mlsanityData to 14 Oct 2026

MOT20: A benchmark for multi object tracking in crowded scenes

arXiv 2003.09003 ↗First posted 19 Mar 2020cs.CVcited by 357

Not on the map. Why?

Abstract (arXiv)

Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore important guides for research. The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods. The challenge focuses on multiple people tracking, since pedestrians are well studied in the tracking community, and precise tracking and detection has high practical relevance. Since the first release, MOT15, MOT16, and MOT17 have tremendously contributed to the community by introducing a clean dataset and precise framework to benchmark multi-object trackers. In this paper, we present our MOT20benchmark, consisting of 8 new sequences depicting very crowded challenging scenes. The benchmark was presented first at the 4thBMTT MOT Challenge Workshop at the Computer Vision and Pattern Recognition Conference (CVPR) 2019, and gives to chance to evaluate state-of-the-art methods for multiple object tracking when handling extremely crowded scenarios.

Key facts. Cited by 357 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 38; 2022: 67; 2023: 75; 2024: 87; 2025: 55; 2026: 35.

357 papers.

Sort:

By area:

  1. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
  2. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 518
  3. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 346
  4. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 320
  5. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 217
  6. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  7. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  8. 2026Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Groundingcited by 139
  9. 2023Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identificationcited by 132
  10. 2023SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenescited by 131
  11. 2022MeMOT: Multi-Object Tracking with Memorycited by 114
  12. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
38 more
  1. 2023TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environmentscited by 91
  2. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 88
  3. 2022SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videoscited by 80
  4. 2021STEP: Segmenting and Tracking Every Pixelcited by 73
  5. 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 69
  6. 2021Multiple Object Tracking with Correlation Learningcited by 67
  7. 2023Hybrid-SORT: Weak Cues Matter for Online Multi-Object Trackingcited by 67
  8. 2023MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Trackingcited by 64
  9. 2021The Multi-Temporal Urban Development SpaceNet Datasetcited by 62
  10. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  11. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  12. 2021SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Watercited by 61
  13. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  14. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 60
  15. 2024Multiple Object Tracking as ID Predictioncited by 60
  16. 2024DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Predictioncited by 59
  17. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  18. 2021RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representationcited by 52
  19. 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
  20. 2022Simple Cues Lead to a Strong Multi-Object Trackercited by 44
  21. 2022Tracking Every Thing in the Wildcited by 44
  22. 2023UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensationcited by 44
  23. 2021Learning a Proposal Classifier for Multiple Object Trackingcited by 42
  24. 2021TransCenter: Transformers with Dense Representations for Multiple-Object Trackingcited by 42
  25. 2023DiffusionTrack: Diffusion Model For Multi-Object Trackingcited by 40
  26. 2021Learnable Online Graph Representations for 3D Multi-Object Trackingcited by 38
  27. 2022AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wildcited by 37
  28. 2022Tracking Objects as Pixel-wise Distributionscited by 37
  29. 2022How many Observations are Enough? Knowledge Distillation for Trajectory Forecastingcited by 35
  30. 2022Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Trackingcited by 33
  31. 2024ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Associationcited by 33
  32. 2022Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?cited by 29
  33. 2022SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Trackingcited by 29
  34. 2023Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sportscited by 29
  35. 2021MODS -- A USV-oriented object detection and obstacle segmentation benchmarkcited by 27
  36. 20223D Multi-Object Tracking Using Graph Neural Networks with Cross-Edge Modality Attentioncited by 27
  37. 2021One More Check: Making "Fake Background" Be Tracked Againcited by 25
  38. 2022JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Trackingcited by 25

50 most cited of 357 All 357 (JSON)