Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913168010248192 |
|---|---|
| author | Xie, Zequn Luo, Guijin Wang, Chuxin Cai, Sihang Jin, Tao Zhao, Zhou Tang, Yixuan |
| author_facet | Xie, Zequn Luo, Guijin Wang, Chuxin Cai, Sihang Jin, Tao Zhao, Zhou Tang, Yixuan |
| contents | Text-based person anomaly search retrieves specific behavioral events from surveillance archives using natural-language queries. Although recent pose-aware methods align geometric structures well, they face a fundamental Pose-Semantic Gap: semantically different actions can share similar skeletal geometries. While Multimodal Large Language Models (MLLMs) can reduce this ambiguity, using them for large-scale retrieval is computationally prohibitive. We propose the Structure-Semantic Decoupled Cascade (SSDC) framework, which decouples retrieval into two stages: (1) Structure-Aware Coarse Retrieval, where a lightweight model quickly filters candidates by skeletal similarity ; and (2) Detective Squad Interaction, a multi-agent semantic verification module. The squad consists of a Detective for fast binary filtering, an Analyst for evidence extraction, and a Writer for semantic synthesis. Finally, we re-rank candidates by fusing the synthesized captions with structural priors. Experiments on the PAB benchmark show that SSDC achieves state-of-the-art performance by balancing efficiency and semantic reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_23282 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search Xie, Zequn Luo, Guijin Wang, Chuxin Cai, Sihang Jin, Tao Zhao, Zhou Tang, Yixuan Computer Vision and Pattern Recognition Multimedia Text-based person anomaly search retrieves specific behavioral events from surveillance archives using natural-language queries. Although recent pose-aware methods align geometric structures well, they face a fundamental Pose-Semantic Gap: semantically different actions can share similar skeletal geometries. While Multimodal Large Language Models (MLLMs) can reduce this ambiguity, using them for large-scale retrieval is computationally prohibitive. We propose the Structure-Semantic Decoupled Cascade (SSDC) framework, which decouples retrieval into two stages: (1) Structure-Aware Coarse Retrieval, where a lightweight model quickly filters candidates by skeletal similarity ; and (2) Detective Squad Interaction, a multi-agent semantic verification module. The squad consists of a Detective for fast binary filtering, an Analyst for evidence extraction, and a Writer for semantic synthesis. Finally, we re-rank candidates by fusing the synthesized captions with structural priors. Experiments on the PAB benchmark show that SSDC achieves state-of-the-art performance by balancing efficiency and semantic reasoning. |
| title | Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2604.23282 |