an efficient 3D human pose forecasting model based on GCNs that encompasses specific layers, aiding model interpretability and providing information that might be useful when analyzing motion distribution and body behavior. Our architecture extracts meaningful information from pose sequences, aggregates displacements and accelerations into the input model, and finally predicts the output displacements. Extensive experiments on Human 3.6M, AMASS, 3DPW, and ExPI datasets demonstrate that CIST-GCN outperforms previous methods in human motion prediction and robustness. Since the idea of enhancing interpretability for motion prediction has its merits, we showcase experiments towards it and provide preliminary evaluations of such insights here. available code: https://github.com/QualityMinds/cistgcn |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_19237 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting Medina, Edgar Loh, Leyong Gurung, Namrata Oh, Kyung Hun Heller, Niels Computer Vision and Pattern Recognition Artificial Intelligence Human motion prediction is still an open problem extremely important for autonomous driving and safety applications. Due to the complex spatiotemporal relation of motion sequences, this remains a challenging problem not only for movement prediction but also to perform a preliminary interpretation of the joint connections. In this work, we present a Context-based Interpretable Spatio-Temporal Graph Convolutional Network (CIST-GCN), as an efficient 3D human pose forecasting model based on GCNs that encompasses specific layers, aiding model interpretability and providing information that might be useful when analyzing motion distribution and body behavior. Our architecture extracts meaningful information from pose sequences, aggregates displacements and accelerations into the input model, and finally predicts the output displacements. Extensive experiments on Human 3.6M, AMASS, 3DPW, and ExPI datasets demonstrate that CIST-GCN outperforms previous methods in human motion prediction and robustness. Since the idea of enhancing interpretability for motion prediction has its merits, we showcase experiments towards it and provide preliminary evaluations of such insights here. available code: https://github.com/QualityMinds/cistgcn |
| title | Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2402.19237 |