mlsanityData to 7 Oct 2026

SwiftNet: Real-time Video Object Segmentation

arXiv 2102.04604 ↗First posted 9 Feb 2021cs.CVcited by 67

Not on the map. Why?

Abstract (arXiv)

In this work we present SwiftNet for real-time semisupervised video object segmentation (one-shot VOS), which reports 77.8% J &F and 70 FPS on DAVIS 2017 validation dataset, leading all present solutions in overall accuracy and speed performance. We achieve this by elaborately compressing spatiotemporal redundancy in matching-based VOS via Pixel-Adaptive Memory (PAM). Temporally, PAM adaptively triggers memory updates on frames where objects display noteworthy inter-frame variations. Spatially, PAM selectively performs memory update and match on dynamic pixels while ignoring the static ones, significantly reducing redundant computations wasted on segmentation-irrelevant pixels. To promote efficient reference encoding, light-aggregation encoder is also introduced in SwiftNet deploying reversed sub-pixel. We hope SwiftNet could set a strong and efficient baseline for real-time VOS and facilitate its application in mobile vision. The source code of SwiftNet can be found at https://github.com/haochenheheda/SwiftNet.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 9 Feb 2021.

Builds on

37 of 46 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Non-local Neural Networkscited by 2,290
  4. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  5. 2019Video Object Segmentation using Space-Time Memory Networkscited by 436
  6. 2019Video Instance Segmentationcited by 391
  7. 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
  8. 2016One-Shot Video Object Segmentationcited by 233
  9. 2018YouTube-VOS: Sequence-to-Sequence Video Object Segmentationcited by 228
  10. 2019FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentationcited by 178
  11. 2016Learning Video Object Segmentation from Static Imagescited by 151
  12. 2020Collaborative Video Object Segmentation by Foreground-Background Integrationcited by 142
25 more
  1. 2020See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networkscited by 138
  2. 2017Online Adaptation of Convolutional Neural Networks for Video Object Segmentationcited by 109
  3. 2018Efficient Video Object Segmentation via Network Modulationcited by 98
  4. 2017Video Object Segmentation Without Temporal Informationcited by 93
  5. 2019RVOS: End-to-End Recurrent Network for Video Object Segmentationcited by 88
  6. 2018PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentationcited by 81
  7. 2017FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videoscited by 77
  8. 2020Learning Fast and Robust Target Models for Video Object Segmentationcited by 76
  9. 2017Learning Video Object Segmentation with Visual Memorycited by 66
  10. 2018A Generative Appearance Model for End-to-end Video Object Segmentationcited by 66
  11. 2020Fast Video Object Segmentation using the Global Context Modulecited by 65
  12. 2019RANet: Ranking Attention Network for Fast Video Object Segmentationcited by 60
  13. 2018Fast and Accurate Online Video Object Segmentation via Tracking Partscited by 57
  14. 2018Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagationcited by 56
  15. 2020A Transductive Approach for Video Object Segmentationcited by 55
  16. 2020State-Aware Tracker for Real-Time Video Object Segmentationcited by 54
  17. 2019Anchor Diffusion for Unsupervised Video Object Segmentationcited by 50
  18. 2019Video Object Segmentation and Tracking: A Surveycited by 49
  19. 2018CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRFcited by 48
  20. 2018MaskRNN: Instance Level Video Object Segmentationcited by 48
  21. 2020Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matchingcited by 37
  22. 2017Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networkscited by 32
  23. 2019DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentationcited by 26
  24. 2019Spatiotemporal CNN for Video Object Segmentationcited by 24
  25. 2020Fast Template Matching and Update for Video Object Tracking and Segmentationcited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 19; 2023: 20; 2024: 13; 2025: 5; 2026: 3.

67 papers.

