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: Apr 23, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

1.3K

Object recognition with hierarchical discriminant saliency networks.

Sunhyoung Han1, Nuno Vasconcelos2

  • 1Analytics Department, ID Analytics San Diego, CA, USA.

Frontiers in Computational Neuroscience
|September 25, 2014
PubMed
Summary
This summary is machine-generated.

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

Rapid Artificial Intelligence Autoplanning Rivals Manual Expert Planning for Cervical Brachytherapy.

Practical radiation oncology·2026
Same author

Macula Spatial Patterns and Their Association With Central Visual Field Progression in Glaucoma Using Artificial Intelligence.

Journal of glaucoma·2026
Same author

Integration of single-click, AI-based brachytherapy auto-planning for cervical cancer within a treatment planning system.

Brachytherapy·2025
Same author

Deep Learning Estimation of 24-2 Visual Field Map From Optic Nerve Head Optical Coherence Tomography Angiography.

Journal of glaucoma·2025
Same author

Neural network dose prediction for cervical brachytherapy: Overcoming data scarcity for applicator-specific models.

Medical physics·2024
Same author

Deep Learning Estimation of 10-2 Visual Field Map Based on Macular Optical Coherence Tomography Angiography Measurements.

American journal of ophthalmology·2023

Integrating attention and object recognition offers significant benefits. The hierarchical discriminant saliency network (HDSN) demonstrates that attention is integral to recognition, enhancing feature detection and class selectivity.

Area of Science:

  • Computational Neuroscience
  • Computer Vision
  • Artificial Intelligence

Background:

  • Attention is often viewed as a pre-processing step for object recognition.
  • The intrinsic relationship between attention and recognition requires further investigation.
  • Existing models may not fully capture the synergistic benefits of their integration.

Purpose of the Study:

  • To investigate the hypothesis that attention and object recognition are intrinsically linked.
  • To introduce and evaluate a novel network model that integrates attention and recognition.
  • To demonstrate the functional enhancements of this integrated approach.

Main Methods:

  • Developed the hierarchical discriminant saliency network (HDSN) with top-down saliency detection layers.
Keywords:
discriminant saliencyhierarchical networkobject detectionobject recognitiontop-down saliency

Related Experiment Videos

Last Updated: Apr 23, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

1.3K
  • Implemented HDSN using biologically plausible (neurophysiological) and convolutional neural network (CNN) architectures.
  • Utilized parametric rectified linear units (ReLUs) for enhanced feature detection and class tuning.

    • Main Results:

    • HDSN demonstrated optimal feature denoising, saliency modulation by feature discriminant power, and detection of feature presence/absence.
    • The network achieved high selectivity and invariance to target object classes through statistical learning.
    • Performance comparisons showed advantages over existing models in saliency and object recognition tasks.

    Conclusions:

    • Integrating attention and object recognition yields substantial benefits for visual processing models.
    • The HDSN architecture effectively combines saliency detection with object recognition capabilities.
    • The findings support a unified view of attention and recognition as interdependent processes.