Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.11336 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917358882258944 |
|---|---|
| author | Pan, Hewen Wei, Cong Liang, Dashuang Huang, Zepeng Gao, Pengfei Zhou, Ziqi Xue, Lulu Yan, Pengfei Wei, Xiaoming Li, Minghui Hu, Shengshan |
| author_facet | Pan, Hewen Wei, Cong Liang, Dashuang Huang, Zepeng Gao, Pengfei Zhou, Ziqi Xue, Lulu Yan, Pengfei Wei, Xiaoming Li, Minghui Hu, Shengshan |
| contents | With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existing works are limited to specialized video understanding tasks, failing to achieve a comprehensive and multi-grained video perception. To bridge this gap, we introduce UFVideo, the first Video LLM with unified multi-grained cooperative understanding capabilities. Specifically, we design unified visual-language guided alignment to flexibly handle video understanding across global, pixel and temporal scales within a single model. UFVideo dynamically encodes the visual and text inputs of different tasks and generates the textual response, temporal localization, or grounded mask. Additionally, to evaluate challenging multi-grained video understanding tasks, we construct the UFVideo-Bench consisting of three distinct collaborative tasks within the scales, which demonstrates UFVideo's flexibility and advantages over GPT-4o. Furthermore, we validate the effectiveness of our model across 9 public benchmarks covering various common video understanding tasks, providing valuable insights for future Video LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11336 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models Pan, Hewen Wei, Cong Liang, Dashuang Huang, Zepeng Gao, Pengfei Zhou, Ziqi Xue, Lulu Yan, Pengfei Wei, Xiaoming Li, Minghui Hu, Shengshan Computer Vision and Pattern Recognition With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existing works are limited to specialized video understanding tasks, failing to achieve a comprehensive and multi-grained video perception. To bridge this gap, we introduce UFVideo, the first Video LLM with unified multi-grained cooperative understanding capabilities. Specifically, we design unified visual-language guided alignment to flexibly handle video understanding across global, pixel and temporal scales within a single model. UFVideo dynamically encodes the visual and text inputs of different tasks and generates the textual response, temporal localization, or grounded mask. Additionally, to evaluate challenging multi-grained video understanding tasks, we construct the UFVideo-Bench consisting of three distinct collaborative tasks within the scales, which demonstrates UFVideo's flexibility and advantages over GPT-4o. Furthermore, we validate the effectiveness of our model across 9 public benchmarks covering various common video understanding tasks, providing valuable insights for future Video LLMs. |
| title | UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.11336 |