-
Hybrid-S2S: Video Object Segmentation with Recurrent Networks and Corresponde...
One-shot Video Object Segmentation (VOS) is the task of pixel-wise tracking an object of interest within a video sequence, where the segmentation mask of the first frame is given... -
Occluded Video Instance Segmentation (OVIS)
Occluded Video Instance Segmentation (OVIS) is a benchmark for evaluating video object segmentation models in occluded scenes. -
The 2017 Davis Challenge on Video Object Segmentation
The 2017 Davis Challenge on Video Object Segmentation is a benchmark for evaluating video object segmentation models. -
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
MOSE is a new dataset for video object segmentation in complex scenes. It contains 2149 videos, out of which only 1507 come with available ground-truth masks. -
Learning the What and How of Annotation in Video Object Segmentation
Video object segmentation is crucial for several applications, from video editing to video data generation. Training a VOS model requires an abundance of manually labeled... -
YouTube-VOS 2018 and 2019
YouTube-VOS 2018 and 2019 datasets are benchmarks for video object segmentation, featuring various challenging scenarios. -
DAVIS 2016 and 2017
DAVIS 2016 and 2017 datasets are benchmarks for video object segmentation, featuring various challenging scenarios. -
Youtube-VOS
The Youtube-VOS dataset is a large-scale benchmark for multi-object video object segmentation, containing 120 videos with dense annotation. -
Regional Memory Network for Video Object Segmentation
The proposed Regional Memory Network (RMNet) for semi-supervised video object segmentation.
