mlsanityData to 14 Oct 2026

TransTrack: Multiple Object Tracking with Transformer

arXiv 2012.15460 ↗First posted 31 Dec 2020cs.CVcited by 371

Not on the map. Why?

Abstract (arXiv)

In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems. TransTrack leverages the transformer architecture, which is an attention-based query-key mechanism. It applies object features from the previous frame as a query of the current frame and introduces a set of learned object queries to enable detecting new-coming objects. It builds up a novel joint-detection-and-tracking paradigm by accomplishing object detection and object association in a single shot, simplifying complicated multi-step settings in tracking-by-detection methods. On MOT17 and MOT20 benchmark, TransTrack achieves 74.5% and 64.5% MOTA, respectively, competitive to the state-of-the-art methods. We expect TransTrack to provide a novel perspective for multiple object tracking. The code is available at: urlhttps://github.com/PeizeSun/TransTrack.

Key facts. Cited by 371 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 41; 2022: 86; 2023: 83; 2024: 85; 2025: 46; 2026: 30.

371 papers.

Sort:

By area:

  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  2. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  3. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  4. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
  5. 2021TransReID: Transformer-based Object Re-Identificationcited by 435
  6. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 381
  7. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 350
  8. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 346
  9. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 320
  10. 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Modelscited by 314
  11. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 302
  12. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 241
38 more
  1. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 217
  2. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  3. 2022Language as Queries for Referring Video Object Segmentationcited by 182
  4. 2021Visual Saliency Transformercited by 175
  5. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 168
  6. 2021Instances as Queriescited by 158
  7. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  8. 2022DETRs with Hybrid Matchingcited by 150
  9. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  10. 2022AiATrack: Attention in Attention for Transformer Visual Trackingcited by 137
  11. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 132
  12. 2023Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identificationcited by 132
  13. 2023SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenescited by 131
  14. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  15. 2022MeMOT: Multi-Object Tracking with Memorycited by 114
  16. 2022Global Tracking Transformerscited by 110
  17. 2022AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensingcited by 110
  18. 2021SeqFormer: Sequential Transformer for Video Instance Segmentationcited by 98
  19. 2022In Defense of Online Models for Video Instance Segmentationcited by 97
  20. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
  21. 2022Towards Grand Unification of Object Trackingcited by 93
  22. 2023Referring Multi-Object Trackingcited by 93
  23. 2023ReasonNet: End-to-End Driving with Temporal and Global Reasoningcited by 93
  24. 2022MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queriescited by 91
  25. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 88
  26. 2023DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuningcited by 84
  27. 2022Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentationcited by 79
  28. 2022TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformerscited by 78
  29. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  30. 2024Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformerscited by 76
  31. 2022Boosting Crowd Counting via Multifaceted Attentioncited by 73
  32. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 70
  33. 2024MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mappingcited by 68
  34. 2023Hybrid-SORT: Weak Cues Matter for Online Multi-Object Trackingcited by 67
  35. 2022Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Spacecited by 66
  36. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  37. 2024Multiple Object Tracking as ID Predictioncited by 60
  38. 2024DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Predictioncited by 59

50 most cited of 371 All 371 (JSON)