mlsanityData to 14 Oct 2026

Fast Online Object Tracking and Segmentation: A Unifying Approach

arXiv 1812.05050 ↗First posted 12 Dec 2018cs.CVcited by 272

Not on the map. Why?

Abstract (arXiv)

In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task. Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second. Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state of the art among real-time trackers on VOT-2018, while at the same time demonstrating competitive performance and the best speed for the semi-supervised video object segmentation task on DAVIS-2016 and DAVIS-2017. The project website is http://www.robots.ox.ac.uk/~qwang/SiamMask.

Key facts. Cited by 272 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 95; 2022: 58; 2023: 53; 2024: 32; 2025: 26; 2026: 8.

272 papers.

Sort:

By area:

  1. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  2. 2023Segment Everything Everywhere All at Oncecited by 548
  3. 2022XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Modelcited by 439
  4. 2021Transformer Trackingcited by 412
  5. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 350
  6. 2022Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Frameworkcited by 330
  7. 2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 281
  8. 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 234
  9. 2023Track Anything: Segment Anything Meets Videoscited by 234
  10. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  11. 2021Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentationcited by 203
  12. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
38 more
  1. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 192
  2. 2023Putting the Object Back into Video Object Segmentationcited by 188
  3. 2021Learning To Count Everythingcited by 150
  4. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  5. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  6. 2021Learning Target Candidate Association to Keep Track of What Not to Trackcited by 131
  7. 2021Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusioncited by 129
  8. 2021VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flowscited by 129
  9. 2021Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmarkcited by 126
  10. 2022Backbone is All Your Need: A Simplified Architecture for Visual Object Trackingcited by 119
  11. 2022Transforming Model Prediction for Trackingcited by 117
  12. 2022Towards Grand Unification of Object Trackingcited by 93
  13. 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
  14. 2022Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baselinecited by 91
  15. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  16. 2023Segment Anything Meets Point Trackingcited by 81
  17. 2024SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Treecited by 80
  18. 2022LVOS: A Benchmark for Long-term Video Object Segmentationcited by 77
  19. 2023Siamese Masked Autoencoderscited by 76
  20. 2022Transformer Tracking with Cyclic Shifting Window Attentioncited by 75
  21. 2023Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baselinecited by 73
  22. 2021HiFT: Hierarchical Feature Transformer for Aerial Trackingcited by 72
  23. 2023General Object Foundation Model for Images and Videos at Scalecited by 71
  24. 2022TCTrack: Temporal Contexts for Aerial Trackingcited by 69
  25. 2021SwiftNet: Real-time Video Object Segmentationcited by 67
  26. 2021Box-Aware Feature Enhancement for Single Object Tracking on Point Cloudscited by 66
  27. 2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuningcited by 65
  28. 2021The Multi-Temporal Urban Development SpaceNet Datasetcited by 62
  29. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  30. 2022Correlation-Aware Deep Trackingcited by 62
  31. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 62
  32. 2021Joint Inductive and Transductive Learning for Video Object Segmentationcited by 61
  33. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  34. 2023Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Trackingcited by 53
  35. 2023Visual In-Context Promptingcited by 52
  36. 2021Efficient Visual Tracking with Exemplar Transformerscited by 48
  37. 2021Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlookcited by 46
  38. 2023Implicit Temporal Modeling with Learnable Alignment for Video Recognitioncited by 46

50 most cited of 272 All 272 (JSON)