MOSE
Complex Video Object Segmentation
VideosIntroduced 2023-02-03
CoMplex video Object SEgmentation (MOSE) is a dataset to study the tracking and segmenting objects in complex environments. MOSE contains 2,149 video clips and 5,200 objects from 36 categories, with 431,725 high-quality object segmentation masks. The most notable feature of MOSE dataset is complex scenes with crowded and occluded objects.
Source: MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
Benchmarks
Semi-Supervised Video Object Segmentation/J&FSemi-Supervised Video Object Segmentation/JSemi-Supervised Video Object Segmentation/FSemi-Supervised Video Object Segmentation/FPSVideo/J&FVideo/JVideo/FVideo/FPSVideo Object Segmentation/J&FVideo Object Segmentation/JVideo Object Segmentation/FVideo Object Segmentation/FPS