Research map / Vision-language and multimodal / Human and embodied modeling
Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search
Shuyu Yang, Yaxiong Wang, Li Zhu, Zhedong Zheng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train X-VLM on 0.1M synthetic PAB pairs | X-VLM · PAB test | R@1: 71.94 -> 81.95 | Improved |
| add pose-aware image encoder (PE) (ablation) | X-VLM baseline · PAB test (1M) | R@1: 83.47 -> 84.13 | Improved |
| add identity-based hard negative mining (IHNM) (ablation) | X-VLM baseline · PAB test (1M) | R@1: 83.47 -> 84.48 | Improved |
| add both PE and IHNM (ablation) | X-VLM baseline · PAB test (1M) | R@1: 83.47 -> 84.93 | Improved |
| add both PE and IHNM | X-VLM · PAB test (0.1M) | R@1: 81.95 -> 83.06 | Improved |
| train CMP on 1M instead of 0.1M pairs | CMP · PAB test | R@1: 83.06 -> 84.93 | Improved |
| train CMP on 1M instead of 0.1M pairs | CMP · UCC OOD | R@1: 54.12 -> 55.23 | Improved |
| add PE and IHNM (ablation) | X-VLM baseline · PAB multi-weather mean | R@1: 64.11 -> 67.12 | Improved |
| add IHNM only vs full CMP (ablation) | CMP · PAB multi-weather Dark + Rain | R@1: 40.75 -> 39.03 | Hurt |
| use behavior search evaluation instead of identity search | CMP · PAB test | R@1: 94.34 -> 84.93 | Hurt |
| use CMP instead of RaSa | RaSa · UCC OOD (0.1M) | R@1: 54.12 -> 54.12 | No clear effect |
| use only 10% of PAB training data with hard negative sampling (ablation) | CMP · PAB test | recall | No clear effect |
Closest papers by meaning
- A Survey on Text-Based Person Search (TPAMI 2026 · similarity 0.89)
- Diverse Person: Customize Your Own Dataset for Text-Based Person Search (AAAI 2024 · similarity 0.86)
- Exploring the Potential of Large Vision-Language Models for Unsupervised Text-Based Person Retrieval (AAAI 2025 · similarity 0.84)
- Divide and Conquer: Hybrid Pre-training for Person Search (AAAI 2024 · similarity 0.84)
- Adaptive Uncertainty-Based Learning for Text-Based Person Retrieval (AAAI 2024 · similarity 0.83)
- Visual Perturbation for Text-Based Person Search (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
