UVO

홈페이지 · 논문 27편

UVO is a new benchmark for open-world class-agnostic object segmentation in videos. Besides shifting the problem focus to the open-world setup, UVO is significantly larger, providing approximately 8 times more videos compared with [DAVIS](/dataset/davis), and 7 times more mask (instance) annotations per video compared with [YouTube-VOS](/dataset/youtube-vos) and [YouTube-VIS](/dataset/youtubevis). UVO is also more challenging as it includes many videos with crowded scenes and complex background motions. Some highlights of the dataset include: - High quality instance masks densely annotated at 30 fps on 1024 YouTube videos and 1fps on 10337 videos from Kinetics dataset - Open-world: annotating all objects in each video, 13.5 objects per video on average - Diverse object categories: 57% of objects are not covered by COCO categories

벤치마크