Video Understanding: From Geometry and Semantics to Unified Models
Abstract
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.
Cite
@article{arxiv.2603.17840,
title = {Video Understanding: From Geometry and Semantics to Unified Models},
author = {Zhaochong An and Zirui Li and Mingqiao Ye and Feng Qiao and Jiaang Li and Zongwei Wu and Vishal Thengane and Chengzu Li and Lei Li and Luc Van Gool and Guolei Sun and Serge Belongie},
journal= {arXiv preprint arXiv:2603.17840},
year = {2026}
}
Comments
A comprehensive survey of video understanding, spanning low-level geometry, high-level semantics, and unified understanding models