AI Paper Atlas

Research map / Benchmarks / MARS

MARS leaderboard

61 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MARS. Best mAP: 96.6 (SEAS, CVPR 2024).

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.

MARS · mAP

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

#mAP ↑MethodPaperTopic
196.6SEAS
PSTA
SEAS: ShapE-Aligned Supervision for Person Re-Identification
CVPR 2024 · Table 2
Video segmentation and tracking
291.5AG-VPReID-NetAG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification
CVPR 2025 · Table 4
Video segmentation and tracking
391.1HAMoBE
CLIP ViT-L/14
HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID
ICCV 2025 · Table 1
Video segmentation and tracking
490.4CSIP-ReID (Ours)Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-Identification
AAAI 2026 · Table 1
Video segmentation and tracking
589.7CLIMB-ReID
CLIP ViT-B/16
CLIMB-ReID: A Hybrid CLIP-Mamba Framework for Person Re-Identification
AAAI 2025 · Table 1
Video segmentation and tracking
689.4TF-CLIP
ViT-B/16 (CLIP)
TF-CLIP: Learning Text-Free CLIP for Video-Based Person Re-identification
AAAI 2024 · Table 1
Video segmentation and tracking
788.6VSLA-CLIP (ViFi-CLIP init)
CLIP ViT-B/16
Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach
ECCV 2024 · Table 2
Video segmentation and tracking
887.72QI-IRA(2,1)QI-IRA: Quantum-Inspired Interactive Ranking Aggregation for Person Re-identification
AAAI 2024 · Table 1
Recognition and long-tail
987.6TCViT
ViT-base
Temporal Correlation Vision Transformer for Video Person Re-Identification
AAAI 2024 · Table 3
Video segmentation and tracking
1087.4SE-ResNet50 + COSAM4,5 + TPavg + re-ranking
SE-ResNet50
Co-Segmentation Inspired Attention Networks for Video-Based Person Re-Identification
ICCV 2019 · Table 5
Video segmentation and tracking
46 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

MARS · Rank-1

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

#Rank-1 ↑MethodPaperTopic
195.1SEAS
PSTA
SEAS: ShapE-Aligned Supervision for Person Re-Identification
CVPR 2024 · Table 2
Video segmentation and tracking
294.2CSIP-ReID (Ours)Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-Identification
AAAI 2026 · Table 1
Video segmentation and tracking
393.37QI-IRA(2,1)QI-IRA: Quantum-Inspired Interactive Ranking Aggregation for Person Re-identification
AAAI 2024 · Table 1
Recognition and long-tail
493.3CLIMB-ReID
CLIP ViT-B/16
CLIMB-ReID: A Hybrid CLIP-Mamba Framework for Person Re-Identification
AAAI 2025 · Table 1
Video segmentation and tracking
593.2AG-VPReID-NetAG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification
CVPR 2025 · Table 4
Video segmentation and tracking
693TF-CLIP
ViT-B/16 (CLIP)
TF-CLIP: Learning Text-Free CLIP for Video-Based Person Re-identification
AAAI 2024 · Table 1
Video segmentation and tracking
791.82VSLA-CLIP (ViFi-CLIP init)
CLIP ViT-B/16
Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach
ECCV 2024 · Table 2
Video segmentation and tracking
891.7TCViT
ViT-base
Temporal Correlation Vision Transformer for Video Person Re-Identification
AAAI 2024 · Table 3
Video segmentation and tracking
991.5PSTA
ResNet-50
Pyramid Spatial-Temporal Aggregation for Video-Based Person Re-Identification
ICCV 2021 · Table 3
Video segmentation and tracking
1091.4CTL
ResNet-50
Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
CVPR 2021 · Table: Performance comparison
Video segmentation and tracking
27 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.