mlsanityData to 7 Oct 2026

FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking

arXiv 2004.01888 ↗First posted 4 Apr 2020cs.CVcited by 489

Not on the map. Why?

Abstract (arXiv)

Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency. However, we find that the two tasks tend to compete with each other which need to be carefully addressed. In particular, previous works usually treat re-ID as a secondary task whose accuracy is heavily affected by the primary detection task. As a result, the network is biased to the primary detection task which is not fair to the re-ID task. To solve the problem, we present a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet. Note that it is not a naive combination of CenterNet and re-ID. Instead, we present a bunch of detailed designs which are critical to achieve good tracking results by thorough empirical studies. The resulting approach achieves high accuracy for both detection and tracking. The approach outperforms the state-of-the-art methods by a large margin on several public datasets. The source code and pre-trained models are released at https://github.com/ifzhang/FairMOT.

Key facts. Cited by 489 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 47; 2022: 102; 2023: 98; 2024: 110; 2025: 90; 2026: 42.

489 papers.

Sort:

By area:

  1. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  2. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  3. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  4. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  5. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  6. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Drivingcited by 324
  7. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
  8. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 213
  9. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  10. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  11. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  12. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
38 more
  1. 2023Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identificationcited by 130
  2. 2023SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenescited by 130
  3. 2022MeMOT: Multi-Object Tracking with Memorycited by 113
  4. 2022Global Tracking Transformerscited by 110
  5. 2021SimpleTrack: Understanding and Rethinking 3D Multi-object Trackingcited by 102
  6. 2022In Defense of Online Models for Video Instance Segmentationcited by 97
  7. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
  8. 2022Towards Grand Unification of Object Trackingcited by 93
  9. 2023Referring Multi-Object Trackingcited by 91
  10. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 86
  11. 2022SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videoscited by 80
  12. 2022Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identificationcited by 78
  13. 2022Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Spacecited by 66
  14. 2023Hybrid-SORT: Weak Cues Matter for Online Multi-Object Trackingcited by 66
  15. 2023MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Trackingcited by 64
  16. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  17. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  18. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  19. 2021SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Watercited by 59
  20. 2024DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Predictioncited by 59
  21. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 58
  22. 2024Multiple Object Tracking as ID Predictioncited by 58
  23. 2021DEFT: Detection Embeddings for Trackingcited by 56
  24. 2021Exploring Simple 3D Multi-Object Tracking for Autonomous Drivingcited by 56
  25. 2023Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Trackingcited by 54
  26. 2023OVTrack: Open-Vocabulary Multiple Object Trackingcited by 53
  27. 2021RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representationcited by 52
  28. 2025DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Drivingcited by 52
  29. 2022CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusioncited by 50
  30. 2023PLIP: Language-Image Pre-training for Person Representation Learningcited by 49
  31. 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
  32. 2021Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Trackingcited by 47
  33. 2022GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021cited by 46
  34. 2022Simple Cues Lead to a Strong Multi-Object Trackercited by 44
  35. 2021Anchor-Free Person Searchcited by 42
  36. 2021TransCenter: Transformers with Dense Representations for Multiple-Object Trackingcited by 42
  37. 2023MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Trackingcited by 42
  38. 2022Large-Scale Pre-training for Person Re-identification with Noisy Labelscited by 41

50 most cited of 489 All 489 (JSON)