mlsanityData to 7 Oct 2026

Simple Cues Lead to a Strong Multi-Object Tracker

arXiv 2206.04656 ↗First posted 9 Jun 2022cs.CVcited by 44

Not on the map. Why?

Abstract (arXiv)

For a long time, the most common paradigm in Multi-Object Tracking was tracking-by-detection (TbD), where objects are first detected and then associated over video frames. For association, most models resourced to motion and appearance cues, e.g., re-identification networks. Recent approaches based on attention propose to learn the cues in a data-driven manner, showing impressive results. In this paper, we ask ourselves whether simple good old TbD methods are also capable of achieving the performance of end-to-end models. To this end, we propose two key ingredients that allow a standard re-identification network to excel at appearance-based tracking. We extensively analyse its failure cases, and show that a combination of our appearance features with a simple motion model leads to strong tracking results. Our tracker generalizes to four public datasets, namely MOT17, MOT20, BDD100k, and DanceTrack, achieving state-of-the-art performance. https://github.com/dvl-tum/GHOST.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Builds on 72 of its 99 references that are in the map. First posted on arXiv 9 Jun 2022.

Builds on

72 of 99 references.

References · 72

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  6. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  7. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  8. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  9. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  10. 2016Simple Online and Realtime Trackingcited by 862
  11. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  12. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
38 more
  1. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  2. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
  3. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 546
  4. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  5. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  6. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 489
  7. 2020Tracking Objects as Pointscited by 483
  8. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 472
  9. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 429
  10. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  11. 2019Tracking without bells and whistlescited by 382
  12. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  13. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  14. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  15. 2020MOT20: A benchmark for multi object tracking in crowded scenescited by 355
  16. 2019Towards Real-Time Multi-Object Trackingcited by 311
  17. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
  18. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
  19. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 235
  20. 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
  21. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 213
  22. 2019Learning a Neural Solver for Multiple Object Trackingcited by 198
  23. 2019Domain-Specific Batch Normalization for Unsupervised Domain Adaptationcited by 197
  24. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  25. 2020MOTChallenge: A Benchmark for Single-Camera Multiple Target Trackingcited by 134
  26. 2019ABD-Net: Attentive but Diverse Person Re-Identificationcited by 126
  27. 2021Learning to Track with Object Permanencecited by 117
  28. 2020Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Trackingcited by 115
  29. 2022MeMOT: Multi-Object Tracking with Memorycited by 113
  30. 2020Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identificationcited by 110
  31. 2022Global Tracking Transformerscited by 110
  32. 2018Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identificationcited by 96
  33. 2018Deep Affinity Network for Multiple Object Trackingcited by 82
  34. 2016Learning by tracking: Siamese CNN for robust target associationcited by 79
  35. 2020Meta Batch-Instance Normalization for Generalizable Person Re-Identificationcited by 77
  36. 2017Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependenciescited by 76
  37. 2016POI: Multiple Object Tracking with High Performance Detection and Appearance Featurecited by 74
  38. 2019Spatial-Temporal Relation Networks for Multi-Object Trackingcited by 74

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 16; 2025: 17; 2026: 6.

44 papers.

Sort:

By area:

  1. 2023Hybrid-SORT: Weak Cues Matter for Online Multi-Object Trackingcited by 66
  2. 2024Multiple Object Tracking as ID Predictioncited by 58
  3. 2023UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensationcited by 42
  4. 2023EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye Viewcited by 33
  5. 2024Lifting Multi-View Detection and Tracking to the Bird's Eye Viewcited by 25
  6. 2024Towards Generalizable Multi-Object Trackingcited by 22
  7. 2024Keypoint Promptable Re-Identificationcited by 15
  8. 2023DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusionscited by 12
  9. 2024DeconfuseTrack:Dealing with Confusion for Multi-Object Trackingcited by 9
  10. 2024MambaMOT: State-Space Model as Motion Predictor for Multi-Object Trackingcited by 8
  11. 2024SPAMming Labels: Efficient Annotations for the Trackers of Tomorrowcited by 7
  12. 2025Zero-Shot 4D Lidar Panoptic Segmentationcited by 6
32 more
  1. 2023Single-Shot and Multi-Shot Feature Learning for Multi-Object Trackingcited by 5
  2. 2024Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknowncited by 5
  3. 2024Is Multiple Object Tracking a Matter of Specialization?cited by 5
  4. 2025CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Trackingcited by 4
  5. 2024DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergycited by 3
  6. 2025NOOUGAT: Towards Unified Online and Offline Multi-Object Trackingcited by 3
  7. 2024Multi-Granularity Language-Guided Training for Multi-Object Trackingcited by 2
  8. 2024DroneMOT: Drone-based Multi-Object Tracking Considering Detection Difficulties and Simultaneous Moving of Drones and Objectscited by 2
  9. 2025When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Trackingcited by 2
  10. 2025SIS-Challenge: Event-based Spatio-temporal Instance Segmentation Challenge at the CVPR 2025 Event-based Vision Workshopcited by 2
  11. 2024AM-SORT: Adaptable Motion Predictor with Historical Trajectory Embedding for Multi-Object Trackingcited by 1
  12. 2024Spatial-Temporal Multi-Cuts for Online Multiple-Camera Vehicle Trackingcited by 1
  13. 2025FusionSORT: Fusion Methods for Online Multi-object Visual Trackingcited by 1
  14. 2025Tiny Neural Networks for Multi-Object Tracking in a Modular Kalman Frameworkcited by 1
  15. 2025Depth-Aware Scoring and Hierarchical Alignment for Multiple Object Trackingcited by 1
  16. 2026Occlusion-Aware SORT: Observing Occlusion for Robust Multi-Object Trackingcited by 1
  17. 2024Hierarchical IoU Tracking based on Intervalcited by 0
  18. 2024When to Extract ReID Features: A Selective Approach for Improved Multiple Object Trackingcited by 0
  19. 2025FaceQSORT: a Multi-Face Tracking Method based on Biometric and Appearance Featurescited by 0
  20. 2025Deep LG-Track: An Enhanced Localization-Confidence-Guided Multi-Object Trackercited by 0
  21. 2025SAM2Auto: Auto Annotation Using FLASHcited by 0
  22. 2025Towards Continuous Home Cage Monitoring: An Evaluation of Tracking and Identification Strategies for Laboratory Micecited by 0
  23. 2025GRASPTrack: Geometry-Reasoned Association via Segmentation and Projection for Multi-Object Trackingcited by 0
  24. 2025SocialTrack: Multi-Object Tracking in Complex Urban Traffic Scenes Inspired by Social Behaviorcited by 0
  25. 2025SelfMOTR: Revisiting MOTR with Self-Generating Detection Priorscited by 0
  26. 2025DM3T: Harmonizing Modalities via Diffusion for Multi-Object Trackingcited by 0
  27. 2025Learning Association via Track-Detection Matching for Multi-Object Trackingcited by 0
  28. 2026SAMOFT: Robust Multi-Object Tracking via Region and Flowcited by 0
  29. 2026When Fish Look Alike: Tracking Identities with Dual-branch Elasticitycited by 0
  30. 2026Tracking the Unseen: An Occlusion-Robust Framework for Target Tracking Under Full and Long-Term Occlusioncited by 0
  31. 2026Rule-Constrained Assignment for Cue-Ball Identification in Broadcast Snookercited by 0
  32. 2026Towards Automatic Video Annotation with ASH: Zero-Shot Open-Vocabulary Multi-Object Tracking and Segmentationcited by 0