mlsanityData to 7 Oct 2026

SiamMOT: Siamese Multi-Object Tracking

arXiv 2105.11595 ↗First posted 25 May 2021cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

In this paper, we focus on improving online multi-object tracking (MOT). In particular, we introduce a region-based Siamese Multi-Object Tracking network, which we name SiamMOT. SiamMOT includes a motion model that estimates the instance's movement between two frames such that detected instances are associated. To explore how the motion modelling affects its tracking capability, we present two variants of Siamese tracker, one that implicitly models motion and one that models it explicitly. We carry out extensive quantitative experiments on three different MOT datasets: MOT17, TAO-person and Caltech Roadside Pedestrians, showing the importance of motion modelling for MOT and the ability of SiamMOT to substantially outperform the state-of-the-art. Finally, SiamMOT also outperforms the winners of ACM MM'20 HiEve Grand Challenge on HiEve dataset. Moreover, SiamMOT is efficient, and it runs at 17 FPS for 720P videos on a single modern GPU. Codes are available in urlhttps://github.com/amazon-research/siam-mot.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Builds on 55 of its 78 references that are in the map. First posted on arXiv 25 May 2021.

Builds on

55 of 78 references.

References · 55

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017Mask R-CNNcited by 7,259
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2015Fast R-CNNcited by 2,930
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  7. 2018Group Normalizationcited by 1,514
  8. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  9. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  10. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  11. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  12. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
38 more
  1. 2016Simple Online and Realtime Trackingcited by 862
  2. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  3. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  4. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  5. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  6. 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 535
  7. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  8. 2020Tracking Objects as Pointscited by 483
  9. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  10. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
  11. 2017Deep Layer Aggregationcited by 436
  12. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  13. 2019Video Instance Segmentationcited by 391
  14. 2019Tracking without bells and whistlescited by 382
  15. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  16. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
  17. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  18. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  19. 2019Learning a Neural Solver for Multiple Object Trackingcited by 198
  20. 2018Distractor-aware Siamese Networks for Visual Object Trackingcited by 187
  21. 2019Deeper and Wider Siamese Networks for Real-Time Visual Trackingcited by 156
  22. 2019SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Trackingcited by 147
  23. 2020TAO: A Large-Scale Benchmark for Tracking Any Objectcited by 146
  24. 2017End-to-end representation learning for Correlation Filter based trackingcited by 90
  25. 2016Learning to Track at 100 FPS with Deep Regression Networkscited by 89
  26. 2018Features for Multi-Target Multi-Camera Tracking and Re-Identificationcited by 88
  27. 2018Deep Affinity Network for Multiple Object Trackingcited by 82
  28. 2016Learning by tracking: Siamese CNN for robust target associationcited by 79
  29. 2017Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependenciescited by 76
  30. 2019How To Train Your Deep Multi-Object Trackercited by 71
  31. 2018Siamese Cascaded Region Proposal Networks for Real-Time Visual Trackingcited by 65
  32. 2018A Twofold Siamese Network for Real-Time Object Trackingcited by 62
  33. 2019DirectPose: Direct End-to-End Multi-Person Pose Estimationcited by 49
  34. 2017Recurrent Autoregressive Networks for Online Multi-Object Trackingcited by 48
  35. 2015Near-Online Multi-target Tracking with Aggregated Local Flow Descriptorcited by 46
  36. 2018A Structured Model For Action Detectioncited by 43
  37. 2019Soft Anchor-Point Object Detectioncited by 42
  38. 2020BorderDet: Border Feature for Dense Object Detectioncited by 39

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 23; 2023: 16; 2024: 11; 2025: 6; 2026: 1.

62 papers.

