SOURCE-LINKED INTELLIGENCE

Thinking with Cameras: Active Visual Reasoning via Dynamic Viewpoint Control for Surveillance Video Understanding

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Large vision-language models (LVLMs) have recently achieved remarkable progress in general-purpose video understanding. However, their application to surveillance videos remains challenging due to the lack of large-scale domain-specific datasets and the limitation of passive observation from fixed viewpoints. In surveillance scenarios, critical visual evidence can be easily missed when targets are distant, small, occluded, or move beyond the current camera view. In this work, we introduce CamVLM, a new framework for Thinking with Cameras, which enables LVLMs to actively acquire visual evidence

Read original source ↗ Open in workspace

recordType

paper

region

Global