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

arXiv: https://arxiv.org/abs/1905.00737 · HTML: https://mlsanity.com/paper/1905.00737/

## Key facts

- Cited by 97 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2019.

## Built on by (most cited first, 30 of 97)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [Tracking Anything with Decoupled Video Segmentation](https://mlsanity.com/paper/2309.03903/) (2023)
- [SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos](https://mlsanity.com/paper/2206.07764/) (2022)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency](https://mlsanity.com/paper/2407.17470/) (2024)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion](https://mlsanity.com/paper/2103.07941/) (2021)
- [TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments](https://mlsanity.com/paper/2306.02850/) (2023)
- [Streaming Dense Video Captioning](https://mlsanity.com/paper/2404.01297/) (2024)
- [Segment Anything Meets Point Tracking](https://mlsanity.com/paper/2307.01197/) (2023)
- [Full-Duplex Strategy for Video Object Segmentation](https://mlsanity.com/paper/2108.03151/) (2021)
- [Video Instance Segmentation with a Propose-Reduce Paradigm](https://mlsanity.com/paper/2103.13746/) (2021)
- [OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation](https://mlsanity.com/paper/2410.11792/) (2024)
- [The Multi-Temporal Urban Development SpaceNet Dataset](https://mlsanity.com/paper/2102.04420/) (2021)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [Temporally Efficient Vision Transformer for Video Instance Segmentation](https://mlsanity.com/paper/2204.08412/) (2022)
- [Opening up Open-World Tracking](https://mlsanity.com/paper/2104.11221/) (2021)
- [SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation](https://mlsanity.com/paper/2503.16396/) (2025)
- [LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation](https://mlsanity.com/paper/2404.19326/) (2024)
- [LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis](https://mlsanity.com/paper/2412.15214/) (2024)
- [Generative Omnimatte: Learning to Decompose Video into Layers](https://mlsanity.com/paper/2411.16683/) (2024)
- [Efficient Video Instance Segmentation via Tracklet Query and Proposal](https://mlsanity.com/paper/2203.01853/) (2022)
- [Rethinking Optical Flow from Geometric Matching Consistent Perspective](https://mlsanity.com/paper/2303.08384/) (2023)
- [FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing](https://mlsanity.com/paper/2505.23145/) (2025)
- [NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors](https://mlsanity.com/paper/2504.11427/) (2025)
- [Video Class Agnostic Segmentation Benchmark for Autonomous Driving](https://mlsanity.com/paper/2103.11015/) (2021)
- [RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos](https://mlsanity.com/paper/2207.11075/) (2022)
- [Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation](https://mlsanity.com/paper/2104.04782/) (2021)

## 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.