mlsanityData to 14 Oct 2026

AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

arXiv 1711.08184 ↗First posted 22 Nov 2017cs.CVcited by 61

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features. Global feature learning benefits greatly from local feature learning, which performs an alignment/matching by calculating the shortest path between two sets of local features, without requiring extra supervision. After the joint learning, we only keep the global feature to compute the similarities between images. Our method achieves rank-1 accuracy of 94.4% on Market1501 and 97.8% on CUHK03, outperforming state-of-the-art methods by a large margin. We also evaluate human-level performance and demonstrate that our method is the first to surpass human-level performance on Market1501 and CUHK03, two widely used Person ReID datasets.

Key facts. Cited by 61 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 20; 2022: 14; 2023: 11; 2024: 13; 2025: 3.

61 papers.

Sort:

By area:

  1. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 96
  2. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
  3. 2021Person Re-identification Method Based on Color Attack and Joint Defencecited by 56
  4. 2021Intra-Inter Camera Similarity for Unsupervised Person Re-Identificationcited by 52
  5. 2021AAformer: Auto-Aligned Transformer for Person Re-Identificationcited by 48
  6. 2021Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identificationcited by 44
  7. 2021Feature Erasing and Diffusion Network for Occluded Person Re-Identificationcited by 42
  8. 2023DyGait: Exploiting Dynamic Representations for High-performance Gait Recognitioncited by 35
  9. 2023Region Generation and Assessment Network for Occluded Person Re-Identificationcited by 20
  10. 2021Person Re-Identification with a Locally Aware Transformercited by 19
  11. 2022Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identificationcited by 18
  12. 2021A Person Re-identification Data Augmentation Method with Adversarial Defense Effectcited by 13
38 more
  1. 2021Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistencycited by 12
  2. 2022A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identificationcited by 11
  3. 2022Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baselinecited by 11
  4. 2023Graph Convolution Based Efficient Re-Ranking for Visual Retrievalcited by 11
  5. 2021Holistic Guidance for Occluded Person Re-Identificationcited by 9
  6. 2023Feature Completion Transformer for Occluded Person Re-identificationcited by 9
  7. 2024Other Tokens Matter: Exploring Global and Local Features of Vision Transformers for Object Re-Identificationcited by 9
  8. 2021Discriminator-Free Generative Adversarial Attackcited by 8
  9. 2021MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReIDcited by 8
  10. 2023OOD Aware Supervised Contrastive Learningcited by 7
  11. 2021Graph Convolution for Re-ranking in Person Re-identificationcited by 6
  12. 2022The Group Loss++: A deeper look into group loss for deep metric learningcited by 6
  13. 2023Rethinking Person Re-identification from a Projection-on-Prototypes Perspectivecited by 6
  14. 2023Meta Generative Attack on Person Reidentificationcited by 5
  15. 2024Part-Attention Based Model Make Occluded Person Re-Identification Strongercited by 5
  16. 2024Disentangled Representations for Short-Term and Long-Term Person Re-Identificationcited by 5
  17. 2024An Open-World, Diverse, Cross-Spatial-Temporal Benchmark for Dynamic Wild Person Re-Identificationcited by 4
  18. 2025What Makes You Unique? Attribute Prompt Composition for Object Re-Identificationcited by 4
  19. 2021Homogeneous and Heterogeneous Relational Graph for Visible-infrared Person Re-identificationcited by 3
  20. 2022DiP: Learning Discriminative Implicit Parts for Person Re-Identificationcited by 3
  21. 2024DiffPhysBA: Diffusion-based Physical Backdoor Attack against Person Re-Identification in Real-Worldcited by 3
  22. 2021Pose Invariant Person Re-Identification using Robust Pose-transformation GANcited by 2
  23. 2022Motion-Aware Transformer For Occluded Person Re-identificationcited by 2
  24. 2022Feature-Distribution Perturbation and Calibration for Generalized Person ReIDcited by 2
  25. 2024Data Augmentation in Human-Centric Visioncited by 2
  26. 2024Tran-GCN: A Transformer-Enhanced Graph Convolutional Network for Person Re-Identification in Monitoring Videoscited by 2
  27. 2021Unified Batch All Triplet Loss for Visible-Infrared Person Re-identificationcited by 1
  28. 2021Bridging the Distribution Gap of Visible-Infrared Person Re-identification with Modality Batch Normalizationcited by 1
  29. 2021Vehicle Re-identification Method Based on Vehicle Attribute and Mutual Exclusion Between Camerascited by 1
  30. 2021PGGANet: Pose Guided Graph Attention Network for Person Re-identificationcited by 1
  31. 2022Cross-modal Local Shortest Path and Global Enhancement for Visible-Thermal Person Re-Identificationcited by 1
  32. 2022Generalizable Re-Identification from Videos with Cycle Associationcited by 1
  33. 2024Style Alignment based Dynamic Observation Method for UAV-View Geo-localizationcited by 1
  34. 2024Learning to Learn Transferable Generative Attack for Person Re-Identificationcited by 1
  35. 2024Prototype-Driven Multi-Feature Generation for Visible-Infrared Person Re-identificationcited by 1
  36. 2024GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolutioncited by 1
  37. 2021A Generic Object Re-identification System for Short Videoscited by 0
  38. 2022STURE: Spatial-Temporal Mutual Representation Learning for Robust Data Association in Online Multi-Object Trackingcited by 0

50 most cited of 61 All 61 (JSON)