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
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
YouTube-VIS 2021
|
DVIS++
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
