ARC-Chapter: Structuring Hour-Long Videos into Navigable Chapters and Hierarchical Summaries
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918208155418624 |
|---|---|
| author | Pu, Junfu Wang, Teng Ge, Yixiao Ge, Yuying Li, Chen Shan, Ying |
| author_facet | Pu, Junfu Wang, Teng Ge, Yixiao Ge, Yuying Li, Chen Shan, Ying |
| contents | The proliferation of hour-long videos (e.g., lectures, podcasts, documentaries) has intensified demand for efficient content structuring. However, existing approaches are constrained by small-scale training with annotations that are typical short and coarse, restricting generalization to nuanced transitions in long videos. We introduce ARC-Chapter, the first large-scale video chaptering model trained on over million-level long video chapters, featuring bilingual, temporally grounded, and hierarchical chapter annotations. To achieve this goal, we curated a bilingual English-Chinese chapter dataset via a structured pipeline that unifies ASR transcripts, scene texts, visual captions into multi-level annotations, from short title to long summaries. We demonstrate clear performance improvements with data scaling, both in data volume and label intensity. Moreover, we design a new evaluation metric termed GRACE, which incorporates many-to-one segment overlaps and semantic similarity, better reflecting real-world chaptering flexibility. Extensive experiments demonstrate that ARC-Chapter establishes a new state-of-the-art by a significant margin, outperforming the previous best by 14.0% in F1 score and 11.3% in SODA score. Moreover, ARC-Chapter shows excellent transferability, improving the state-of-the-art on downstream tasks like dense video captioning on YouCook2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14349 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ARC-Chapter: Structuring Hour-Long Videos into Navigable Chapters and Hierarchical Summaries Pu, Junfu Wang, Teng Ge, Yixiao Ge, Yuying Li, Chen Shan, Ying Computer Vision and Pattern Recognition The proliferation of hour-long videos (e.g., lectures, podcasts, documentaries) has intensified demand for efficient content structuring. However, existing approaches are constrained by small-scale training with annotations that are typical short and coarse, restricting generalization to nuanced transitions in long videos. We introduce ARC-Chapter, the first large-scale video chaptering model trained on over million-level long video chapters, featuring bilingual, temporally grounded, and hierarchical chapter annotations. To achieve this goal, we curated a bilingual English-Chinese chapter dataset via a structured pipeline that unifies ASR transcripts, scene texts, visual captions into multi-level annotations, from short title to long summaries. We demonstrate clear performance improvements with data scaling, both in data volume and label intensity. Moreover, we design a new evaluation metric termed GRACE, which incorporates many-to-one segment overlaps and semantic similarity, better reflecting real-world chaptering flexibility. Extensive experiments demonstrate that ARC-Chapter establishes a new state-of-the-art by a significant margin, outperforming the previous best by 14.0% in F1 score and 11.3% in SODA score. Moreover, ARC-Chapter shows excellent transferability, improving the state-of-the-art on downstream tasks like dense video captioning on YouCook2. |
| title | ARC-Chapter: Structuring Hour-Long Videos into Navigable Chapters and Hierarchical Summaries |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.14349 |