Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Structure and multipartite genome architecture of the mitochondrial genome in the endangered medicinal plant <i>Fritillaria taipaiensis</i> P. Y. Li.

Frontiers in systems biology·2026

Same author

Analysis of the correlation between the serum residual cholesterol level at admission and the risk of death after discharge in patients with ischemic stroke.

Journal of medical biochemistry·2026

Same author

Association between health literacy and chronic diseases in Anhui Province: findings from a province-wide cross-sectional survey of 16,067 individuals.

Scientific reports·2025

Same author

Association of <i>Helicobacter pylori</i> Infection With Lipid Metabolism, Inflammatory Markers, and Modified Framingham Stroke Risk Score in Patients at High-Risk of Ischemic Stroke: A Retrospective Study.

British journal of hospital medicine (London, England : 2005)·2025

Same author

Comparative analysis of mitochondrial genomes of <i>Epimedium</i> L. reveals heterogeneity in structure, synteny, intercellular gene transfer, and RNA editing.

Frontiers in plant science·2025

Same author

Study on Sulfate Migration Behavior of Potassium Magnesium Phosphate Cement Slurry Based on Electro-Pulse-Accelerated Corrosion.

Materials (Basel, Switzerland)·2025

Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026

Same journal

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 17, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Directional Deep Embedding and Appearance Learning for Fast Video Object Segmentation.

Yingjie Yin, De Xu, Xingang Wang

IEEE Transactions on Neural Networks and Learning Systems

|February 15, 2021

Summary

This summary is machine-generated.

We introduce a fast video object segmentation (VOS) method called DDEAL that avoids slow online fine-tuning. This approach achieves state-of-the-art results on benchmark datasets while maintaining high processing speeds.

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Related Experiment Videos

Last Updated: Nov 17, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Semisupervised video object segmentation (VOS) typically requires time-consuming online fine-tuning of deep neural networks.
This online fine-tuning limits the practical application of existing VOS methods.

Purpose of the Study:

To develop a fast and effective VOS method that eliminates the need for online fine-tuning.
To improve the efficiency and applicability of VOS techniques in real-world scenarios.

Main Methods:

Proposed a directional deep embedding and appearance learning (DDEAL) method for fast VOS.
Introduced a global directional matching module (GDMM) for semantic pixel-wise embedding.
Developed a directional appearance model using spherical embedding space statistics for target and background representation.

Main Results:

DDEAL achieves state-of-the-art VOS performance without online fine-tuning.
Achieved a J & F mean score of 74.8% on the DAVIS 2017 dataset.
Reached an overall score G of 71.3% on the YouTube-VOS dataset at 25 fps.
A faster version achieved 31 fps with minimal accuracy loss.

Conclusions:

DDEAL offers a significant advancement in VOS by providing high accuracy and speed.
The method demonstrates the potential for efficient and practical VOS applications.
Eliminating online fine-tuning is a viable strategy for accelerating VOS methods.