AI Paper Atlas

Research map / Benchmarks / SYSU-MM01 all-search multi-shot

SYSU-MM01 all-search multi-shot leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SYSU-MM01 all-search multi-shot. Best Rank-1: 85.31 (BIT, 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.

SYSU-MM01 all-search multi-shot · Rank-1

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

#Rank-1 ↑MethodPaperTopic
185.31BIT
ViT-B/16 (PMT backbone)
BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification
CVPR 2026 · Table 1
Recognition and long-tail
283.2WRIM-Net
ResNet50
WRIM-Net: Wide-Ranging Information Mining Network for Visible-Infrared Person Re-Identification
ECCV 2024 · Table 1
Recognition and long-tail
380.54PartMix
MPANet
PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification
CVPR 2023 · Table 1
Recognition and long-tail
479.74CIFT (Ours)
ResNet-50
Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
ECCV 2022 · Table 1
Recognition and long-tail
578.35Ours
ResNet-50
Cross-Modality Person Re-identification with Memory-Based Contrastive Embedding
AAAI 2023 · Table 1
Recognition and long-tail
677.05CAL
ResNet-50
Learning Concordant Attention via Target-aware Alignment for Visible-Infrared Person Re-identification
ICCV 2023 · Table 1
Recognition and long-tail
771.35OursExploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID
IJCV 2024 · Table 3
Recognition and long-tail
868.39CMTR
ViT-B
Cross-Modality Transformer for Visible-Infrared Person Re-identification
ECCV 2022 · Table 1
Recognition and long-tail
951.5AlignGANRGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
ICCV 2019 · Table 2
Recognition and long-tail
1045.1JSIA-ReID
ResNet-50
Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification
AAAI 2020 · Table: Comparison with the sta
Recognition and long-tail
1 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

SYSU-MM01 all-search multi-shot · mAP

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

#mAP ↑MethodPaperTopic
182.39SAAI
ResNet-50
Visible-Infrared Person Re-Identification via Semantic Alignment and Affinity Inference
ICCV 2023 · Table 1
Recognition and long-tail
275.56CIFT (Ours)
ResNet-50
Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
ECCV 2022 · Table 1
Recognition and long-tail
374.6SALCR w/ CMFP(te)Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID
IJCV 2025 · Table 2
Recognition and long-tail
469.84PartMix
MPANet
PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification
CVPR 2023 · Table 1
Recognition and long-tail
565.77Ours
ResNet-50
Cross-Modality Person Re-identification with Memory-Based Contrastive Embedding
AAAI 2023 · Table 1
Recognition and long-tail
662cm-SSFT
ResNet50
Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer
CVPR 2020 · Table 1
Recognition and long-tail
755.69CMTR
ViT-B
Cross-Modality Transformer for Visible-Infrared Person Re-identification
ECCV 2022 · Table 1
Recognition and long-tail
833.9AlignGANRGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
ICCV 2019 · Table 2
Recognition and long-tail
929.5JSIA-ReID
ResNet-50
Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification
AAAI 2020 · Table: Comparison with the sta
Recognition and long-tail
1010.89Deep zero-padding (one-stream)RGB-Infrared Cross-Modality Person Re-Identification
ICCV 2017 · Table 3
Recognition and long-tail

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