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: Jul 9, 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

Frequency-based cross-attention fusion network for RGB-D salient object detection.

Xin Zhou1, Wenyao Ji2

  • 1Western University, London, Ontario, N6A 5B9, Canada.

Neural Networks : the Official Journal of the International Neural Network Society
|July 7, 2026
PubMed
Summary

Related Concept Videos

Association Areas of the Cortex01:21

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...

You might also read

Related Articles

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

Sort by
Same author

Thyroid Hormone Signaling Is Required for Dynamic Variation in Opsins in the Retina during Metamorphosis of the Japanese Flounder (<i>Paralichthys olivaceus</i>).

Biology·2023
Same author

Biomass and its allocation in relation to temperature, precipitation, and soil nutrients in Inner Mongolia grasslands, China.

PloS one·2013
Same author

[Use of zebrafish models for the research of traditional Chinese medicine].

Zhong xi yi jie he xue bao = Journal of Chinese integrative medicine·2012
Same author

Simultaneously sensitive detection of multiple miRNAs based on a strand displacement amplification.

Chemical communications (Cambridge, England)·2012
Same author

Hydrogen peroxide induces overexpression of angiotensin-converting enzyme in human umbilical vein endothelial cells.

Free radical research·2012
Same author

A genetic and pharmacological analysis of isoprenoid pathway by LC-MS/MS in fission yeast.

PloS one·2012

This study introduces a novel Frequency-based Cross-Attention Fusion Network (FCAFNet) for RGB-D salient object detection. FCAFNet enhances cross-modality fusion in the frequency domain, significantly improving detection accuracy and boundary refinement.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Signal Processing

Background:

  • Effective fusion of RGB and depth data is critical for salient object detection.
  • Existing methods primarily focus on spatial domain fusion, neglecting frequency domain integration.

Purpose of the Study:

  • To propose a novel Frequency-based Cross-Attention Fusion Network (FCAFNet) for RGB-D salient object detection.
  • To explore frequency domain fusion for improved cross-modality information integration.

Main Methods:

  • Implemented a Frequency-based element-product Cross-Attention Module (FCAM) for long-range feature relationships.
  • Introduced a Bi-directional Feature Aggregation Module (BFAM) for feature context aggregation.
  • Utilized an edge supervision module (ESM) with frequency features for boundary refinement.
Keywords:
Bi-directional feature aggregationCross-attention fusionEdge supervisionFrequency domainRGB-DSalient object detection

Related Experiment Videos

Last Updated: Jul 9, 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

Main Results:

  • The proposed FCAFNet model demonstrated superior performance compared to state-of-the-art methods.
  • Qualitative and quantitative experimental results validated the model's effectiveness.
  • The frequency-based approach significantly enhanced salient object detection.

Conclusions:

  • FCAFNet effectively fuses cross-modality information in the frequency domain for RGB-D salient object detection.
  • The proposed modules (FCAM, BFAM, ESM) contribute to improved detection accuracy and boundary definition.
  • This work opens new avenues for frequency domain fusion in multi-modal computer vision tasks.