MOTCOM: The Multi-Object Tracking Dataset Complexity Metric
Not on the map. Why?
Abstract (arXiv)
There exists no comprehensive metric for describing the complexity of Multi-Object Tracking (MOT) sequences. This lack of metrics decreases explainability, complicates comparison of datasets, and reduces the conversation on tracker performance to a matter of leader board position. As a remedy, we present the novel MOT dataset complexity metric (MOTCOM), which is a combination of three sub-metrics inspired by key problems in MOT: occlusion, erratic motion, and visual similarity. The insights of MOTCOM can open nuanced discussions on tracker performance and may lead to a wider acknowledgement of novel contributions developed for either less known datasets or those aimed at solving sub-problems. We evaluate MOTCOM on the comprehensive MOT17, MOT20, and MOTSynth datasets and show that MOTCOM is far better at describing the complexity of MOT sequences compared to the conventional density and number of tracks. Project page at https://vap.aau.dk/motcom
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 49 references that are in the map. First posted on arXiv 20 Jul 2022.
Builds on
29 of 49 references.
References · 29
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
- 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
- 2016Simple Online and Realtime Trackingcited by 862
- 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
- 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
- 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
- 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 546
- 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
- 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 489
- 2020Tracking Objects as Pointscited by 483
- 2019Tracking without bells and whistlescited by 382
17 more
- 2019MOTS: Multi-Object Tracking and Segmentationcited by 222
- 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
- 2014Multiple Object Tracking: A Literature Reviewcited by 165
- 2020MOTChallenge: A Benchmark for Single-Camera Multiple Target Trackingcited by 134
- 2020Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Trackingcited by 115
- 2016Learning by tracking: Siamese CNN for robust target associationcited by 79
- 2019Spatial-Temporal Relation Networks for Multi-Object Trackingcited by 74
- 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 68
- 2020RetinaTrack: Online Single Stage Joint Detection and Trackingcited by 67
- 2018Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Datacited by 45
- 2019A survey of advances in vision-based vehicle re-identificationcited by 36
- 2020A Unified Object Motion and Affinity Model for Online Multi-Object Trackingcited by 33
- 20203D-ZeF: A 3D Zebrafish Tracking Benchmark Datasetcited by 24
- 2017Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Trackingcited by 18
- 2019Similarity Learning Networks for Animal Individual Re-Identification -- Beyond the Capabilities of a Human Observercited by 18
- 2019Spectral Metric for Dataset Complexity Assessmentcited by 15
- 2019Measuring Dataset Granularitycited by 8
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.
2 papers.