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

Abstract

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.

CVPR 2019 Workshop/Challenge

References in corpus (1)

• A Detailed Rubric for Motion Segmentation

Cited by in corpus (9)

• Anchor Diffusion for Unsupervised Video Object Segmentation
• ALBA : Reinforcement Learning for Video Object Segmentation
• Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
• High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling
• Coverless Video Steganography based on Maximum DC Coefficients
• MSN: Efficient Online Mask Selection Network for Video Instance Segmentation
• A Unified Framework for Shot Type Classification Based on Subject Centric Lens
• Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation
• Detecting Biological Locomotion in Video: A Computational Approach