mlsanityData to 7 Oct 2026

The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation

arXiv 1905.00737 ↗First posted 2 May 2019cs.CVcited by 95

Not on the map. Why?

Abstract (arXiv)

We present the 2019 DAVIS Challenge on Video Object Segmentation, the third edition of the DAVIS Challenge series, a public competition designed for the task of Video Object Segmentation (VOS). In addition to the original semi-supervised track and the interactive track introduced in the previous edition, a new unsupervised multi-object track will be featured this year. In the newly introduced track, participants are asked to provide non-overlapping object proposals on each image, along with an identifier linking them between frames (i.e. video object proposals), without any test-time human supervision (no scribbles or masks provided on the test video). In order to do so, we have re-annotated the train and val sets of DAVIS 2017 in a concise way that facilitates the unsupervised track, and created new test-dev and test-challenge sets for the competition. Definitions, rules, and evaluation metrics for the unsupervised track are described in detail in this paper.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 11; 2023: 19; 2024: 17; 2025: 20; 2026: 10.

95 papers.

Sort:

By area:

  1. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  2. 2021Conditional Object-Centric Learning from Videocited by 247
  3. 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 232
  4. 2023Tracking Anything with Decoupled Video Segmentationcited by 197
  5. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 165
  6. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  7. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistencycited by 143
  8. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  9. 2021Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusioncited by 129
  10. 2023TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environmentscited by 89
  11. 2024Streaming Dense Video Captioningcited by 82
  12. 2023Segment Anything Meets Point Trackingcited by 81
38 more
  1. 2021Full-Duplex Strategy for Video Object Segmentationcited by 78
  2. 2021Video Instance Segmentation with a Propose-Reduce Paradigmcited by 74
  3. 2021The Multi-Temporal Urban Development SpaceNet Datasetcited by 62
  4. 2024OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitationcited by 62
  5. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 59
  6. 2022Temporally Efficient Vision Transformer for Video Instance Segmentationcited by 55
  7. 2021Opening up Open-World Trackingcited by 50
  8. 2025SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generationcited by 44
  9. 2024LVOS: A Benchmark for Large-scale Long-term Video Object Segmentationcited by 41
  10. 2024LeviTor: 3D Trajectory Oriented Image-to-Video Synthesiscited by 39
  11. 2024Generative Omnimatte: Learning to Decompose Video into Layerscited by 38
  12. 2022Efficient Video Instance Segmentation via Tracklet Query and Proposalcited by 33
  13. 2023Rethinking Optical Flow from Geometric Matching Consistent Perspectivecited by 33
  14. 2025FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editingcited by 31
  15. 2025NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priorscited by 25
  16. 2022RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videoscited by 22
  17. 2021Video Class Agnostic Segmentation Benchmark for Autonomous Drivingcited by 21
  18. 2021Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentationcited by 21
  19. 2021D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videoscited by 20
  20. 2023Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videoscited by 20
  21. 2021BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtractioncited by 15
  22. 2023Semi-Supervised Visual Tracking of Marine Animals using Autonomous Underwater Vehiclescited by 15
  23. 2023Semantic Attention Flow Fields for Monocular Dynamic Scene Decompositioncited by 12
  24. 2023Learning from One Continuous Video Streamcited by 11
  25. 2023Appearance-Based Refinement for Object-Centric Motion Segmentationcited by 11
  26. 2021The SpaceNet Multi-Temporal Urban Development Challengecited by 10
  27. 2023SANPO: A Scene Understanding, Accessibility and Human Navigation Datasetcited by 10
  28. 2023Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenescited by 9
  29. 2023Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volumecited by 9
  30. 2026PISCO: Precise Video Instance Insertion with Sparse Controlcited by 9
  31. 2023Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videoscited by 8
  32. 2024Rethinking Image-to-Video Adaptation: An Object-centric Perspectivecited by 8
  33. 2024TRASE: Tracking-free 4D Segmentation and Editingcited by 8
  34. 2024X-Prompt: Multi-modal Visual Prompt for Video Object Segmentationcited by 7
  35. 2025O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Viewscited by 7
  36. 2021MSN: Efficient Online Mask Selection Network for Video Instance Segmentationcited by 6
  37. 2021Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challengecited by 6
  38. 2024Hybrid Cost Volume for Memory-Efficient Optical Flowcited by 6

50 most cited of 95 All 95 (JSON)