mlsanityData to 14 Oct 2026

MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

arXiv 2211.09791 ↗First posted 17 Nov 2022cs.CVcited by 148

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose MOTRv2, a simple yet effective pipeline to bootstrap end-to-end multi-object tracking with a pretrained object detector. Existing end-to-end methods, MOTR and TrackFormer are inferior to their tracking-by-detection counterparts mainly due to their poor detection performance. We aim to improve MOTR by elegantly incorporating an extra object detector. We first adopt the anchor formulation of queries and then use an extra object detector to generate proposals as anchors, providing detection prior to MOTR. The simple modification greatly eases the conflict between joint learning detection and association tasks in MOTR. MOTRv2 keeps the query propogation feature and scales well on large-scale benchmarks. MOTRv2 ranks the 1st place (73.4% HOTA on DanceTrack) in the 1st Multiple People Tracking in Group Dance Challenge. Moreover, MOTRv2 reaches state-of-the-art performance on the BDD100K dataset. We hope this simple and effective pipeline can provide some new insights to the end-to-end MOT community. Code is available at urlhttps://github.com/megvii-research/MOTRv2.

Key facts. Cited by 148 papers in the map (data through 14 Oct 2026). Builds on 42 of its 51 references that are in the map. First posted on arXiv 17 Nov 2022.

Builds on

42 of 51 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  5. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  6. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  7. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  8. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  9. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 910
  10. 2016Simple Online and Realtime Trackingcited by 868
  11. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
  12. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 692
30 more
  1. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 573
  2. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 552
  3. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 532
  4. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 518
  5. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 495
  6. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 490
  7. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
  8. 2020Tracking Objects as Pointscited by 483
  9. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  10. 2019Tracking without bells and whistlescited by 382
  11. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 381
  12. 2020TransTrack: Multiple Object Tracking with Transformercited by 371
  13. 2020MOT20: A benchmark for multi object tracking in crowded scenescited by 357
  14. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 346
  15. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 320
  16. 2019Towards Real-Time Multi-Object Trackingcited by 311
  17. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 284
  18. 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
  19. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 217
  20. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  21. 2015MOTChallenge 2015: Towards a Benchmark for Multi-Target Trackingcited by 133
  22. 2022MeMOT: Multi-Object Tracking with Memorycited by 114
  23. 2022Global Tracking Transformerscited by 110
  24. 2018Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identificationcited by 96
  25. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
  26. 2022Towards Grand Unification of Object Trackingcited by 93
  27. 2021Multiple Object Tracking with Correlation Learningcited by 67
  28. 2022Tracking Every Thing in the Wildcited by 44
  29. 2022Tracking Objects as Pixel-wise Distributionscited by 37
  30. 2020Multi-Object Tracking with Siamese Track-RCNNcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 25; 2024: 55; 2025: 37; 2026: 31.

148 papers.

Sort:

By area:

  1. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  2. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 241
  3. 2023Referring Multi-Object Trackingcited by 93
  4. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 88
  5. 2024MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mappingcited by 68
  6. 2023Hybrid-SORT: Weak Cues Matter for Online Multi-Object Trackingcited by 67
  7. 2024Multiple Object Tracking as ID Predictioncited by 60
  8. 2024Matching Anything by Segmenting Anythingcited by 50
  9. 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
  10. 2024SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Drivingcited by 47
  11. 2023A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineeringcited by 45
  12. 2023UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensationcited by 44
38 more
  1. 2023MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Trackingcited by 42
  2. 2023TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoningcited by 41
  3. 2023iKUN: Speak to Trackers without Retrainingcited by 32
  4. 2024Towards Generalizable Multi-Object Trackingcited by 23
  5. 2024Bootstrapping Referring Multi-Object Trackingcited by 22
  6. 2024Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Trackingcited by 21
  7. 2023Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Trackingcited by 20
  8. 2023SoccerNet 2023 Challenges Resultscited by 20
  9. 2023OmniTracker: Unifying Object Tracking by Tracking-with-Detectioncited by 19
  10. 2024EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Drivingcited by 19
  11. 2024Delving into the Trajectory Long-tail Distribution for Muti-object Trackingcited by 18
  12. 2025SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentationcited by 17
  13. 2024AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movementscited by 15
  14. 2024Multi-Object Tracking in the Darkcited by 14
  15. 2024CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentationcited by 13
  16. 2024Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approachcited by 13
  17. 2025Omnidirectional Multi-Object Trackingcited by 13
  18. 2023DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusionscited by 12
  19. 2024GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matchingcited by 12
  20. 2024Beyond MOT: Semantic Multi-Object Trackingcited by 12
  21. 2023A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decisioncited by 11
  22. 2024TeamTrack: A Dataset for Multi-Sport Multi-Object Tracking in Full-pitch Videoscited by 11
  23. 2025OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformercited by 11
  24. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  25. 2024DeconfuseTrack:Dealing with Confusion for Multi-Object Trackingcited by 9
  26. 2024RobMOT: Robust 3D Multi-Object Tracking by Observational Noise and State Estimation Drift Mitigation on LiDAR PointCloudcited by 9
  27. 2024ETTrack: Enhanced Temporal Motion Predictor for Multi-Object Trackingcited by 9
  28. 2024LaMOT: Language-Guided Multi-Object Trackingcited by 9
  29. 2024Multiview Scene Graphcited by 9
  30. 2024MCTR: Multi Camera Tracking Transformercited by 8
  31. 2023Z-GMOT: Zero-shot Generic Multiple Object Trackingcited by 7
  32. 2023AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributescited by 6
  33. 2023Contrastive Learning for Multi-Object Tracking with Transformerscited by 6
  34. 2024TrackSSM: A General Motion Predictor by State-Space Modelcited by 6
  35. 2024Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentationcited by 6
  36. 2025PD-SORT: Occlusion-Robust Multi-Object Tracking Using Pseudo-Depth Cuescited by 6
  37. 2025Cognitive Disentanglement for Referring Multi-Object Trackingcited by 6
  38. 2025No Train Yet Gain: Towards Generic Multi-Object Tracking in Sports and Beyondcited by 6

50 most cited of 148 All 148 (JSON)