mlsanityData to 7 Oct 2026

Towards Grand Unification of Object Tracking

arXiv 2207.07078 ↗First posted 14 Jul 2022cs.CVcited by 93

Not on the map. Why?

Abstract (arXiv)

We present a unified method, termed Unicorn, that can simultaneously solve four tracking problems (SOT, MOT, VOS, MOTS) with a single network using the same model parameters. Due to the fragmented definitions of the object tracking problem itself, most existing trackers are developed to address a single or part of tasks and overspecialize on the characteristics of specific tasks. By contrast, Unicorn provides a unified solution, adopting the same input, backbone, embedding, and head across all tracking tasks. For the first time, we accomplish the great unification of the tracking network architecture and learning paradigm. Unicorn performs on-par or better than its task-specific counterparts in 8 tracking datasets, including LaSOT, TrackingNet, MOT17, BDD100K, DAVIS16-17, MOTS20, and BDD100K MOTS. We believe that Unicorn will serve as a solid step towards the general vision model. Code is available at https://github.com/MasterBin-IIAU/Unicorn.

Key facts. Cited by 93 papers in the map (data through 7 Oct 2026). Builds on 89 of its 94 references that are in the map. First posted on arXiv 14 Jul 2022.

Builds on

89 of 94 references.

References · 89

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2022A ConvNet for the 2020scited by 3,545
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2018YOLOv3: An Incremental Improvementcited by 2,652
  10. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  11. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  12. 2018Group Normalizationcited by 1,514
38 more
  1. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  2. 2019Objects as Pointscited by 1,172
  3. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  4. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  5. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  6. 2016Simple Online and Realtime Trackingcited by 862
  7. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  8. 2021Florence: A New Foundation Model for Computer Visioncited by 802
  9. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  10. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  11. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  12. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  13. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 489
  14. 2020Tracking Objects as Pointscited by 483
  15. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 471
  16. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
  17. 2019Video Object Segmentation using Space-Time Memory Networkscited by 436
  18. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 424
  19. 2021Transformer Trackingcited by 412
  20. 2019Video Instance Segmentationcited by 391
  21. 2019Tracking without bells and whistlescited by 382
  22. 2018YouTube-VOS: A Large-Scale Video Object Segmentation Benchmarkcited by 381
  23. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  24. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  25. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 348
  26. 2019Learning Discriminative Model Prediction for Trackingcited by 344
  27. 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 342
  28. 2020Conditional Convolutions for Instance Segmentationcited by 314
  29. 2019Towards Real-Time Multi-Object Trackingcited by 311
  30. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  31. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
  32. 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
  33. 2016ECO: Efficient Convolution Operators for Trackingcited by 239
  34. 2020Space-Time Correspondence as a Contrastive Random Walkcited by 239
  35. 2020Probabilistic Regression for Visual Trackingcited by 231
  36. 2019MOTS: Multi-Object Tracking and Segmentationcited by 222
  37. 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
  38. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 45; 2024: 24; 2025: 13; 2026: 4.

93 papers.

Sort:

By area:

  1. 2023Emergent Correspondence from Image Diffusioncited by 437
  2. 2023Tracking Anything with Decoupled Video Segmentationcited by 197
  3. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  4. 2023Putting the Object Back into Video Object Segmentationcited by 182
  5. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  6. 2022In Defense of Online Models for Video Instance Segmentationcited by 97
  7. 2023Generalized Relation Modeling for Transformer Trackingcited by 93
  8. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 86
  9. 2023Robust Object Modeling for Visual Trackingcited by 80
  10. 2023General Object Foundation Model for Images and Videos at Scalecited by 71
  11. 2023ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding Systemcited by 65
  12. 2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuningcited by 64
38 more
  1. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  2. 2024Matching Anything by Segmenting Anythingcited by 49
  3. 2023Advances in Deep Concealed Scene Understandingcited by 47
  4. 2023Frame-Event Alignment and Fusion Network for High Frame Rate Trackingcited by 43
  5. 2023TarViS: A Unified Approach for Target-based Video Segmentationcited by 32
  6. 2023Lenna: Language Enhanced Reasoning Detection Assistantcited by 29
  7. 2022Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localizationcited by 24
  8. 2023DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Taskscited by 22
  9. 2023UniRef++: Segment Every Reference Object in Spatial and Temporal Spacescited by 22
  10. 2024OmniVid: A Generative Framework for Universal Video Understandingcited by 22
  11. 2024Towards Generalizable Multi-Object Trackingcited by 22
  12. 2023TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenescited by 21
  13. 2023ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Boxcited by 20
  14. 2023Mask-Free Video Instance Segmentationcited by 20
  15. 2023Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Trackingcited by 20
  16. 2023Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Trackingcited by 20
  17. 2023PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Predictioncited by 20
  18. 2023OmniTracker: Unifying Object Tracking by Tracking-with-Detectioncited by 19
  19. 2023VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Modelscited by 19
  20. 2024Spider: A Unified Framework for Context-dependent Concept Segmentationcited by 18
  21. 2025MangaNinja: Line Art Colorization with Precise Reference Followingcited by 17
  22. 2025SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentationcited by 17
  23. 2025Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMscited by 16
  24. 2024PartGLEE: A Foundation Model for Recognizing and Parsing Any Objectscited by 15
  25. 2024Reading Relevant Feature from Global Representation Memory for Visual Object Trackingcited by 12
  26. 2022Beyond SOT: Tracking Multiple Generic Objects at Oncecited by 11
  27. 2023Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Modelscited by 11
  28. 2024Beyond MOT: Semantic Multi-Object Trackingcited by 11
  29. 2023Streaming Video Modelcited by 10
  30. 2023Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Trackingcited by 10
  31. 2023Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Trackingcited by 9
  32. 2024LaMOT: Language-Guided Multi-Object Trackingcited by 9
  33. 2023Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Drivingcited by 8
  34. 2024360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videoscited by 8
  35. 2022Robust Multi-Object Tracking by Marginal Inferencecited by 7
  36. 2023Z-GMOT: Zero-shot Generic Multiple Object Trackingcited by 7
  37. 2023Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Trackingcited by 7
  38. 2023Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentationcited by 5

50 most cited of 93 All 93 (JSON)