mlsanityData to 7 Oct 2026

Tracking Objects as Points

arXiv 2004.01177 ↗First posted 2 Apr 2020cs.CVcited by 483

Not on the map. Why?

Abstract (arXiv)

Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by temporal association, also known as tracking-by-detection. In this paper, we present a simultaneous detection and tracking algorithm that is simpler, faster, and more accurate than the state of the art. Our tracker, CenterTrack, applies a detection model to a pair of images and detections from the prior frame. Given this minimal input, CenterTrack localizes objects and predicts their associations with the previous frame. That's it. CenterTrack is simple, online (no peeking into the future), and real-time. It achieves 67.3% MOTA on the MOT17 challenge at 22 FPS and 89.4% MOTA on the KITTI tracking benchmark at 15 FPS, setting a new state of the art on both datasets. CenterTrack is easily extended to monocular 3D tracking by regressing additional 3D attributes. Using monocular video input, it achieves 28.3% [email protected] on the newly released nuScenes 3D tracking benchmark, substantially outperforming the monocular baseline on this benchmark while running at 28 FPS.

Key facts. Cited by 483 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 79; 2022: 129; 2023: 94; 2024: 101; 2025: 50; 2026: 30.

483 papers.

Sort:

By area:

  1. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  2. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  3. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  4. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  5. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
  6. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  7. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 213
  8. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  9. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  10. 2024Enhancing End-to-End Autonomous Driving with Latent World Modelcited by 161
  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. 2022Learning from All Vehiclescited by 135
  2. 2023Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identificationcited by 130
  3. 2023SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenescited by 130
  4. 2021Learning to Track with Object Permanencecited by 117
  5. 2022ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queriescited by 116
  6. 2022MeMOT: Multi-Object Tracking with Memorycited by 113
  7. 2022Global Tracking Transformerscited by 110
  8. 2022In Defense of Online Models for Video Instance Segmentationcited by 97
  9. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
  10. 2022Towards Grand Unification of Object Trackingcited by 93
  11. 2022MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queriescited by 90
  12. 2021SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentationcited by 87
  13. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 86
  14. 2021EagerMOT: 3D Multi-Object Tracking via Sensor Fusioncited by 83
  15. 2021Monocular Quasi-Dense 3D Object Trackingcited by 80
  16. 2022Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentationcited by 79
  17. 2021STEP: Segmenting and Tracking Every Pixelcited by 72
  18. 2023General Object Foundation Model for Images and Videos at Scalecited by 71
  19. 2022CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimationcited by 69
  20. 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 68
  21. 2021Multiple Object Tracking with Correlation Learningcited by 67
  22. 2023Hybrid-SORT: Weak Cues Matter for Online Multi-Object Trackingcited by 66
  23. 2023Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perceptioncited by 65
  24. 2021Generic Event Boundary Detection: A Benchmark for Event Segmentationcited by 64
  25. 20214D Panoptic LiDAR Segmentationcited by 64
  26. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  27. 2023MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Trackingcited by 64
  28. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  29. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  30. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  31. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  32. 2024DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Predictioncited by 59
  33. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 58
  34. 2024Multiple Object Tracking as ID Predictioncited by 58
  35. 2021DEFT: Detection Embeddings for Trackingcited by 56
  36. 2021Exploring Simple 3D Multi-Object Tracking for Autonomous Drivingcited by 56
  37. 2023Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Trackingcited by 54
  38. 2023OVTrack: Open-Vocabulary Multiple Object Trackingcited by 53

50 most cited of 483 All 483 (JSON)