Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 6, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Random walks on graphs for salient object detection in images.

Viswanath Gopalakrishnan1, Yiqun Hu, Deepu Rajan

  • 1Centre for Multimedia and Network Technology, Nanyang Technological University, Singapore. asdrajan@ntu.edu.sg

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|November 17, 2010
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Wald-Wolfowitz Runs Test I01:17

Wald-Wolfowitz Runs Test I

The Wald-Wolfowitz test, also known as the runs test, is a nonparametric statistical test used to assess the randomness of a sequence of two different types of elements (e.g., positive/negative values, successes/failures). It examines whether the order of the elements in a sequence is random or if there is a pattern or trend present. This nonparametric test applies to any ordered data despite the population and sample data distribution, even if a higher sample size is available.
The test works...

You might also read

Related Articles

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

Sort by
Same author

Dryness Response of the Ocular Surface With Use of Wearable Ventilation for Improving Air Quality and Comfort.

Safety and health at work·2026
Same author

Beta-Glucan modulates monocyte plasticity and differentiation capacity to mitigate DSS-induced colitis.

eLife·2026
Same author

Stress Engineering in the Optimization of Next-Generation Hafnium-Based Ferroelectric Memory.

Nanomaterials (Basel, Switzerland)·2026
Same author

Association between serum total cholesterol levels and Crohn's clinical disease severity: a retrospective cross-sectional study.

Frontiers in medicine·2025
Same author

Unidirectional Ligament Orientation Enables Enhanced Out-of-Plane Mechanical Properties in Anisotropic Nanoporous Gold.

Nanomaterials (Basel, Switzerland)·2025
Same author

A compact time-domain diffuse optical tomography system for cortical neuroimaging.

Imaging neuroscience (Cambridge, Mass.)·2025

This study introduces a novel graph-based approach for salient object detection in images. It utilizes Markov random walks and a "pop-out graph" model for accurate automatic labeling of image regions.

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Salient object detection is crucial for image understanding.
  • Existing methods often struggle with accurately identifying salient regions.
  • Graph-based representations offer a promising avenue for image analysis.

Purpose of the Study:

  • To develop an automatic labeling method for salient object detection.
  • To improve the accuracy of identifying salient and background nodes in images.
  • To introduce a novel
  • pop-out graph
  • model for enhanced saliency representation.

Main Methods:

  • Formulating salient object detection as a graph labeling problem.
  • Employing Markov random walks on complete and sparse graphs to capture global and local image properties.

Related Experiment Videos

Last Updated: Jun 6, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • Utilizing random walk hitting times to identify initial salient and background nodes.
  • Constructing a
  • pop-out graph
  • model based on labeled nodes.
  • Applying semi-supervised learning to label remaining nodes by optimizing a smoothness objective.

    • Main Results:

    • Successfully identified salient and background nodes using a combination of global and local image features.
    • The
    • pop-out graph
    • model demonstrated improved saliency representation.
    • Semi-supervised learning effectively labeled unlabeled nodes based on the new graph model and constraints.

    Conclusions:

    • The proposed graph-based approach offers an effective method for salient object detection.
    • The integration of Markov random walks and the
    • pop-out graph
    • model enhances detection accuracy.
    • This technique provides a robust framework for automatic image labeling and object saliency analysis.