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 1–50 of 89 papers

TitleStatusHype
Saliency-Motion Guided Trunk-Collateral Network for Unsupervised Video Object Segmentation—0
Learning Motion and Temporal Cues for Unsupervised Video Object SegmentationCode1
Improving Unsupervised Video Object Segmentation via Fake Flow Generation—0
Self-supervised Video Object Segmentation with Distillation Learning of Deformable Attention—0
SimulFlow: Simultaneously Extracting Feature and Identifying Target for Unsupervised Video Object Segmentation—0
Treating Motion as Option with Output Selection for Unsupervised Video Object SegmentationCode1
Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation—0
Tracking Anything with Decoupled Video SegmentationCode3
Online Unsupervised Video Object Segmentation via Contrastive Motion ClusteringCode0
UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything ModelCode1
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual GroupingCode1
Adaptive Multi-source Predictor for Zero-shot Video Object SegmentationCode1
Guided Slot Attention for Unsupervised Video Object SegmentationCode1
Tsanet: Temporal and Scale Alignment for Unsupervised Video Object Segmentation—0
Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation—0
Flow-guided Semi-supervised Video Object Segmentation—0
Unsupervised Video Object Segmentation with Online Adversarial Self-Tuning—0
Improving Unsupervised Video Object Segmentation with Motion-Appearance Synergy—0
Dual Prototype Attention for Unsupervised Video Object SegmentationCode1
Efficient Unsupervised Video Object Segmentation Network Based on Motion Guidance—0
A Simple and Powerful Global Optimization for Unsupervised Video Object SegmentationCode1
Unsupervised Video Object Segmentation via Prototype Memory NetworkCode1
Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object SegmentationCode1
TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut—0
Hierarchical Feature Alignment Network for Unsupervised Video Object SegmentationCode1
Implicit Motion-Compensated Network for Unsupervised Video Object SegmentationCode0
In-N-Out Generative Learning for Dense Unsupervised Video SegmentationCode1
Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier—0
Autoencoder-based background reconstruction and foreground segmentation with background noise estimationCode1
Learning To Segment Dominant Object Motion From Watching Videos—0
D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in VideosCode1
D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in VideosCode1
Dense Unsupervised Learning for Video SegmentationCode1
Video Salient Object Detection via Contrastive Features and Attention Modules—0
Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object SegmentationCode1
Full-Duplex Strategy for Video Object SegmentationCode1
Reciprocal Transformations for Unsupervised Video Object SegmentationCode1
Video Instance Segmentation with a Propose-Reduce ParadigmCode1
Mask Selection and Propagation for Unsupervised Video Object SegmentationCode0
Deep Transport Network for Unsupervised Video Object Segmentation—0
Learning Motion-Appearance Co-Attention for Zero-Shot Video Object SegmentationCode1
F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation—0
Making a Case for 3D Convolutions for Object Segmentation in VideosCode1
MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object SegmentationCode1
DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping—0
Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation—0
Unsupervised Video Object Segmentation with Joint Hotspot Tracking—0
ALBA : Reinforcement Learning for Video Object SegmentationCode0
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in VideosCode1
Learning Video Object Segmentation from Unlabeled VideosCode1
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.