YouTube VOS

Study / ResearchMentioned in 1 video

A dataset for video object segmentation, containing 94 object categories, which is considered small by Nikhila compared to the scale of Sam's data.

Videos Mentioning YouTube VOS

Segment Anything 2: Memory + Vision = Object Permanence — with Nikhila Ravi and Joseph Nelson

Segment Anything 2: Memory + Vision = Object Permanence — with Nikhila Ravi and Joseph Nelson

Latent Space

A dataset for video object segmentation, containing 94 object categories, which is considered small by Nikhila compared to the scale of Sam's data.