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

arXiv:2609.06475 · cs.CV · Submitted 2026-09-06 · Read on arXiv

cs.CV

Submitted: 2026-09-06

Updated: 2026-09-25

Code: https://github.com/xiaozhang79/CamVLM

Terminology

• Reinforcement Learning — 11× in this paper · explained in 4 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Benchmark — 8× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Active Perception — 5× in this paper · explained in 2 episodes
• Computer Vision and Pattern Recognition — 4× in this paper
• Ablation Studies — 3× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Action Space — 3× in this paper · explained in 1 episode
• Counterfactual Inference — 3× in this paper
• GRPO — 3× in this paper · explained in 6 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Basic Understanding — 2× in this paper
• Consistency — 2× in this paper · explained in 3 episodes
• Event Reasoning — 2× in this paper
• Temporal Reasoning — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Causal Understanding — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Group Relative Policy Optimization — 1× in this paper
• Hallucination — 1× in this paper · explained in 3 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes

Sources

• LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
• Qwen3-VL Technical Report
• LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning
• VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
• ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation
• Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• UDVideoQA: A Traffic Video Question Answering Dataset for Multi-Object Spatio-Temporal Reasoning in Urban Dynamics
• TrackVLA: Embodied Visual Tracking in the Wild
• MiMo-VL Technical Report
• Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
• Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models