mlsanityData to 7 Oct 2026

Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch

arXiv 1910.10093 ↗First posted 22 Oct 2019cs.CVcited by 41

Not on the map. Why?

Abstract (arXiv)

Person re-identification (re-ID), which aims to re-identify people across different camera views, has been significantly advanced by deep learning in recent years, particularly with convolutional neural networks (CNNs). In this paper, we present Torchreid, a software library built on PyTorch that allows fast development and end-to-end training and evaluation of deep re-ID models. As a general-purpose framework for person re-ID research, Torchreid provides (1) unified data loaders that support 15 commonly used re-ID benchmark datasets covering both image and video domains, (2) streamlined pipelines for quick development and benchmarking of deep re-ID models, and (3) implementations of the latest re-ID CNN architectures along with their pre-trained models to facilitate reproducibility as well as future research. With a high-level modularity in its design, Torchreid offers a great flexibility to allow easy extension to new datasets, CNN models and loss functions.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 14; 2023: 8; 2024: 3; 2025: 3; 2026: 2.

41 papers.

Sort:

By area:

  1. 2021Domain Generalization with MixStylecited by 563
  2. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  3. 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
  4. 2022Simple Cues Lead to a Strong Multi-Object Trackercited by 44
  5. 20213D Human Texture Estimation from a Single Image with Transformerscited by 35
  6. 2022DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotationscited by 35
  7. 2022Virtual Correspondence: Humans as a Cue for Extreme-View Geometrycited by 25
  8. 2022Quality-aware Part Models for Occluded Person Re-identificationcited by 17
  9. 2021CoReS: Compatible Representations via Stationaritycited by 14
  10. 2022Spatio-Temporal Action Detection Under Large Motioncited by 14
  11. 2025DanceTogether! Identity-Preserving Multi-Person Interactive Video Generationcited by 12
  12. 2022Similarity Distribution based Membership Inference Attack on Person Re-identificationcited by 8
29 more
  1. 2022The Self-Optimal-Transport Feature Transformcited by 7
  2. 2021AttributeNet: Attribute Enhanced Vehicle Re-Identificationcited by 6
  3. 2021Unsupervised and self-adaptative techniques for cross-domain person re-identificationcited by 6
  4. 2022Sports Re-ID: Improving Re-Identification Of Players In Broadcast Videos Of Team Sportscited by 6
  5. 2024TrackSSM: A General Motion Predictor by State-Space Modelcited by 6
  6. 2022SportsTrack: An Innovative Method for Tracking Athletes in Sports Scenescited by 5
  7. 2021UAV-ReID: A Benchmark on Unmanned Aerial Vehicle Re-identification in Video Imagerycited by 3
  8. 2021Improving Person Re-Identification with Temporal Constraintscited by 3
  9. 2023DoUnseen: Tuning-Free Class-Adaptive Object Detection of Unseen Objects for Robotic Graspingcited by 3
  10. 2024Context-Aware Full Body Anonymization using Text-to-Image Diffusion Modelscited by 3
  11. 2026Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worldscited by 3
  12. 2022Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attributioncited by 2
  13. 2022On the Applicability of Synthetic Data for Re-Identificationcited by 2
  14. 2023Refining 3D Human Texture Estimation from a Single Imagecited by 2
  15. 2023"Reading Between the Heat": Co-Teaching Body Thermal Signatures for Non-intrusive Stress Detectioncited by 2
  16. 2021Going Deeper into Semi-supervised Person Re-identificationcited by 1
  17. 2022TDT: Teaching Detectors to Track without Fully Annotated Videoscited by 1
  18. 2023A Review on Generative Adversarial Networks for Data Augmentation in Person Re-Identification Systemscited by 1
  19. 2023Person Re-ID through Unsupervised Hypergraph Rank Selection and Fusioncited by 1
  20. 2023Large-scale Fully-Unsupervised Re-Identificationcited by 1
  21. 2021Heuristics2Annotate: Efficient Annotation of Large-Scale Marathon Dataset For Bounding Box Regressioncited by 0
  22. 2021Multi-granularity for knowledge distillationcited by 0
  23. 2022People Tracking and Re-Identifying in Distributed Contexts: Extension Study of PoseTReIDcited by 0
  24. 2022Is Synthetic Dataset Reliable for Benchmarking Generalizable Person Re-Identification?cited by 0
  25. 2023Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)cited by 0
  26. 2024DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identificationcited by 0
  27. 2025TRAX: TRacking Axles for Accurate Axle Count Estimationcited by 0
  28. 2025GRAP-MOT: Unsupervised Graph-based Position Weighted Person Multi-camera Multi-object Tracking in a Highly Congested Spacecited by 0
  29. 2026ModTrack: Sensor-Agnostic Multi-View Tracking via Identity-Informed PHD Filtering with Covariance Propagationcited by 0