mlsanityData to 7 Oct 2026

Local Metrics for Multi-Object Tracking

arXiv 2104.02631 ↗First posted 6 Apr 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper introduces temporally local metrics for Multi-Object Tracking. These metrics are obtained by restricting existing metrics based on track matching to a finite temporal horizon, and provide new insight into the ability of trackers to maintain identity over time. Moreover, the horizon parameter offers a novel, meaningful mechanism by which to define the relative importance of detection and association, a common dilemma in applications where imperfect association is tolerable. It is shown that the historical Average Tracking Accuracy (ATA) metric exhibits superior sensitivity to association, enabling its proposed local variant, ALTA, to capture a wide range of characteristics. In particular, ALTA is better equipped to identify advances in association independent of detection. The paper further presents an error decomposition for ATA that reveals the impact of four distinct error types and is equally applicable to ALTA. The diagnostic capabilities of ALTA are demonstrated on the MOT 2017 and Waymo Open Dataset benchmarks.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 47 of its 87 references that are in the map. First posted on arXiv 6 Apr 2021.

Builds on

47 of 87 references.

References · 47

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  4. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  6. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  7. 2019Objects as Pointscited by 1,172
  8. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  9. 2016Simple Online and Realtime Trackingcited by 862
  10. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
  11. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 546
  12. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
35 more
  1. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  2. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 489
  3. 2020Tracking Objects as Pointscited by 483
  4. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 428
  5. 2019Tracking without bells and whistlescited by 382
  6. 2016ECO: Efficient Convolution Operators for Trackingcited by 239
  7. 2019Learning a Neural Solver for Multiple Object Trackingcited by 198
  8. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  9. 2020TAO: A Large-Scale Benchmark for Tracking Any Objectcited by 146
  10. 2020Video Panoptic Segmentationcited by 141
  11. 2020MOTChallenge: A Benchmark for Single-Camera Multiple Target Trackingcited by 134
  12. 2020Rethinking the competition between detection and ReID in Multi-Object Trackingcited by 101
  13. 2018Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identificationcited by 96
  14. 2018Deep Affinity Network for Multiple Object Trackingcited by 82
  15. 2017Action Tubelet Detector for Spatio-Temporal Action Localizationcited by 77
  16. 2019Online Multi-Object Tracking with Dual Matching Attention Networkscited by 77
  17. 2019Spatial-Temporal Relation Networks for Multi-Object Trackingcited by 74
  18. 2019How To Train Your Deep Multi-Object Trackercited by 71
  19. 2020TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Modelcited by 70
  20. 2019FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Trackingcited by 65
  21. 2020Lifted Disjoint Paths with Application in Multiple Object Trackingcited by 55
  22. 2020MAT: Motion-Aware Multi-Object Trackingcited by 40
  23. 2020Simple Unsupervised Multi-Object Trackingcited by 33
  24. 2018Exploit the Connectivity: Multi-Object Tracking with TrackletNetcited by 30
  25. 2020GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalizationcited by 25
  26. 2019Multi-Object Tracking with Multiple Cues and Switcher-Aware Classificationcited by 16
  27. 2020Joint Object Detection and Multi-Object Tracking with Graph Neural Networkscited by 14
  28. 2019Occlusion-Robust Online Multi-Object Visual Tracking using a GM-PHD Filter with CNN-Based Re-Identificationcited by 12
  29. 2020SoDA: Multi-Object Tracking with Soft Data Associationcited by 12
  30. 2019Online Multiple Pedestrians Tracking using Deep Temporal Appearance Matching Associationcited by 9
  31. 2018Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filteringcited by 6
  32. 2018Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Trackingcited by 6
  33. 2018Multiple People Tracking Using Hierarchical Deep Tracklet Re-identificationcited by 5
  34. 20201st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Trackingcited by 5
  35. 2020SAMOT: Switcher-Aware Multi-Object Tracking and Still Another MOT Measurecited by 3

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 3; 2023: 1.

8 papers.

  1. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  2. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  3. 2021Split and Connect: A Universal Tracklet Booster for Multi-Object Trackingcited by 17
  4. 2023Robotic Table Tennis: A Case Study into a High Speed Learning Systemcited by 12
  5. 2022Recent Advances in Embedding Methods for Multi-Object Tracking: A Surveycited by 8
  6. 2021Few-Shot Video Object Detectioncited by 7
  7. 2021Multi-Object Tracking and Segmentation with a Space-Time Memory Networkcited by 1
  8. 2022Detection-aware multi-object tracking evaluationcited by 1