Densely Annotated VIdeo Segmentation
The Densely Annotation Video Segmentation dataset (DAVIS) is a high quality and high resolution densely annotated video segmentation dataset under two resolutions, 480p and 1080p. There are 50 video sequences with 3455 densely annotated frames in pixel level. 30 videos with 2079 frames are for training and 20 videos with 1376 frames are for validation.
Source: TENet: Triple Excitation Network for Video Salient Object Detection
Variants: DAVIS (no YouTube-VOS training), DAVIS sigma50, DAVIS sigma40, DAVIS sigma30, DAVIS sigma20, DAVIS sigma10, DAVIS 2017, DAVIS
This dataset is used in 4 benchmarks:
Recent papers with results on this dataset: