mlsanityData to 7 Oct 2026

Learning a Neural Solver for Multiple Object Tracking

arXiv 1912.07515 ↗First posted 16 Dec 2019cs.CVcited by 198

Not on the map. Why?

Abstract (arXiv)

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as defining a model that can operate on such textitstructured domain is not trivial. As a consequence, most learning-based work has been devoted to learning better features for MOT, and then using these with well-established optimization frameworks. In this work, we exploit the classical network flow formulation of MOT to define a fully differentiable framework based on Message Passing Networks (MPNs). By operating directly on the graph domain, our method can reason globally over an entire set of detections and predict final solutions. Hence, we show that learning in MOT does not need to be restricted to feature extraction, but it can also be applied to the data association step. We show a significant improvement in both MOTA and IDF1 on three publicly available benchmarks. Our code is available at https://bit.ly/motsolv .

Key facts. Cited by 198 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 48; 2022: 57; 2023: 31; 2024: 42; 2025: 14; 2026: 6.

198 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. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  4. 2022Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detectioncited by 313
  5. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  6. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  7. 2021Learning Target Candidate Association to Keep Track of What Not to Trackcited by 131
  8. 2021Learning to Track with Object Permanencecited by 117
  9. 2022MeMOT: Multi-Object Tracking with Memorycited by 113
  10. 2022Global Tracking Transformerscited by 110
  11. 2021SimpleTrack: Understanding and Rethinking 3D Multi-object Trackingcited by 102
  12. 2022VITA: Video Instance Segmentation via Object Token Associationcited by 94
38 more
  1. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
  2. 2022Towards Grand Unification of Object Trackingcited by 93
  3. 2022MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queriescited by 90
  4. 2021EagerMOT: 3D Multi-Object Tracking via Sensor Fusioncited by 83
  5. 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 68
  6. 2021Multiple Object Tracking with Correlation Learningcited by 67
  7. 2023Hybrid-SORT: Weak Cues Matter for Online Multi-Object Trackingcited by 66
  8. 20214D Panoptic LiDAR Segmentationcited by 64
  9. 2023MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Trackingcited by 64
  10. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  11. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  12. 2021The Dawn of Quantum Natural Language Processingcited by 60
  13. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  14. 2023OVTrack: Open-Vocabulary Multiple Object Trackingcited by 53
  15. 2021Opening up Open-World Trackingcited by 50
  16. 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
  17. 2021Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Trackingcited by 47
  18. 2022GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021cited by 46
  19. 2023Towards Open-Vocabulary Video Instance Segmentationcited by 45
  20. 2022Simple Cues Lead to a Strong Multi-Object Trackercited by 44
  21. 2022Tracking Every Thing in the Wildcited by 44
  22. 2021Learning a Proposal Classifier for Multiple Object Trackingcited by 42
  23. 2021TransCenter: Transformers with Dense Representations for Multiple-Object Trackingcited by 42
  24. 2023DiffusionTrack: Diffusion Model For Multi-Object Trackingcited by 40
  25. 2021Learnable Online Graph Representations for 3D Multi-Object Trackingcited by 38
  26. 2024Neural Markov Random Field for Stereo Matchingcited by 38
  27. 2022AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wildcited by 37
  28. 20224D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregationcited by 35
  29. 2021Learning Intra-Batch Connections for Deep Metric Learningcited by 34
  30. 2021LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Trackingcited by 34
  31. 2024ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Associationcited by 33
  32. 2022Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Drivingcited by 30
  33. 2022PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?cited by 29
  34. 2022Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?cited by 28
  35. 20223D Multi-Object Tracking Using Graph Neural Networks with Cross-Edge Modality Attentioncited by 27
  36. 2022Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Modelscited by 27
  37. 2021Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Trackingcited by 26
  38. 2021One More Check: Making "Fake Background" Be Tracked Againcited by 25

50 most cited of 198 All 198 (JSON)