About

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Latest papers without code

Learning to Better Segment Objects from Unseen Classes with Unlabeled Videos

25 Apr 2021

Through extensive experiments, we show that our method can generate a high-quality training set which significantly boosts the performance of segmenting objects of unseen classes.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION VIDEO SEGMENTATION VIDEO SEMANTIC SEGMENTATION

Self-supervised Video Object Segmentation by Motion Grouping

15 Apr 2021

We additionally evaluate on a challenging camouflage dataset (MoCA), significantly outperforming the other self-supervised approaches, and comparing favourably to the top supervised approach, highlighting the importance of motion cues, and the potential bias towards visual appearance in existing video segmentation models.

MOTION SEGMENTATION OPTICAL FLOW ESTIMATION SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEGMENTATION VIDEO SEMANTIC SEGMENTATION

Learning Position and Target Consistency for Memory-based Video Object Segmentation

9 Apr 2021

To address this limitation, we propose to Learn position and target Consistency framework for Memory-based video object segmentation, termed as LCM.

SEMANTIC SEGMENTATION VIDEO SEMANTIC SEGMENTATION YOUTUBE-VOS

Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective

31 Mar 2021

To learn generalizable representation for correspondence in large-scale, a variety of self-supervised pretext tasks are proposed to explicitly perform object-level or patch-level similarity learning.

SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION VISUAL OBJECT TRACKING

Fully Automated 2D and 3D Convolutional Neural Networks Pipeline for Video Segmentation and Myocardial Infarction Detection in Echocardiography

26 Mar 2021

Our model is implemented as a pipeline consisting of a 2D CNN that performs data preprocessing by segmenting the LV chamber from the apical four-chamber (A4C) view, followed by a 3D CNN that performs a binary classification to detect if the segmented echocardiography shows signs of MI.

MYOCARDIAL INFARCTION DETECTION VIDEO SEGMENTATION VIDEO SEMANTIC SEGMENTATION

ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation

19 Mar 2021

Text-based video segmentation is a challenging task that segments out the natural language referred objects in videos.

VIDEO SEGMENTATION VIDEO SEMANTIC SEGMENTATION VIDEO UNDERSTANDING

GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video

16 Mar 2021

Moreover, we introduce a guided spatially-varying convolution for fusing segmentations derived from the previous and current frames, to mitigate propagation error and enable lightweight feature extraction on non-keyframes.

SEMANTIC SEGMENTATION VIDEO SEGMENTATION VIDEO SEMANTIC SEGMENTATION

Novel tile segmentation scheme for omnidirectional video

10 Mar 2021

Regular omnidirectional video encoding technics use map projection to flatten a scene from a spherical shape into one or several 2D shapes.

VIDEO SEGMENTATION VIDEO SEMANTIC SEGMENTATION

Fast Interactive Video Object Segmentation with Graph Neural Networks

5 Mar 2021

Interactive video object segmentation aims to utilize automatic methods to speed up the process and reduce the workload of the annotators.

INTERACTIVE VIDEO OBJECT SEGMENTATION SEMANTIC SEGMENTATION VIDEO SEMANTIC SEGMENTATION