Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2502.09967 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917922910240768 |
|---|---|
| author | Wang, Zhuming Zheng, Yihao Li, Jiarui Wu, Yaofei Huang, Yan Li, Zun Wu, Lifang Wang, Liang |
| author_facet | Wang, Zhuming Zheng, Yihao Li, Jiarui Wu, Yaofei Huang, Yan Li, Zun Wu, Lifang Wang, Liang |
| contents | Existing weakly supervised group activity recognition methods rely on object detectors or attention mechanisms to capture key areas automatically. However, they overlook the semantic information associated with captured areas, which may adversely affect the recognition performance. In this paper, we propose a novel framework named Visual Conceptual Knowledge Guided Action Map (VicKAM) which effectively captures the locations of individual actions and integrates them with action semantics for weakly supervised group activity recognition.It generates individual action prototypes from training set as visual conceptual knowledge to bridge action semantics and visual representations. Guided by this knowledge, VicKAM produces action maps that indicate the likelihood of each action occurring at various locations, based on image correlation theorem. It further augments individual action maps using group activity related statistical information, representing individual action distribution under different group activities, to establish connections between action maps and specific group activities. The augmented action map is incorporated with action semantic representations for group activity recognition.Extensive experiments on two public benchmarks, the Volleyball and the NBA datasets, demonstrate the effectiveness of our proposed method, even in cases of limited training data. The code will be released later. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09967 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition Wang, Zhuming Zheng, Yihao Li, Jiarui Wu, Yaofei Huang, Yan Li, Zun Wu, Lifang Wang, Liang Computer Vision and Pattern Recognition Existing weakly supervised group activity recognition methods rely on object detectors or attention mechanisms to capture key areas automatically. However, they overlook the semantic information associated with captured areas, which may adversely affect the recognition performance. In this paper, we propose a novel framework named Visual Conceptual Knowledge Guided Action Map (VicKAM) which effectively captures the locations of individual actions and integrates them with action semantics for weakly supervised group activity recognition.It generates individual action prototypes from training set as visual conceptual knowledge to bridge action semantics and visual representations. Guided by this knowledge, VicKAM produces action maps that indicate the likelihood of each action occurring at various locations, based on image correlation theorem. It further augments individual action maps using group activity related statistical information, representing individual action distribution under different group activities, to establish connections between action maps and specific group activities. The augmented action map is incorporated with action semantic representations for group activity recognition.Extensive experiments on two public benchmarks, the Volleyball and the NBA datasets, demonstrate the effectiveness of our proposed method, even in cases of limited training data. The code will be released later. |
| title | VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.09967 |