Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.16079 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909047195697152 |
|---|---|
| author | Zhao, Yiming Zeng, Yu Huang, Wenxuan Fang, Zhen Miao, Qing Su, Qisheng Zhao, Jiawei Cai, Jiayin Chen, Lin Chen, Zehui Qi, Yukun Hu, Yao Jiang, Xiaolong Zhao, Feng |
| author_facet | Zhao, Yiming Zeng, Yu Huang, Wenxuan Fang, Zhen Miao, Qing Su, Qisheng Zhao, Jiawei Cai, Jiayin Chen, Lin Chen, Zehui Qi, Yukun Hu, Yao Jiang, Xiaolong Zhao, Feng |
| contents | Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring precise spatiotemporal localization at the instance level. Existing methods primarily rely on text prompts for human-model interaction, but these prompts struggle to provide precise spatial and temporal references, resulting in poor user experience. Furthermore, current approaches typically decouple visual perception from language reasoning, centering reasoning around language rather than visual content, which limits the model's ability to proactively perceive fine-grained visual evidence. To address these challenges, we propose VideoSeeker, a novel paradigm for instance-level video understanding through visual prompts. VideoSeeker seamlessly integrates agentic reasoning with instance-level video understanding tasks, enabling the model to proactively perceive and retrieve relevant video segments on demand. We construct a four-stage fully automated data synthesis pipeline to efficiently generate large-scale, high-quality instance-level video data. We internalize tool-calling and proactive perception capabilities into the model via cold-start supervision and RL training, building a powerful video understanding model. Experiments demonstrate that our model achieves an average improvement of +13.7% over baselines on instance-level video understanding tasks, surpassing powerful closed-source models such as GPT-4o and Gemini-2.5-Pro, while also showing effective transferability on general video understanding benchmarks. The relevant datasets and code will be released publicly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16079 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation Zhao, Yiming Zeng, Yu Huang, Wenxuan Fang, Zhen Miao, Qing Su, Qisheng Zhao, Jiawei Cai, Jiayin Chen, Lin Chen, Zehui Qi, Yukun Hu, Yao Jiang, Xiaolong Zhao, Feng Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring precise spatiotemporal localization at the instance level. Existing methods primarily rely on text prompts for human-model interaction, but these prompts struggle to provide precise spatial and temporal references, resulting in poor user experience. Furthermore, current approaches typically decouple visual perception from language reasoning, centering reasoning around language rather than visual content, which limits the model's ability to proactively perceive fine-grained visual evidence. To address these challenges, we propose VideoSeeker, a novel paradigm for instance-level video understanding through visual prompts. VideoSeeker seamlessly integrates agentic reasoning with instance-level video understanding tasks, enabling the model to proactively perceive and retrieve relevant video segments on demand. We construct a four-stage fully automated data synthesis pipeline to efficiently generate large-scale, high-quality instance-level video data. We internalize tool-calling and proactive perception capabilities into the model via cold-start supervision and RL training, building a powerful video understanding model. Experiments demonstrate that our model achieves an average improvement of +13.7% over baselines on instance-level video understanding tasks, surpassing powerful closed-source models such as GPT-4o and Gemini-2.5-Pro, while also showing effective transferability on general video understanding benchmarks. The relevant datasets and code will be released publicly. |
| title | VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2605.16079 |