YouTube-VIS 2021 (Video Instance Segmentation on YouTube-VIS 2021 validation)

Introduced by Yang et al. in Video Instance Segmentation

3,859 high-resolution YouTube videos, 2,985 training videos, 421 validation videos and 453 test videos. An improved 40-category label set by merging eagle and owl into bird, ape into monkey, deleting hands, and adding flying disc, squirrel and whale 8,171 unique video instances 232k high-quality manual annotations


Paper Code Results Date Stars

Dataset Loaders

No data loaders found. You can submit your data loader here.


Similar Datasets