Semi-Supervised Video Object Segmentation
94 papers with code • 15 benchmarks • 13 datasets
The semi-supervised scenario assumes the user inputs a full mask of the object(s) of interest in the first frame of a video sequence. Methods have to produce the segmentation mask for that object(s) in the subsequent frames.
Benchmarks
These leaderboards are used to track progress in Semi-Supervised Video Object Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Semi-Supervised Video Object Segmentation models and implementationsDatasets
DAVIS
DAVIS 2017
DAVIS 2016
YouTube-VOS 2018
Referring Expressions for DAVIS 2016 & 2017
VOTChallenge
MOSE
BURST
BL30K
VOT2020
Most implemented papers
One-Shot Video Object Segmentation
kmaninis/OSVOS-PyTorch
•
•
CVPR 2017
This paper tackles the task of semi-supervised video object segmentation, i. e., the separation of an object from the background in a video, given the mask of the first frame.
PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation
We address semi-supervised video object segmentation, the task of automatically generating accurate and consistent pixel masks for objects in a video sequence, given the first-frame ground truth annotations.
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
hkchengrex/MiVOS
•
•
CVPR 2021
We present Modular interactive VOS (MiVOS) framework which decouples interaction-to-mask and mask propagation, allowing for higher generalizability and better performance.
Lucid Data Dreaming for Video Object Segmentation
Our approach is suitable for both single and multiple object segmentation.
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
BehradToghi/ECCV_Youtube_VOS
•
•
ECCV 2018
End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i. e., even the largest video segmentation dataset only contains 90 short video clips.
Make One-Shot Video Object Segmentation Efficient Again
dvl-tum/e-osvos
•
•
NeurIPS 2020
In the semi-supervised setting, the first mask of each object is provided at test time.
Fast Online Object Tracking and Segmentation: A Unifying Approach
foolwood/SiamMask
•
•
CVPR 2019
In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach.
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
tensorflow/models
•
•
CVPR 2019
Many of the recent successful methods for video object segmentation (VOS) are overly complicated, heavily rely on fine-tuning on the first frame, and/or are slow, and are hence of limited practical use.
Video Object Segmentation using Space-Time Memory Networks
In our framework, the past frames with object masks form an external memory, and the current frame as the query is segmented using the mask information in the memory.
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
hkchengrex/STCN
•
•
NeurIPS 2021
This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation.
