mlsanityData to 14 Oct 2026

Object Discovery in Videos as Foreground Motion Clustering

arXiv 1812.02772 ↗First posted 6 Dec 2018cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

We consider the problem of providing dense segmentation masks for object discovery in videos. We formulate the object discovery problem as foreground motion clustering, where the goal is to cluster foreground pixels in videos into different objects. We introduce a novel pixel-trajectory recurrent neural network that learns feature embeddings of foreground pixel trajectories linked across time. By clustering the pixel trajectories using the learned feature embeddings, our method establishes correspondences between foreground object masks across video frames. To demonstrate the effectiveness of our framework for object discovery, we conduct experiments on commonly used datasets for motion segmentation, where we achieve state-of-the-art performance.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 7; 2023: 10; 2024: 3; 2025: 1; 2026: 1.

32 papers.

Sort:

  1. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  2. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 137
  3. 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
  4. 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
  5. 2022Deformable Sprites for Unsupervised Video Decompositioncited by 61
  6. 2021NeuralDiff: Segmenting 3D objects that move in egocentric videoscited by 57
  7. 2021Opening up Open-World Trackingcited by 50
  8. 2023Advances in Deep Concealed Scene Understandingcited by 47
  9. 2021Motion-aware Contrastive Video Representation Learning via Foreground-background Mergingcited by 45
  10. 2022Discovering Objects that Can Movecited by 44
  11. 2024A Survey of Camouflaged Object Detection and Beyondcited by 37
  12. 2021Unsupervised Object Learning via Common Fatecited by 29
20 more
  1. 2022Mean Shift Mask Transformer for Unseen Object Instance Segmentationcited by 19
  2. 2021Unknown Object Segmentation from Stereo Imagescited by 16
  3. 2023Multi-Object Discovery by Low-Dimensional Object Motioncited by 16
  4. 2021RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networkscited by 15
  5. 2022A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentationcited by 15
  6. 2022Motion-inductive Self-supervised Object Discovery in Videoscited by 14
  7. 2021The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memorycited by 13
  8. 2023MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Fieldcited by 12
  9. 2023Appearance-Based Refinement for Object-Centric Motion Segmentationcited by 11
  10. 2023Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentationcited by 10
  11. 2023Event-Free Moving Object Segmentation from Moving Ego Vehiclecited by 8
  12. 2023DEVIAS: Learning Disentangled Video Representations of Action and Scenecited by 7
  13. 2023Online Unsupervised Video Object Segmentation via Contrastive Motion Clusteringcited by 6
  14. 2024On Moving Object Segmentation from Monocular Video with Transformerscited by 6
  15. 2021A topological solution to object segmentation and trackingcited by 4
  16. 2021RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditionscited by 2
  17. 2024MOD-UV: Learning Mobile Object Detectors from Unlabeled Videoscited by 2
  18. 2023Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentationcited by 1
  19. 2025Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videoscited by 0
  20. 2026MotionBits: Video Segmentation through Motion-Level Analysis of Rigid Bodiescited by 0