Research map / Vision-language and multimodal / Human and embodied modeling
ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language
Zhe Wang, Zhiyuan Fang, Jun Wang, Yezhou Yang
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 |
|---|---|---|---|
| add segmentation loss to ID-loss baseline (ablation) | ViTAA baseline · CUHK-PEDES test | R@1: 29.68 -> 30.93 | Improved |
| add attribute alignment to ID-loss baseline (ablation) | ViTAA baseline · CUHK-PEDES test | R@1: 29.68 -> 31.40 | Improved |
| add attribute alignment to segmentation model (ablation) | ViTAA · CUHK-PEDES test | R@1: 30.93 -> 39.26 | Improved |
| add global alignment to ID-loss baseline (ablation) | ViTAA baseline · CUHK-PEDES test | R@1: 29.68 -> 52.27 | Improved |
| add segmentation and attribute alignment to global alignment (ablation) | ViTAA · CUHK-PEDES test | R@1: 52.27 -> 55.97 | Improved |
| add segmentation and attribute alignment to global alignment (ablation) | ViTAA · CUHK-PEDES test | R@10: 81.61 -> 83.52 | Improved |
| add global alignment to segmentation + attribute alignment (ablation) | ViTAA · CUHK-PEDES test | R@1: 39.26 -> 55.97 | Improved |
| increase K in K-reciprocal sampling beyond 8 (ablation) | ViTAA · CUHK-PEDES test | R@1 and R@10: best R@1 and R@10 is achieved when K is set to 8 | Hurt |
| use ViTAA instead of GALM | person search · CUHK-PEDES test | R@1: 54.12 -> 55.97 | Improved |
| use ViTAA instead of MIA | person search · CUHK-PEDES test | R@1: 53.10 -> 55.97 | Improved |
Later papers that compared with this method
2 later accepted papers report ViTAA as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- A Simple and Robust Correlation Filtering Method for Text-Based Person Search (ECCV 2022 · better on 2 of 2 shared results)
- LapsCore: Language-Guided Person Search via Color Reasoning (ICCV 2021 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Tackling Alignment Ambiguity in Person Retrieval through Conversational Attribute Mining (CVPR 2026 · similarity 0.87)
- Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval (NeurIPS 2025 · similarity 0.86)
- Visual Perturbation for Text-Based Person Search (AAAI 2025 · similarity 0.85)
- Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models (ICML 2024 · similarity 0.84)
- An Empirical Study of CLIP for Text-Based Person Search (AAAI 2024 · similarity 0.84)
- Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification (AAAI 2024 · 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.