Sort:

By area:

  1. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  2. 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
  3. 2021Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlookcited by 45
  4. 2023MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Trackingcited by 42
  5. 2022AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wildcited by 37
  6. 2022Tracking Objects as Pixel-wise Distributionscited by 36
  7. 2022Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Trackingcited by 33
  8. 2023Focus On Details: Online Multi-object Tracking with Diverse Fine-grained Representationcited by 25
  9. 2023ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Boxcited by 20
  10. 2024EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Drivingcited by 18
  11. 2025SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentationcited by 17
  12. 2022Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimationcited by 16
38 more
  1. 2022Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representationcited by 16
  2. 2024Self-Supervised Multi-Object Tracking with Path Consistencycited by 16
  3. 2023FOLT: Fast Multiple Object Tracking from UAV-captured Videos Based on Optical Flowcited by 15
  4. 2024RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learningcited by 15
  5. 2022Large Scale Real-World Multi-Person Trackingcited by 14
  6. 2022In Pursuit of Many: A Review of Modern Multiple Object Tracking Systemscited by 12
  7. 2023DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusionscited by 12
  8. 2023Video-based Visible-Infrared Person Re-Identification with Auxiliary Samplescited by 11
  9. 2022Continuous Human Action Recognition for Human-Machine Interaction: A Reviewcited by 10
  10. 2022Multi-Object Tracking and Segmentation via Neural Message Passingcited by 9
  11. 2022AirTrack: Onboard Deep Learning Framework for Long-Range Aircraft Detection and Trackingcited by 9
  12. 2022Towards PAC Multi-Object Detection and Trackingcited by 8
  13. 2022Recent Advances in Embedding Methods for Multi-Object Tracking: A Surveycited by 8
  14. 2022Robust Online Video Instance Segmentation with Track Queriescited by 8
  15. 2021Multi-Object Tracking with Hallucinated and Unlabeled Videoscited by 6
  16. 2023SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Featurescited by 6
  17. 2024TrackSSM: A General Motion Predictor by State-Space Modelcited by 6
  18. 2022PatchTrack: Multiple Object Tracking Using Frame Patchescited by 5
  19. 2022End-to-end Tracking with a Multi-query Transformercited by 5
  20. 2023Single-Shot and Multi-Shot Feature Learning for Multi-Object Trackingcited by 5
  21. 2024Is Multiple Object Tracking a Matter of Specialization?cited by 5
  22. 2023DFR-FastMOT: Detection Failure Resistant Tracker for Fast Multi-Object Tracking Based on Sensor Fusioncited by 4
  23. 20233D Multiple Object Tracking on Autonomous Driving: A Literature Reviewcited by 4
  24. 2023OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Trackingcited by 3
  25. 2024MM-Tracker: Motion Mamba with Margin Loss for UAV-platform Multiple Object Trackingcited by 3
  26. 2024DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergycited by 3
  27. 2025IC-Mapper: Instance-Centric Spatio-Temporal Modeling for Online Vectorized Map Constructioncited by 3
  28. 2021A Survey of Fish Tracking Techniques Based on Computer Visioncited by 2
  29. 2022SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learningcited by 2
  30. 2022SearchTrack: Multiple Object Tracking with Object-Customized Search and Motion-Aware Featurescited by 2
  31. 2023Are Labels Needed for Incremental Instance Learning?cited by 2
  32. 2023CityTrack: Improving City-Scale Multi-Camera Multi-Target Tracking by Location-Aware Tracking and Box-Grained Matchingcited by 2
  33. 2023Occlusion-Aware Detection and Re-ID Calibrated Network for Multi-Object Trackingcited by 2
  34. 2024DroneMOT: Drone-based Multi-Object Tracking Considering Detection Difficulties and Simultaneous Moving of Drones and Objectscited by 2
  35. 2021Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackerscited by 1
  36. 2022DSRRTracker: Dynamic Search Region Refinement for Attention-based Siamese Multi-Object Trackingcited by 1
  37. 2022EnsembleMOT: A Step towards Ensemble Learning of Multiple Object Trackingcited by 1
  38. 2022Strong-TransCenter: Improved Multi-Object Tracking based on Transformers with Dense Representationscited by 1

50 most cited of 62 All 62 (JSON)