paper-with-me

MeViS

Motion expressions Video Segmentation

홈페이지 · 논문 46편

MeViS is a large-scale dataset for motion expressions guided video segmentation, which focuses on segmenting objects in video content based on a sentence describing the motion of the objects. The dataset contains numerous motion expressions to indicate target objects in complex environments.

벤치마크

Referring Video Object Segmentation on MeViS 결과 33개