Saved in:
Bibliographic Details
Main Authors: Liu, Cheng, Zhang, Daou, Liu, Tingxu, Wang, Yuhan, Chen, Jinyang, Li, Yuexuan, Xiao, Xinying, Xin, Chenbo, Wang, Ziru, Wu, Weichao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.06189
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • With the acceleration of urbanization, criminal behavior in public scenes poses an increasingly serious threat to social security. Traditional anomaly detection methods based on feature recognition struggle to capture high-level behavioral semantics from historical information, while generative approaches based on Large Language Models (LLMs) often fail to meet real-time requirements. To address these challenges, we propose MA-CBP, a criminal behavior prediction framework based on multi-agent asynchronous collaboration. This framework transforms real-time video streams into frame-level semantic descriptions, constructs causally consistent historical summaries, and fuses adjacent image frames to perform joint reasoning over long- and short-term contexts. The resulting behavioral decisions include key elements such as event subjects, locations, and causes, enabling early warning of potential criminal activity. In addition, we construct a high-quality criminal behavior dataset that provides multi-scale language supervision, including frame-level, summary-level, and event-level semantic annotations. Experimental results demonstrate that our method achieves superior performance on multiple datasets and offers a promising solution for risk warning in urban public safety scenarios.