MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912348901474304 |
|---|---|
| author | Cao, Shiwen Zhang, Zhaoxing Jiao, Junming Qiao, Juyi Song, Guowen Shen, Rong Meng, Xiangbing |
| author_facet | Cao, Shiwen Zhang, Zhaoxing Jiao, Junming Qiao, Juyi Song, Guowen Shen, Rong Meng, Xiangbing |
| contents | Even in the era of rapid advances in large models, video understanding remains a highly challenging task. Compared to texts or images, videos commonly contain more information with redundancy, requiring large models to properly allocate attention at a global level for comprehensive and accurate understanding. To address this, we propose a Multimodal hierarchical Attention focusing Self-reflective Reasoning (MASR) framework for agent-based video understanding. The key innovation lies in its ability to detect and prioritize segments of videos that are highly relevant to the query. Firstly, MASR realizes Multimodal Coarse-to-fine Relevance Sensing (MCRS) which enhances the correlation between the acquired contextual information and the query. Secondly, MASR employs Dilated Temporal Expansion (DTE) to mitigate the risk of missing crucial details when extracting semantic information from the focused frames selected through MCRS. By iteratively applying MCRS and DTE in the self-reflective reasoning process, MASR is able to adaptively adjust the attention to extract highly query-relevant context and therefore improve the response accuracy. In the EgoSchema dataset, MASR achieves a remarkable 5% performance gain over previous leading approaches. In the Next-QA and IntentQA datasets, it outperforms the state-of-the-art standards by 0.2% and 0.3% respectively. In the Video-MME dataset that contains long-term videos, MASR also performs better than other agent-based methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17213 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding Cao, Shiwen Zhang, Zhaoxing Jiao, Junming Qiao, Juyi Song, Guowen Shen, Rong Meng, Xiangbing Computer Vision and Pattern Recognition Artificial Intelligence Even in the era of rapid advances in large models, video understanding remains a highly challenging task. Compared to texts or images, videos commonly contain more information with redundancy, requiring large models to properly allocate attention at a global level for comprehensive and accurate understanding. To address this, we propose a Multimodal hierarchical Attention focusing Self-reflective Reasoning (MASR) framework for agent-based video understanding. The key innovation lies in its ability to detect and prioritize segments of videos that are highly relevant to the query. Firstly, MASR realizes Multimodal Coarse-to-fine Relevance Sensing (MCRS) which enhances the correlation between the acquired contextual information and the query. Secondly, MASR employs Dilated Temporal Expansion (DTE) to mitigate the risk of missing crucial details when extracting semantic information from the focused frames selected through MCRS. By iteratively applying MCRS and DTE in the self-reflective reasoning process, MASR is able to adaptively adjust the attention to extract highly query-relevant context and therefore improve the response accuracy. In the EgoSchema dataset, MASR achieves a remarkable 5% performance gain over previous leading approaches. In the Next-QA and IntentQA datasets, it outperforms the state-of-the-art standards by 0.2% and 0.3% respectively. In the Video-MME dataset that contains long-term videos, MASR also performs better than other agent-based methods. |
| title | MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.17213 |