Research map / Vision-language and multimodal / Cross-modal learning
Towards Modality-Agnostic Person Re-Identification With Descriptive Query
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 task-aware dynamic training to task-specific modality learning (ablation) | UNIReID · Tri-CUHK-PEDES, Text-to-RGB | Rank-1 accuracy: 51.06 -> 53.48 | Helped |
| Add task-aware dynamic training to task-specific modality learning (ablation) | UNIReID · Tri-ICFG-PEDES, Text-to-RGB | Rank-1 accuracy: 50.68 -> 55.04 | Helped |
| Add task-aware dynamic training to task-specific modality learning (ablation) | UNIReID · Tri-RSTPReid, Text-to-RGB | Rank-1 accuracy: 47.55 -> 49.15 | Helped |
| Add task-aware dynamic training to task-specific modality learning (ablation) | UNIReID · Tri-CUHK-PEDES, Sketch-to-RGB | Rank-1 accuracy: 80.70 -> 84.02 | Helped |
| Add task-aware dynamic training to task-specific modality learning (ablation) | UNIReID · Tri-ICFG-PEDES, Sketch-to-RGB | Rank-1 accuracy: 70.11 -> 76.15 | Helped |
| Add task-aware dynamic training to task-specific modality learning (ablation) | UNIReID · Tri-RSTPReid, Sketch-to-RGB | Rank-1 accuracy: 60.10 -> 64.90 | Helped |
| Add task-aware dynamic training to task-specific modality learning (ablation) | UNIReID · Tri-CUHK-PEDES, Text+Sketch-to-RGB | Rank-1 accuracy: 85.41 -> 86.14 | Helped |
| Add task-aware dynamic training to task-specific modality learning (ablation) | UNIReID · Tri-ICFG-PEDES, Text+Sketch-to-RGB | Rank-1 accuracy: 78.41 -> 81.96 | Helped |
| Add task-aware dynamic training to task-specific modality learning (ablation) | UNIReID · Tri-RSTPReid, Text+Sketch-to-RGB | Rank-1 accuracy: 69.80 -> 73.05 | Helped |
| Add cross-modality interaction after dynamic training (ablation) | UNIReID · Tri-CUHK-PEDES, Text-to-RGB | Rank-1 accuracy: 53.48 -> 53.82 | Helped |
| Add cross-modality interaction after dynamic training (ablation) | UNIReID · Tri-ICFG-PEDES, Text-to-RGB | Rank-1 accuracy: 55.04 -> 55.39 | Helped |
| Add cross-modality interaction after dynamic training (ablation) | UNIReID · Tri-RSTPReid, Text-to-RGB | Rank-1 accuracy: 49.15 -> 49.30 | Helped |
Closest papers by meaning
- ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model (NeurIPS 2025 · similarity 0.91)
- MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification (NeurIPS 2025 · similarity 0.90)
- Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification (AAAI 2024 · similarity 0.90)
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.89)
- FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification (ICML 2025 · similarity 0.89)
- Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification (CVPR 2025 · 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.