Given the segmentation mask of the first frame of a video clip, predict the segmentation masks in the subsequent frames.
Davis challenge https://davischallenge.org/ held since 2017, related papers [1] [2]
YouTube-VOS: A Large-Scale Benchmark for Video Object Segmentation https://youtube-vos.org/home
GyGO: an E-commerce Video Object Segmentation Dataset by Visualead https://github.com/ilchemla/gygo-dataset
Reference:
Perazzi, Federico, et al. “A benchmark dataset and evaluation methodology for video object segmentation.” CVPR, 2016.
Pont-Tuset, Jordi, et al. “The 2017 davis challenge on video object segmentation.” arXiv preprint arXiv:1704.00675 (2017).