Video Understanding: From Geometry and Semantics to Unified Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912972927926272 |
|---|---|
| author | An, Zhaochong Li, Zirui Ye, Mingqiao Qiao, Feng Li, Jiaang Wu, Zongwei Thengane, Vishal Li, Chengzu Li, Lei Van Gool, Luc Sun, Guolei Belongie, Serge |
| author_facet | An, Zhaochong Li, Zirui Ye, Mingqiao Qiao, Feng Li, Jiaang Wu, Zongwei Thengane, Vishal Li, Chengzu Li, Lei Van Gool, Luc Sun, Guolei Belongie, Serge |
| contents | Video understanding aims to enable models to perceive, reason about, and interact with the dynamic visual world. In contrast to image understanding, video understanding inherently requires modeling temporal dynamics and evolving visual context, placing stronger demands on spatiotemporal reasoning and making it a foundational problem in computer vision. In this survey, we present a structured overview of video understanding by organizing the literature into three complementary perspectives: low-level video geometry understanding, high-level semantic understanding, and unified video understanding models. We further highlight a broader shift from isolated, task-specific pipelines toward unified modeling paradigms that can be adapted to diverse downstream objectives, enabling a more systematic view of recent progress. By consolidating these perspectives, this survey provides a coherent map of the evolving video understanding landscape, summarizes key modeling trends and design principles, and outlines open challenges toward building robust, scalable, and unified video foundation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17840 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Video Understanding: From Geometry and Semantics to Unified Models An, Zhaochong Li, Zirui Ye, Mingqiao Qiao, Feng Li, Jiaang Wu, Zongwei Thengane, Vishal Li, Chengzu Li, Lei Van Gool, Luc Sun, Guolei Belongie, Serge Computer Vision and Pattern Recognition Video understanding aims to enable models to perceive, reason about, and interact with the dynamic visual world. In contrast to image understanding, video understanding inherently requires modeling temporal dynamics and evolving visual context, placing stronger demands on spatiotemporal reasoning and making it a foundational problem in computer vision. In this survey, we present a structured overview of video understanding by organizing the literature into three complementary perspectives: low-level video geometry understanding, high-level semantic understanding, and unified video understanding models. We further highlight a broader shift from isolated, task-specific pipelines toward unified modeling paradigms that can be adapted to diverse downstream objectives, enabling a more systematic view of recent progress. By consolidating these perspectives, this survey provides a coherent map of the evolving video understanding landscape, summarizes key modeling trends and design principles, and outlines open challenges toward building robust, scalable, and unified video foundation models. |
| title | Video Understanding: From Geometry and Semantics to Unified Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.17840 |