SOTAVerified

Unsupervised Video Object Segmentation

The unsupervised scenario assumes that the user does not interact with the algorithm to obtain the segmentation masks. Methods should provide a set of object candidates with no overlapping pixels that span through the whole video sequence. This set of objects should contain at least the objects that capture human attention when watching the whole video sequence i.e objects that are more likely to be followed by human gaze.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–89 of 89 papers

TitleStatusHype
Extending Layered Models to 3D MotionCode0
Unsupervised Video Object Segmentation for Deep Reinforcement LearningCode0
Adversarial Framework for Unsupervised Learning of Motion Dynamics in Videos—0
Instance Embedding Transfer to Unsupervised Video Object Segmentation—0
Learning to Segment Moving Objects—0
SegFlow: Joint Learning for Video Object Segmentation and Optical FlowCode0
Primary Object Segmentation in Videos Based on Region Augmentation and Reduction—0
Learning Video Object Segmentation with Visual Memory—0
Video Object Segmentation using Supervoxel-Based GerrymanderingCode0
FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos—0
Learning Motion Patterns in Videos—0
Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions—0
Motion Trajectory Segmentation via Minimum Cost Multicuts—0
Causal Video Object Segmentation From Persistence of Occlusions—0
Show:102550
← PrevPage 4 of 4Next →

No leaderboard results yet.