Research map / Label-efficient and robust learning / Recognition and long-tail
Infrared-Visible Cross-Modal Person Re-Identification with an X Modality
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 learned X modality (ablation) | two-modality ReID baseline (ResNet-50) · SYSU-MM01 | rank-1: 38.39 -> 45.57 | Helped |
| add learned X modality (ablation) | two-modality ReID baseline (DenseNet-121) · SYSU-MM01 | mAP: 39.68 -> 41.09 | Helped |
| add cross modality gap constraint (ablation) | Baseline+X (ResNet-50) · SYSU-MM01 | mAP: 47.03 -> 50.73 | Helped |
| add cross modality gap constraint (ablation) | Baseline+X (DenseNet-121) · SYSU-MM01 | rank-1: 41.29 -> 48.20 | Helped |
| learned 1x1-conv X generator instead of fixed V channel (ablation) | Baseline+X · SYSU-MM01 | mAP: 46.49 -> 47.03 | Helped |
| learned X generator instead of grayscale (ablation) | Baseline+X · SYSU-MM01 | mAP: 42.92 -> 47.03 | Helped |
| XIV vs AlignGAN with same backbone | IV-ReID · SYSU-MM01 | mAP: 40.70 -> 44.22 | Helped |
| XIV vs AlignGAN with same backbone | IV-ReID · SYSU-MM01 | rank-10: 85.00 -> 83.57 | Hurt |
| vary trade-off lambda between MRG and CMG (ablation) | XIV · SYSU-MM01 | rank-1 and mAP | Mixed |
Closest papers by meaning
- Cross-Modality Person Re-identification with Memory-Based Contrastive Embedding (AAAI 2023 · similarity 0.92)
- Cross-Modality Perturbation Synergy Attack for Person Re-identification (NeurIPS 2024 · similarity 0.91)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.90)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.90)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.89)
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.89)
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.