AI Paper Atlas

Research map / Benchmarks / CUHK-PEDES

CUHK-PEDES leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CUHK-PEDES. Best Rank-1: 79.31 (CADA + QC-Align, CVPR 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CUHK-PEDES · Rank-1

15 papers, each with its best reported number for its own method; higher is better.

#Rank-1 ↑MethodPaperTopic
179.31CADA + QC-Align
CADA
Quota-Calibrated Fine-Grained Alignment with Context-Aware Marginals for Text-based Person Retrieval
CVPR 2026 · Table 1
Human and embodied modeling
279.06ICL⋆
CLIP-ViT
Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification
CVPR 2025 · Table 1
Human and embodied modeling
378.36AGA (Ours)
ALBEF/RaSa (ViT-B/16)
Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search
IJCV 2026 · Table 2
Cross-modal learning
478.13Ours (1.0 M) + APTM
Swin-B
Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID
CVPR 2024 · Table 5
Text-to-image diffusion
578.02KPDM
CLIP ViT-L/14
KPDM: Key Phrase Dynamic Masking for Robust Text-to-Image Person Retrieval
AAAI 2026 · Table 2
Human and embodied modeling
677.99HAM-PEDES + RDE
CLIP-ViT
Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification
CVPR 2025 · Table 4
Human and embodied modeling
775.66IRRA+DP
IRRA (CLIP-ViT, CLIP-Xformer)
Diverse Person: Customize Your Own Dataset for Text-Based Person Search
AAAI 2024 · Table 2
Text-to-image diffusion
874.56MDRLMulti-Modal Disordered Representation Learning Network for Description-Based Person Search
AAAI 2024 · Table 1
Cross-modal learning
974.46IRRA+IRLT
CLIP
Causality-Inspired Invariant Representation Learning for Text-Based Person Retrieval
AAAI 2024 · Table 1
Cross-modal learning
1074.25Ours
CLIP-ViT-B/16
Unifying Multi-Modal Uncertainty Modeling and Semantic Alignment for Text-to-Image Person Re-identification
AAAI 2024 · Table 1
Cross-modal learning
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.