Sort:

By area:

  1. 2022XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Modelcited by 436
  2. 2021Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentationcited by 200
  3. 2023Putting the Object Back into Video Object Segmentationcited by 182
  4. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  5. 2022LVOS: A Benchmark for Long-term Video Object Segmentationcited by 76
  6. 2023XMem++: Production-level Video Segmentation From Few Annotated Framescited by 53
  7. 2022Recurrent Dynamic Embedding for Video Object Segmentationcited by 52
  8. 2022Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentationcited by 50
  9. 2024LVOS: A Benchmark for Large-scale Long-term Video Object Segmentationcited by 41
  10. 2021Reliable Propagation-Correction Modulation for Video Object Segmentationcited by 36
  11. 2022Learning Quality-aware Dynamic Memory for Video Object Segmentationcited by 35
  12. 2022Look Before You Match: Instance Understanding Matters in Video Object Segmentationcited by 33
38 more
  1. 2022SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximizationcited by 26
  2. 2025MatAnyone: Stable Video Matting with Consistent Memory Propagationcited by 24
  3. 2022Global Spectral Filter Memory Network for Video Object Segmentationcited by 22
  4. 2023Boosting Video Object Segmentation via Space-time Correspondence Learningcited by 21
  5. 2022Region Aware Video Object Segmentation with Deep Motion Modelingcited by 18
  6. 2023PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentationcited by 18
  7. 2023LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignmentcited by 17
  8. 2022Tackling Background Distraction in Video Object Segmentationcited by 16
  9. 2023MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillationcited by 16
  10. 2021TransVOS: Video Object Segmentation with Transformerscited by 15
  11. 2023ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Datacited by 12
  12. 2021Siamese Network with Interactive Transformer for Video Object Segmentationcited by 11
  13. 2021Accelerating Video Object Segmentation with Compressed Videocited by 10
  14. 2024PyramidMamba: Rethinking Pyramid Feature Fusion with Selective Space State Model for Semantic Segmentation of Remote Sensing Imagerycited by 10
  15. 2022Panoramic Video Salient Object Detection with Ambisonic Audio Guidancecited by 9
  16. 2023Co-attention Propagation Network for Zero-Shot Video Object Segmentationcited by 9
  17. 2024Monocular 3D lane detection for Autonomous Driving: Recent Achievements, Challenges, and Outlookscited by 9
  18. 2025Nav-R2 Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigationcited by 8
  19. 2023Two-shot Video Object Segmentationcited by 7
  20. 2024SMITE: Segment Me In TimEcited by 7
  21. 2024LiVOS: Light Video Object Segmentation with Gated Linear Matchingcited by 7
  22. 2022Learning to Learn Better for Video Object Segmentationcited by 6
  23. 2024OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Frameworkcited by 6
  24. 2024FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentationcited by 6
  25. 2023AccDecoder: Accelerated Decoding for Neural-enhanced Video Analyticscited by 5
  26. 2023eWaSR -- an embedded-compute-ready maritime obstacle detection networkcited by 5
  27. 2023Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentationcited by 5
  28. 2023Exploring Cycle Consistency Learning in Interactive Volume Segmentationcited by 4
  29. 2022Variational Distillation for Multi-View Learningcited by 3
  30. 2022Uncertainty in Real-Time Semantic Segmentation on Embedded Systemscited by 3
  31. 2023SpVOS: Efficient Video Object Segmentation with Triple Sparse Convolutioncited by 2
  32. 2023Hierarchical Graph Pattern Understanding for Zero-Shot VOScited by 2
  33. 2025Segment Anything for Video: A Comprehensive Review of Video Object Segmentation and Tracking from Past to Futurecited by 2
  34. 2021Space Time Recurrent Memory Networkcited by 1
  35. 2022TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistencycited by 1
  36. 2023Flow-guided Semi-supervised Video Object Segmentationcited by 1
  37. 2023Hierarchical Spatiotemporal Transformers for Video Object Segmentationcited by 1
  38. 2024Spatial-Temporal Multi-level Association for Video Object Segmentationcited by 1

50 most cited of 67 All 67 (JSON)