DAVIS: Densely Annotated VIdeo Segmentation 2016
DAVIS (Densely Annotated VIdeo Segmentation 2016) is a public dataset specifically designed for the task of video object segmentation.
DAVIS 2016 dataset consists of fifty high quality, full HD video sequences, spanning multiple occurrences of common video object segmentation challenges such as occlusions, motion-blur and appearance changes. Each video is accompanied by densely annotated, pixel-accurate and per-frame ground truth segmentation. In this dataset the segmented object is defined as the main object in the scene with a distinctive motion.
- F. Perazzi, J. Pont-Tuset, B. McWilliams, L. Van Gool, M. Gross, and A. Sorkine-Hornung, "A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016.