Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.20939 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916867371696128 |
|---|---|
| author | Ge, Yuying Ge, Yixiao Li, Chen Wang, Teng Pu, Junfu Li, Yizhuo Qiu, Lu Ma, Jin Duan, Lisheng Zuo, Xinyu Luo, Jinwen Gu, Weibo Li, Zexuan Zhang, Xiaojing Tao, Yangyu Hu, Han Wang, Di Shan, Ying |
| author_facet | Ge, Yuying Ge, Yixiao Li, Chen Wang, Teng Pu, Junfu Li, Yizhuo Qiu, Lu Ma, Jin Duan, Lisheng Zuo, Xinyu Luo, Jinwen Gu, Weibo Li, Zexuan Zhang, Xiaojing Tao, Yangyu Hu, Han Wang, Di Shan, Ying |
| contents | Real-world user-generated short videos, especially those distributed on platforms such as WeChat Channel and TikTok, dominate the mobile internet. However, current large multimodal models lack essential temporally-structured, detailed, and in-depth video comprehension capabilities, which are the cornerstone of effective video search and recommendation, as well as emerging video applications. Understanding real-world shorts is actually challenging due to their complex visual elements, high information density in both visuals and audio, and fast pacing that focuses on emotional expression and viewpoint delivery. This requires advanced reasoning to effectively integrate multimodal information, including visual, audio, and text. In this work, we introduce ARC-Hunyuan-Video, a multimodal model that processes visual, audio, and textual signals from raw video inputs end-to-end for structured comprehension. The model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning. Leveraging high-quality data from an automated annotation pipeline, our compact 7B-parameter model is trained through a comprehensive regimen: pre-training, instruction fine-tuning, cold start, reinforcement learning (RL) post-training, and final instruction fine-tuning. Quantitative evaluations on our introduced benchmark ShortVid-Bench and qualitative comparisons demonstrate its strong performance in real-world video comprehension, and it supports zero-shot or fine-tuning with a few samples for diverse downstream applications. The real-world production deployment of our model has yielded tangible and measurable improvements in user engagement and satisfaction, a success supported by its remarkable efficiency, with stress tests indicating an inference time of just 10 seconds for a one-minute video on H20 GPU. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20939 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts Ge, Yuying Ge, Yixiao Li, Chen Wang, Teng Pu, Junfu Li, Yizhuo Qiu, Lu Ma, Jin Duan, Lisheng Zuo, Xinyu Luo, Jinwen Gu, Weibo Li, Zexuan Zhang, Xiaojing Tao, Yangyu Hu, Han Wang, Di Shan, Ying Computer Vision and Pattern Recognition Real-world user-generated short videos, especially those distributed on platforms such as WeChat Channel and TikTok, dominate the mobile internet. However, current large multimodal models lack essential temporally-structured, detailed, and in-depth video comprehension capabilities, which are the cornerstone of effective video search and recommendation, as well as emerging video applications. Understanding real-world shorts is actually challenging due to their complex visual elements, high information density in both visuals and audio, and fast pacing that focuses on emotional expression and viewpoint delivery. This requires advanced reasoning to effectively integrate multimodal information, including visual, audio, and text. In this work, we introduce ARC-Hunyuan-Video, a multimodal model that processes visual, audio, and textual signals from raw video inputs end-to-end for structured comprehension. The model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning. Leveraging high-quality data from an automated annotation pipeline, our compact 7B-parameter model is trained through a comprehensive regimen: pre-training, instruction fine-tuning, cold start, reinforcement learning (RL) post-training, and final instruction fine-tuning. Quantitative evaluations on our introduced benchmark ShortVid-Bench and qualitative comparisons demonstrate its strong performance in real-world video comprehension, and it supports zero-shot or fine-tuning with a few samples for diverse downstream applications. The real-world production deployment of our model has yielded tangible and measurable improvements in user engagement and satisfaction, a success supported by its remarkable efficiency, with stress tests indicating an inference time of just 10 seconds for a one-minute video on H20 GPU. |
| title | ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.20939 |