AI Paper Atlas

Research map / Benchmarks / RegDB

RegDB leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on RegDB. Best mAP: 95.8 (ChatReID, ICCV 2025).

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.

RegDB · mAP

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

#mAP ↑MethodPaperTopic
195.8ChatReID
Qwen2-VL 2B
ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models
ICCV 2025 · Table 3
Multimodal LLMs
294.4ANFIANFI: Rethinking Neighbor Feature Interaction in Person Re-ID
ECCV 2026 · Table 1
Recognition and long-tail
385FSAM
AGW
Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification
NeurIPS 2024 · Table 5
Attacks on text and graphs
478.57SMCL (B + CEHL + ADSL + IT)
ResNet-50
Syncretic Modality Collaborative Learning for Visible Infrared Person Re-Identification
ICCV 2021 · Table 1
Recognition and long-tail
569.4Baseline + CICL + IAMA
ResNet50
Joint Color-irrelevant Consistency Learning and Identity-aware Modality Adaptation for Visible-infrared Cross Modality Person Re-identification
AAAI 2021 · Table 3
Recognition and long-tail
666.04Hi-CMD
ResNet-50
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
CVPR 2020 · Table 1
Recognition and long-tail
760.18XIV (Our method)
ResNet-50
Infrared-Visible Cross-Modal Person Re-Identification with an X Modality
AAAI 2020 · Table 1
Recognition and long-tail
847D-HSMEHSME: Hypersphere Manifold Embedding for Visible Thermal Person Re-Identification
AAAI 2019 · Table 1
Recognition and long-tail
944.1D2RL
ResNet-50
Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification
CVPR 2019 · Table 1
Recognition and long-tail
1032.1Proposed (heterogeneous)
ResNet50
Mining on Heterogeneous Manifolds for Zero-Shot Cross-Modal Image Retrieval
AAAI 2020 · Table 3
CLIP and zero-shot

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