mlsanityData to 14 Oct 2026

SiamMask: A Framework for Fast Online Object Tracking and Segmentation

arXiv 2207.02088 ↗First posted 5 Jul 2022cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

In this paper we introduce SiamMask, a framework to perform both visual object tracking and video object segmentation, in real-time, with the same simple method. We improve the offline training procedure of popular fully-convolutional Siamese approaches by augmenting their losses with a binary segmentation task. Once the offline training is completed, SiamMask only requires a single bounding box for initialization and can simultaneously carry out visual object tracking and segmentation at high frame-rates. Moreover, we show that it is possible to extend the framework to handle multiple object tracking and segmentation by simply re-using the multi-task model in a cascaded fashion. Experimental results show that our approach has high processing efficiency, at around 55 frames per second. It yields real-time state-of-the-art results on visual-object tracking benchmarks, while at the same time demonstrating competitive performance at a high speed for video object segmentation benchmarks.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 73 of its 110 references that are in the map. First posted on arXiv 5 Jul 2022.

Builds on

73 of 110 references.

References · 73

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2017Mask R-CNNcited by 7,277
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  8. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
  9. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 568
  10. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  11. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 475
  12. 2019Video Instance Segmentationcited by 393
38 more
  1. 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 343
  2. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  3. 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
  4. 2016ECO: Efficient Convolution Operators for Trackingcited by 239
  5. 2016One-Shot Video Object Segmentationcited by 235
  6. 2018YouTube-VOS: Sequence-to-Sequence Video Object Segmentationcited by 232
  7. 2015Learning Multi-Domain Convolutional Neural Networks for Visual Trackingcited by 209
  8. 2020Siamese Box Adaptive Network for Visual Trackingcited by 189
  9. 2018Distractor-aware Siamese Networks for Visual Object Trackingcited by 187
  10. 2019SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelinescited by 177
  11. 2016Learning Video Object Segmentation from Static Imagescited by 151
  12. 2019SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Trackingcited by 148
  13. 2017Detect to Track and Track to Detectcited by 131
  14. 2015A Novel Performance Evaluation Methodology for Single-Target Trackerscited by 113
  15. 2017YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Videocited by 109
  16. 2017Online Adaptation of Convolutional Neural Networks for Video Object Segmentationcited by 109
  17. 2018Efficient Video Object Segmentation via Network Modulationcited by 98
  18. 2016Learning feed-forward one-shot learnerscited by 93
  19. 2017Video Object Segmentation Without Temporal Informationcited by 93
  20. 2017SegFlow: Joint Learning for Video Object Segmentation and Optical Flowcited by 92
  21. 2017End-to-end representation learning for Correlation Filter based trackingcited by 90
  22. 2018VideoMatch: Matching based Video Object Segmentationcited by 90
  23. 2016Learning to Track at 100 FPS with Deep Regression Networkscited by 89
  24. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  25. 2020Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimationcited by 81
  26. 2015Learning to Segment Object Candidatescited by 79
  27. 2018Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learningcited by 74
  28. 2020Graph Attention Trackingcited by 70
  29. 2019D3S -- A Discriminative Single Shot Segmentation Trackercited by 69
  30. 2016Learning to Refine Object Segmentscited by 67
  31. 2016Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Trackingcited by 66
  32. 2016Learning Spatially Regularized Correlation Filters for Visual Trackingcited by 66
  33. 2020Efficient Adversarial Attacks for Visual Object Trackingcited by 66
  34. 2018Siamese Cascaded Region Proposal Networks for Real-Time Visual Trackingcited by 65
  35. 2018Learning Spatial-Temporal Regularized Correlation Filters for Visual Trackingcited by 63
  36. 2018A Twofold Siamese Network for Real-Time Object Trackingcited by 62
  37. 2016Siamese Instance Search for Trackingcited by 60
  38. 2018Learning Dynamic Memory Networks for Object Trackingcited by 59

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 4; 2025: 4; 2026: 1.

13 papers.

Sort:

By area:

  1. 2022Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localizationcited by 24
  2. 2024Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Modelcited by 19
  3. 2023CUREE: A Curious Underwater Robot for Ecosystem Explorationcited by 13
  4. 2023Large-Scale Person Detection and Localization using Overhead Fisheye Camerascited by 12
  5. 2023SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Featurescited by 6
  6. 2025Vision-Based Anti Unmanned Aerial Technology: Opportunities and Challengescited by 4
  7. 2025VPTracker: Global Vision-Language Tracking via Visual Promptcited by 3
  8. 2024Watching Swarm Dynamics from Above: A Framework for Advanced Object Tracking in Drone Videoscited by 2
  9. 2025Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Trackingcited by 2
  10. 2024DaDiff: Domain-aware Diffusion Model for Nighttime UAV Trackingcited by 1
  11. 2026Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Trackingcited by 1
  12. 2024Rotation center identification based on geometric relationships for rotary motion deblurringcited by 0
1 more
  1. 2025Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Trackingcited by 0