MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916153579798528 |
|---|---|
| author | Song, Enxin Chai, Wenhao Wang, Guanhong Zhang, Yucheng Zhou, Haoyang Wu, Feiyang Chi, Haozhe Guo, Xun Ye, Tian Zhang, Yanting Lu, Yan Hwang, Jenq-Neng Wang, Gaoang |
| author_facet | Song, Enxin Chai, Wenhao Wang, Guanhong Zhang, Yucheng Zhou, Haoyang Wu, Feiyang Chi, Haozhe Guo, Xun Ye, Tian Zhang, Yanting Lu, Yan Hwang, Jenq-Neng Wang, Gaoang |
| contents | Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose additional challenges. Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose the MovieChat to overcome these challenges. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video and 14K manual annotations for validation of the effectiveness of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_16449 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MovieChat: From Dense Token to Sparse Memory for Long Video Understanding Song, Enxin Chai, Wenhao Wang, Guanhong Zhang, Yucheng Zhou, Haoyang Wu, Feiyang Chi, Haozhe Guo, Xun Ye, Tian Zhang, Yanting Lu, Yan Hwang, Jenq-Neng Wang, Gaoang Computer Vision and Pattern Recognition Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose additional challenges. Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose the MovieChat to overcome these challenges. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video and 14K manual annotations for validation of the effectiveness of our method. |
| title | MovieChat: From Dense Token to Sparse Memory for Long Video Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2307.16449 |