mlsanityData to 14 Oct 2026

MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking

arXiv 2305.14298 ↗First posted 23 May 2023cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

Although end-to-end multi-object trackers like MOTR enjoy the merits of simplicity, they suffer from the conflict between detection and association seriously, resulting in unsatisfactory convergence dynamics. While MOTRv2 partly addresses this problem, it demands an additional detection network for assistance. In this work, we serve as the first to reveal that this conflict arises from the unfair label assignment between detect queries and track queries during training, where these detect queries recognize targets and track queries associate them. Based on this observation, we propose MOTRv3, which balances the label assignment process using the developed release-fetch supervision strategy. In this strategy, labels are first released for detection and gradually fetched back for association. Besides, another two strategies named pseudo label distillation and track group denoising are designed to further improve the supervision for detection and association. Without the assistance of an extra detection network during inference, MOTRv3 achieves impressive performance across diverse benchmarks, e.g., MOT17, DanceTrack.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 40 of its 46 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

40 of 46 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  7. 2020End-to-End Object Detection with Transformerscited by 7,414
  8. 2022A ConvNet for the 2020scited by 3,579
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  10. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  11. 2019Objects as Pointscited by 1,175
  12. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
28 more
  1. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 910
  2. 2016Simple Online and Realtime Trackingcited by 868
  3. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
  4. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 552
  5. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 532
  6. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 518
  7. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 495
  8. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 490
  9. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
  10. 2020Tracking Objects as Pointscited by 483
  11. 2019Tracking without bells and whistlescited by 382
  12. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 381
  13. 2020TransTrack: Multiple Object Tracking with Transformercited by 371
  14. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 346
  15. 2019Towards Real-Time Multi-Object Trackingcited by 311
  16. 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
  17. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 217
  18. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  19. 2017Detect to Track and Track to Detectcited by 131
  20. 2020Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Trackingcited by 115
  21. 2022MeMOT: Multi-Object Tracking with Memorycited by 114
  22. 2020TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Modelcited by 70
  23. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  24. 2021RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representationcited by 52
  25. 2020MAT: Motion-Aware Multi-Object Trackingcited by 40
  26. 2022Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Trackingcited by 33
  27. 2022Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representationcited by 17
  28. 2020Joint Object Detection and Multi-Object Tracking with Graph Neural Networkscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 19; 2025: 14; 2026: 7.

42 papers.

Sort:

By area:

  1. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 241
  2. 2025Perception-R1: Pioneering Perception Policy with Reinforcement Learningcited by 120
  3. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 70
  4. 2024Multiple Object Tracking as ID Predictioncited by 60
  5. 2024SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Drivingcited by 47
  6. 2024Delving into the Trajectory Long-tail Distribution for Muti-object Trackingcited by 18
  7. 2025SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentationcited by 17
  8. 2024GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matchingcited by 12
  9. 2025OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformercited by 11
  10. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  11. 2025Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Trackingcited by 9
  12. 2024MCTR: Multi Camera Tracking Transformercited by 8
30 more
  1. 2024MLS-Track: Multilevel Semantic Interaction in RMOTcited by 7
  2. 2025Disentangling Instance and Scene Contexts for 3D Semantic Scene Completioncited by 7
  3. 2024Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentationcited by 6
  4. 2024Is Multiple Object Tracking a Matter of Specialization?cited by 5
  5. 2025GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarkingcited by 5
  6. 2024LiDAR-based End-to-end Temporal Perception for Vehicle-Infrastructure Cooperationcited by 4
  7. 2025Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Artcited by 4
  8. 2025USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterwayscited by 4
  9. 2025ReaMOT: A Benchmark and Framework for Reasoning-based Multi-Object Trackingcited by 3
  10. 2023DecoderTracker: Decoder-Only Method for Multiple-Object Trackingcited by 2
  11. 2024Is a Pure Transformer Effective for Separated and Online Multi-Object Tracking?cited by 2
  12. 2024Multi-Granularity Language-Guided Training for Multi-Object Trackingcited by 2
  13. 2024SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Trackingcited by 2
  14. 2024Tell Me What to Track: Infusing Robust Language Guidance for Enhanced Referring Multi-Object Trackingcited by 2
  15. 2026SCATR: Mitigating New Instance Suppression in LiDAR-based Tracking-by-Attention via Second Chance Assignment and Track Query Dropoutcited by 2
  16. 2026Hypergraph-State Collaborative Reasoning for Multi-Object Trackingcited by 2
  17. 2024Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Trackingcited by 1
  18. 2024FastTrackTr:Towards Fast Multi-Object Tracking with Transformerscited by 1
  19. 2025To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Softwarecited by 1
  20. 2025Motion-Aware Transformer for Multi-Object Trackingcited by 1
  21. 2025From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Trackingcited by 1
  22. 2026SCT-MOT: Enhancing Air-to-Air Multiple UAVs Tracking with Swarm-Coupled Motion and Trajectory Guidancecited by 1
  23. 2026Radar-Informed 3D Multi-Object Tracking under Adverse Conditionscited by 1
  24. 2024TF-SASM: Training-free Spatial-aware Sparse Memory for Multi-object Trackingcited by 0
  25. 2024Tracking by Detection and Query: An Efficient End-to-End Framework for Multi-Object Trackingcited by 0
  26. 2025SOTFormer: A Minimal Transformer for Unified Object Tracking and Trajectory Predictioncited by 0
  27. 2025SelfMOTR: Revisiting MOTR with Self-Generating Detection Priorscited by 0
  28. 2026Beyond the Image Plane: World-Grounded Queries for Multi-Object Trackingcited by 0
  29. 2026EECTracker: Swarm Motion Prior-Guided Feature Compensation for Airborne Optical UAV Swarm Trackingcited by 0
  30. 2026MOTIP2: Spatial Priors for End-to-End Multi-Object Trackingcited by 0