Browse SoTA > Computer Vision > Video > Video Object Segmentation

Video Object Segmentation

66 papers with code ยท Computer Vision
Subtask of Video

Video object segmentation is a binary labeling problem aiming to separate foreground object(s) from the background region of a video.

For leaderboards please refer to the different subtasks.

Benchmarks

Latest papers without code

DAER to Reject Seeds with Dual-loss Additional Error Regression

16 Sep 2020

With these challenges in mind, we propose a novel training method and evaluation metrics for the seed rejection problem.

SCENE CLASSIFICATION SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION VIEWPOINT ESTIMATION

ScribbleBox: Interactive Annotation Framework for Video Object Segmentation

ECCV 2020

Our approach tolerates a modest amount of noise in the box placements, thus typically only a few clicks are needed to annotate tracked boxes to a sufficient accuracy.

SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION

Time-Supervised Primary Object Segmentation

16 Aug 2020

As the volume of our training sets grows, more and more objects are seen moving, thus turning our method into unsupervised (or time-supervised) training to segment primary objects.

RGB SALIENT OBJECT DETECTION SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION

Curriculum Learning for Recurrent Video Object Segmentation

15 Aug 2020

Video object segmentation can be understood as a sequence-to-sequence task that can benefit from the curriculum learning strategies for better and faster training of deep neural networks.

CURRICULUM LEARNING SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION

Self-supervised Object Tracking with Cycle-consistent Siamese Networks

3 Aug 2020

Self-supervised learning for visual object tracking possesses valuable advantages compared to supervised learning, such as the non-necessity of laborious human annotations and online training.

REGION PROPOSAL SELF-SUPERVISED LEARNING SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION VISUAL OBJECT TRACKING

Kernelized Memory Network for Video Object Segmentation

ECCV 2020

Unlike in previous works, we use the Hide-and-Seek strategy in pre-training to obtain the best possible results in handling occlusions and segment boundary extraction.

SEMANTIC SEGMENTATION SEMI-SUPERVISED VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION

Motion Prediction in Visual Object Tracking

1 Jul 2020

Although our baseline system is a straightforward combination of standard methods, we obtain state-of-the-art results.

AUTONOMOUS DRIVING MOTION PREDICTION SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION VISUAL OBJECT TRACKING

Self-supervised Video Object Segmentation

22 Jun 2020

The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a. k. a.

REPRESENTATION LEARNING SEMANTIC SEGMENTATION VIDEO SEMANTIC SEGMENTATION YOUTUBE-VOS