mlsanityData to 7 Oct 2026

Dissecting Person Re-identification from the Viewpoint of Viewpoint

arXiv 1812.02162 ↗First posted 5 Dec 2018cs.CVcited by 83

Not on the map. Why?

Abstract (arXiv)

Variations in visual factors such as viewpoint, pose, illumination and background, are usually viewed as important challenges in person re-identification (re-ID). In spite of acknowledging these factors to be influential, quantitative studies on how they affect a re-ID system are still lacking. To derive insights in this scientific campaign, this paper makes an early attempt in studying a particular factor, viewpoint. We narrow the viewpoint problem down to the pedestrian rotation angle to obtain focused conclusions. In this regard, this paper makes two contributions to the community. First, we introduce a large-scale synthetic data engine, PersonX. Composed of hand-crafted 3D person models, the salient characteristic of this engine is "controllable". That is, we are able to synthesize pedestrians by setting the visual variables to arbitrary values. Second, on the 3D data engine, we quantitatively analyze the influence of pedestrian rotation angle on re-ID accuracy. Comprehensively, the person rotation angles are precisely customized from 0 to 360, allowing us to investigate its effect on the training, query, and gallery sets. Extensive experiment helps us have a deeper understanding of the fundamental problems in person re-ID. Our research also provides useful insights for dataset building and future practical usage, e.g., a person of a side view makes a better query.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 20; 2023: 15; 2024: 14; 2025: 7; 2026: 6.

83 papers.

Sort:

By area:

  1. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  2. 2021Cluster Contrast for Unsupervised Person Re-Identificationcited by 89
  3. 2023Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmarkcited by 75
  4. 2021Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularizationcited by 69
  5. 2022A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localizationcited by 55
  6. 2021IDM: An Intermediate Domain Module for Domain Adaptive Person Re-IDcited by 51
  7. 2022Synthetic Data in Human Analysis: A Surveycited by 28
  8. 2024SDPL: Shifting-Dense Partition Learning for UAV-View Geo-Localizationcited by 25
  9. 2021Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Idcited by 22
  10. 2024Transformer for Object Re-Identification: A Surveycited by 21
  11. 2024View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Networkcited by 21
  12. 2021Towards Discriminative Representation Learning for Unsupervised Person Re-identificationcited by 20
38 more
  1. 2021Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identificationcited by 19
  2. 2021Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptationcited by 18
  3. 2023Semantic-aware Consistency Network for Cloth-changing Person Re-Identificationcited by 18
  4. 2022Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identificationcited by 17
  5. 2023Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identificationcited by 16
  6. 2021Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identificationcited by 15
  7. 2022Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trendscited by 15
  8. 2023Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identificationcited by 13
  9. 2023Occluded Person Re-Identification with Deep Learning: A Survey and Perspectivescited by 13
  10. 2021Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identificationcited by 12
  11. 2022Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edgescited by 12
  12. 2022Deep Learning-based Occluded Person Re-identification: A Surveycited by 12
  13. 2023Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identificationcited by 12
  14. 2021Bringing Generalization to Deep Multi-View Pedestrian Detectioncited by 11
  15. 2022Human Image Generation: A Comprehensive Surveycited by 11
  16. 2024Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Trainingcited by 10
  17. 2021UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Modelcited by 9
  18. 2022Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyondcited by 9
  19. 2023Ground-to-Aerial Person Search: Benchmark Dataset and Approachcited by 9
  20. 2021Semi-Supervised Domain Generalizable Person Re-Identificationcited by 8
  21. 2021Ranking Models in Unlabeled New Environmentscited by 8
  22. 2021Unsupervised Person Re-identification with Stochastic Training Strategycited by 7
  23. 2023Whole-body Detection, Recognition and Identification at Altitude and Rangecited by 7
  24. 2021Meta Clustering Learning for Large-scale Unsupervised Person Re-identificationcited by 6
  25. 2024CCUP: A Controllable Synthetic Data Generation Pipeline for Pretraining Cloth-Changing Person Re-Identification Modelscited by 6
  26. 20223D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspectivecited by 5
  27. 2022Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attentioncited by 5
  28. 2022From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibrationcited by 5
  29. 2023Meta Generative Attack on Person Reidentificationcited by 5
  30. 2024Anti-Forgetting Adaptation for Unsupervised Person Re-identificationcited by 5
  31. 2024Dynamic Token Selection for Aerial-Ground Person Re-Identificationcited by 5
  32. 2025A Theory-Inspired Framework for Few-Shot Cross-Modal Sketch Person Re-Identificationcited by 5
  33. 2022Dual Clustering Co-teaching with Consistent Sample Mining for Unsupervised Person Re-Identificationcited by 4
  34. 2022A Benchmark of Video-Based Clothes-Changing Person Re-Identificationcited by 4
  35. 2023Training with Product Digital Twins for AutoRetail Checkoutcited by 4
  36. 2023Alice Benchmarks: Connecting Real World Re-Identification with the Syntheticcited by 4
  37. 2024An Open-World, Diverse, Cross-Spatial-Temporal Benchmark for Dynamic Wild Person Re-Identificationcited by 4
  38. 2024Camera-aware Label Refinement for Unsupervised Person Re-identificationcited by 4

50 most cited of 83 All 83 (JSON)