mlsanityData to 7 Oct 2026

OCTrack: Benchmarking the Open-Corpus Multi-Object Tracking

arXiv 2407.14047 ↗First posted 19 Jul 2024cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We study a novel yet practical problem of open-corpus multi-object tracking (OCMOT), which extends the MOT into localizing, associating, and recognizing generic-category objects of both seen (base) and unseen (novel) classes, but without the category text list as prompt. To study this problem, the top priority is to build a benchmark. In this work, we build OCTrackB, a large-scale and comprehensive benchmark, to provide a standard evaluation platform for the OCMOT problem. Compared to previous datasets, OCTrackB has more abundant and balanced base/novel classes and the corresponding samples for evaluation with less bias. We also propose a new multi-granularity recognition metric to better evaluate the generative object recognition in OCMOT. By conducting the extensive benchmark evaluation, we report and analyze the results of various state-of-the-art methods, which demonstrate the rationale of OCMOT, as well as the usefulness and advantages of OCTrackB.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 56 of its 63 references that are in the map. First posted on arXiv 19 Jul 2024.

Builds on

56 of 63 references.

References · 56

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  3. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  4. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  5. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  6. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  7. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  8. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  9. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  10. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  11. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  12. 2020Tracking Objects as Pointscited by 483
38 more
  1. 2019Tracking without bells and whistlescited by 382
  2. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  3. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  4. 2020MOT20: A benchmark for multi object tracking in crowded scenescited by 355
  5. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  6. 2023Scaling Open-Vocabulary Object Detectioncited by 335
  7. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
  8. 2020Detection and Tracking Meet Drones Challengecited by 261
  9. 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
  10. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 213
  11. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  12. 2018The Unmanned Aerial Vehicle Benchmark: Object Detection and Trackingcited by 207
  13. 2020TAO: A Large-Scale Benchmark for Tracking Any Objectcited by 146
  14. 2015MOTChallenge 2015: Towards a Benchmark for Multi-Target Trackingcited by 133
  15. 2023SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenescited by 130
  16. 2022MeMOT: Multi-Object Tracking with Memorycited by 113
  17. 2022Global Tracking Transformerscited by 110
  18. 2022Learning Object-Language Alignments for Open-Vocabulary Object Detectioncited by 95
  19. 2016Learning by tracking: Siamese CNN for robust target associationcited by 79
  20. 2017Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependenciescited by 76
  21. 2022BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Videocited by 66
  22. 2023MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Trackingcited by 64
  23. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  24. 2016Online Multi-Target Tracking Using Recurrent Neural Networkscited by 59
  25. 2023OVTrack: Open-Vocabulary Multiple Object Trackingcited by 53
  26. 2023Multi-Modal Classifiers for Open-Vocabulary Object Detectioncited by 53
  27. 2019Towards Segmenting Anything That Movescited by 51
  28. 2021Opening up Open-World Trackingcited by 50
  29. 2022CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusioncited by 50
  30. 2019Track to Reconstruct and Reconstruct to Trackcited by 49
  31. 2023CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detectioncited by 46
  32. 2023Towards Open-Vocabulary Video Instance Segmentationcited by 45
  33. 2022Tracking Every Thing in the Wildcited by 44
  34. 2018Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Trackingcited by 40
  35. 2022AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wildcited by 37
  36. 2020Probabilistic Tracklet Scoring and Inpainting for Multiple Object Trackingcited by 36
  37. 2020GMOT-40: A Benchmark for Generic Multiple Object Trackingcited by 32
  38. 2024Generative Region-Language Pretraining for Open-Ended Object Detectioncited by 29

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Trackingcited by 4