mlsanityData to 7 Oct 2026

Unsupervised Moving Object Detection via Contextual Information Separation

arXiv 1901.03360 ↗First posted 10 Jan 2019cs.CVcited by 72

Not on the map. Why?

Abstract (arXiv)

We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another network attempts to make such context as uninformative as possible. The result is a model where hypotheses naturally compete with no need for explicit regularization or hyper-parameter tuning. Although our method requires no supervision whatsoever, it outperforms several methods that are pre-trained on large annotated datasets. Our model can be thought of as a generalization of classical variational generative region-based segmentation, but in a way that avoids explicit regularization or solution of partial differential equations at run-time.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 22; 2023: 20; 2024: 5; 2025: 8; 2026: 5.

72 papers.

Sort:

By area:

  1. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  2. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  3. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  4. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  5. 2022TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cutcited by 111
  6. 2022ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wildcited by 90
  7. 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71
  8. 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
  9. 2022Deformable Sprites for Unsupervised Video Decompositioncited by 61
  10. 2022Breaking the "Object" in Video Object Segmentationcited by 48
  11. 2021The Emergence of Objectness: Learning Zero-Shot Segmentation from Videoscited by 45
  12. 2022Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motioncited by 42
38 more
  1. 2023VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentationcited by 36
  2. 2025Segment Any Motion in Videoscited by 34
  3. 2022EM-driven unsupervised learning for efficient motion segmentationcited by 33
  4. 2021Unsupervised Object Learning via Common Fatecited by 29
  5. 2021Unsupervised Foreground Extraction via Deep Region Competitioncited by 26
  6. 2022OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Cloudscited by 24
  7. 2021Learning Representational Invariances for Data-Efficient Action Recognitioncited by 22
  8. 2022Unsupervised Multi-View Object Segmentation Using Radiance Field Propagationcited by 22
  9. 2021Learning Semantic-Aware Dynamics for Video Predictioncited by 21
  10. 2022FUN-SIS: a Fully UNsupervised approach for Surgical Instrument Segmentationcited by 20
  11. 2022MOVE: Unsupervised Movable Object Segmentation and Detectioncited by 20
  12. 2023Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videoscited by 20
  13. 2021GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generationcited by 19
  14. 2022Unsupervised Multi-object Segmentation by Predicting Probable Motion Patternscited by 19
  15. 2022AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypointscited by 17
  16. 2023Multi-Object Discovery by Low-Dimensional Object Motioncited by 16
  17. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  18. 2022A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentationcited by 15
  19. 2023Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Groupingcited by 15
  20. 2022Motion-inductive Self-supervised Object Discovery in Videoscited by 14
  21. 2023UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Modelcited by 14
  22. 2025Learning segmentation from point trajectoriescited by 14
  23. 2024DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentationcited by 13
  24. 2021Flow-Guided Video Inpainting with Scene Templatescited by 12
  25. 2023Appearance-Based Refinement for Object-Centric Motion Segmentationcited by 11
  26. 2023JacobiNeRF: NeRF Shaping with Mutual Information Gradientscited by 10
  27. 2023Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentationcited by 10
  28. 2022The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fieldscited by 8
  29. 2023Event-Free Moving Object Segmentation from Moving Ego Vehiclecited by 8
  30. 2023LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-trainingcited by 8
  31. 2022In-N-Out Generative Learning for Dense Unsupervised Video Segmentationcited by 7
  32. 2023PaintSeg: Training-free Segmentation via Paintingcited by 7
  33. 2023Un-EVIMO: Unsupervised Event-Based Independent Motion Segmentationcited by 7
  34. 2023Online Unsupervised Video Object Segmentation via Contrastive Motion Clusteringcited by 6
  35. 2024On Moving Object Segmentation from Monocular Video with Transformerscited by 6
  36. 2023Dynamic Object Removal for Effective Slamcited by 3
  37. 2023FODVid: Flow-guided Object Discovery in Videoscited by 3
  38. 2023Segmenting the motion components of a video: A long-term unsupervised modelcited by 2

50 most cited of 72 All 72 (JSON)