Unsupervised Video Object Segmentation
51 papers with code • 6 benchmarks • 8 datasets
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.
Benchmarks
These leaderboards are used to track progress in Unsupervised Video Object Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
DAVIS 2017
DAVIS 2016
FBMS
SegTrack-v2
Referring Expressions for DAVIS 2016 & 2017
MOSE
FBMS-59
BL30K
Most implemented papers
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
Kinpzz/RCRNet-Pytorch
•
•
ICCV 2019
Specifically, we present an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module.
Anchor Diffusion for Unsupervised Video Object Segmentation
yz93/anchor-diff-VOS
•
•
ICCV 2019
Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow.
UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
UnOVOST even performs competitively with many semi-supervised video object segmentation algorithms even though it is not given any input as to which objects should be tracked and segmented.
Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
Through parametric message passing, AGNN is able to efficiently capture and mine much richer and higher-order relations between video frames, thus enabling a more complete understanding of video content and more accurate foreground estimation.
See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks
carrierlxk/COSNet
•
•
CVPR 2019
We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view.
Motion-Attentive Transition for Zero-Shot Video Object Segmentation
tfzhou/MATNet
•
•
In this paper, we present a novel Motion-Attentive Transition Network (MATNet) for zero-shot video object segmentation, which provides a new way of leveraging motion information to reinforce spatio-temporal object representation.
Learning Video Object Segmentation from Unlabeled Videos
We propose a new method for video object segmentation (VOS) that addresses object pattern learning from unlabeled videos, unlike most existing methods which rely heavily on extensive annotated data.
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
sabarim/STEm-Seg
•
•
ECCV 2020
In this paper, we propose a different approach that is well-suited to a variety of tasks involving instance segmentation in videos.
ALBA : Reinforcement Learning for Video Object Segmentation
kini5gowda/ALBA-RL-for-VOS
•
•
We treat this as a grouping problem by exploiting object proposals and making a joint inference about grouping over both space and time.
MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation
tfzhou/MATNet
•
•
IEEE Transactions on Image Processing 2020
To further demonstrate the generalization ability of our spatiotemporal learning framework, we extend MATNet to another relevant task: dynamic visual attention prediction (DVAP).
