Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search 文章

ArXiv CS.CV2026-05-28NEWSen作者: Zequn Xie, Guijin Luo, Chuxin Wang, Sihang Cai, Tao Jin, Zhou Zhao, Yixuan Tang
查看原文 →
关系图谱

Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search · 相关技术

相关技术

Multimodal Large Language Models (MLLMs)Detective Squad InteractionStructure-Aware Coarse RetrievalStructure-Semantic Decoupled CascadePose-Semantic Gap