From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos
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_ | 1866909265130684416 |
|---|---|
| author | Qiao, Tanqiu Li, Ruochen Li, Frederick W. B. Shum, Hubert P. H. |
| author_facet | Qiao, Tanqiu Li, Ruochen Li, Frederick W. B. Shum, Hubert P. H. |
| contents | Video-based Human-Object Interaction (HOI) recognition explores the intricate dynamics between humans and objects, which are essential for a comprehensive understanding of human behavior and intentions. While previous work has made significant strides, effectively integrating geometric and visual features to model dynamic relationships between humans and objects in a graph framework remains a challenge. In this work, we propose a novel end-to-end category to scenery framework, CATS, starting by generating geometric features for various categories through graphs respectively, then fusing them with corresponding visual features. Subsequently, we construct a scenery interactive graph with these enhanced geometric-visual features as nodes to learn the relationships among human and object categories. This methodological advance facilitates a deeper, more structured comprehension of interactions, bridging category-specific insights with broad scenery dynamics. Our method demonstrates state-of-the-art performance on two pivotal HOI benchmarks, including the MPHOI-72 dataset for multi-person HOIs and the single-person HOI CAD-120 dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_00917 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos Qiao, Tanqiu Li, Ruochen Li, Frederick W. B. Shum, Hubert P. H. Computer Vision and Pattern Recognition Video-based Human-Object Interaction (HOI) recognition explores the intricate dynamics between humans and objects, which are essential for a comprehensive understanding of human behavior and intentions. While previous work has made significant strides, effectively integrating geometric and visual features to model dynamic relationships between humans and objects in a graph framework remains a challenge. In this work, we propose a novel end-to-end category to scenery framework, CATS, starting by generating geometric features for various categories through graphs respectively, then fusing them with corresponding visual features. Subsequently, we construct a scenery interactive graph with these enhanced geometric-visual features as nodes to learn the relationships among human and object categories. This methodological advance facilitates a deeper, more structured comprehension of interactions, bridging category-specific insights with broad scenery dynamics. Our method demonstrates state-of-the-art performance on two pivotal HOI benchmarks, including the MPHOI-72 dataset for multi-person HOIs and the single-person HOI CAD-120 dataset. |
| title | From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.00917 |