Research map / Label-efficient and robust learning / Recognition and long-tail
Person Re-Identification by Contour Sketch Under Moderate Clothing Change
Qize Yang, Ancong Wu, Wei‐Shi 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 |
|---|---|---|---|
| add the SPT transformation layer (ablation) | our model · PRCC cross-clothes | Rank-1: 25.74 -> 34.38 | Improved |
| add the angle-specific extractor (ASE) (ablation) | our model · PRCC cross-clothes | Rank-1: 28.00 -> 34.38 | Improved |
| add loss L_t (ablation) | our model · PRCC cross-clothes | Rank-1: 31.39 -> 34.38 | Improved |
| learn SPT angles instead of fixing theta (ablation) | our model · PRCC cross-clothes | Rank-1: 31.05 -> 34.38 | Improved |
| combine all three streams instead of single stream 1 (ablation) | our model · PRCC cross-clothes | Rank-1: 28.71 -> 34.38 | Improved |
| sample 336 angles instead of 224 (ablation) | our model · PRCC cross-clothes | Rank-1: 34.38 -> 34.76 | No clear effect |
| sample 224 angles instead of 112 (ablation) | our model · PRCC cross-clothes | Rank-1: 31.45 -> 34.38 | Improved |
| update lambda_k instead of updating theta_i directly (ablation) | our model · PRCC cross-clothes | Rank-1: 1.48 -> 34.38 | Improved |
| use image center as SPT origin instead of PTN (ablation) | our model · PRCC cross-clothes | Rank-1: 20.95 -> 34.38 | Improved |
| use neck or hip as SPT origin instead of image center (ablation) | our model · PRCC cross-clothes | Rank-1: 34.38 -> 32.93 | No clear effect |
| use SPT instead of STN or deformable conv in the network | our model · PRCC cross-clothes | Rank-1: 27.47 -> 34.38 | Improved |
| replace RGB inputs with contour sketch for PCB | PCB · PRCC same clothes | Rank-1: 86.88 -> 57.36 | Hurt |
Closest papers by meaning
- Clothes-Changing Person Re-Identification With RGB Modality Only (CVPR 2022 · similarity 0.91)
- DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID (CVPR 2025 · similarity 0.90)
- DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change (ICCV 2023 · similarity 0.90)
- Fine-Grained Shape-Appearance Mutual Learning for Cloth-Changing Person Re-Identification (CVPR 2021 · similarity 0.90)
- Identity-Clothing Similarity Modeling for Unsupervised Clothing Change Person Re-Identification (CVPR 2025 · similarity 0.88)
- DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification (CVPR 2025 · similarity 0.86)
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.
