mlsanityData to 7 Oct 2026

Multiple Object Tracking from appearance by hierarchically clustering tracklets

arXiv 2210.03355 ↗First posted 7 Oct 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Current approaches in Multiple Object Tracking (MOT) rely on the spatio-temporal coherence between detections combined with object appearance to match objects from consecutive frames. In this work, we explore MOT using object appearances as the main source of association between objects in a video, using spatial and temporal priors as weighting factors. We form initial tracklets by leveraging on the idea that instances of an object that are close in time should be similar in appearance, and build the final object tracks by fusing the tracklets in a hierarchical fashion. We conduct extensive experiments that show the effectiveness of our method over three different MOT benchmarks, MOT17, MOT20, and DanceTrack, being competitive in MOT17 and MOT20 and establishing state-of-the-art results in DanceTrack.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 38 of its 55 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

38 of 55 references.

References · 38

  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. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  4. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  5. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  6. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  7. 2016Simple Online and Realtime Trackingcited by 862
  8. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  9. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  10. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
  11. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  12. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 546
26 more
  1. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  2. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  3. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 489
  4. 2020Tracking Objects as Pointscited by 483
  5. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 429
  6. 2019Tracking without bells and whistlescited by 382
  7. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  8. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  9. 2020MOT20: A benchmark for multi object tracking in crowded scenescited by 355
  10. 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 290
  11. 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
  12. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 213
  13. 2019Learning a Neural Solver for Multiple Object Trackingcited by 198
  14. 2020FastReID: A Pytorch Toolbox for General Instance Re-identificationcited by 164
  15. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  16. 2017Detect to Track and Track to Detectcited by 131
  17. 2021Learning to Track with Object Permanencecited by 117
  18. 2018Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identificationcited by 96
  19. 2018Features for Multi-Target Multi-Camera Tracking and Re-Identificationcited by 88
  20. 2021Multiple Object Tracking with Correlation Learningcited by 67
  21. 2019FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Trackingcited by 65
  22. 2020Lifted Disjoint Paths with Application in Multiple Object Trackingcited by 55
  23. 2021RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representationcited by 52
  24. 2021Learning a Proposal Classifier for Multiple Object Trackingcited by 42
  25. 2018Exploit the Connectivity: Multi-Object Tracking with TrackletNetcited by 30
  26. 2017Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Projectcited by 19

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 1.

5 papers.

  1. 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
  2. 2023UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensationcited by 42
  3. 2023Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detectionscited by 5
  4. 2023The detection and rectification for identity-switch based on unfalsified controlcited by 2
  5. 2024MOT FCG++: Enhanced Representation of Spatio-temporal Motion and Appearance Featurescited by 0