OVIS

홈페이지 · 논문 75편

OVIS is a new large scale benchmark dataset for video instance segmentation task. It is designed with the philosophy of perceiving object occlusions in videos, which could reveal the complexity and the diversity of real-world scenes. OVIS consists of: * 296k high-quality instance masks * 25 commonly seen semantic categories * 901 videos with severe object occlusions * 5,223 unique instances If the description or image is from a different paper, please refer to it as follows: Source: http://songbai.site/ovis/

벤치마크