4 datasets found

A benchmark dataset and evaluation methodology for video object segmentation.

Ref-DAVIS17 is an extension of the DAVIS17 dataset, where it enhances the dataset by providing language descriptions for each specific object present in the videos.

Referring video object segmentation (RVOS) aims to accurately segment the target object in the video with the guidance of given language expressions.

Ref-Youtube-VOS is an extensive referring video object segmentation dataset that comprises approximately 15,000 referring expressions associated with more than 3,900 videos.