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

Visual System

Visual System

Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...

Vision

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.

You might also read

Related Articles

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

Sort by

Same author

A Defect Detection Method for Rail Surface and Fasteners Based on Deep Convolutional Neural Network.

Computational intelligence and neuroscience·2021

Same author

Research on track fastener positioning method based on local unidirectional template matching.

Science progress·2021

Same author

Anticancer activity and underlying mechanism of neogambogic acid.

Chinese journal of natural medicines·2018

Same author

Mechanical Behaviors of Angle-Ply Black Phosphorus by Molecular Dynamics Simulations.

Nanomaterials (Basel, Switzerland)·2018

Same author

Gene-methylation epistatic analyses via the W-test identifies enriched signals of neuronal genes in patients undergoing lipid-control treatment.

BMC proceedings·2018

Same author

Developing a hospital-based combat injury registry at the Chinese Peacekeeping Level 2 Military Hospital in GAO, Mali.

Journal of the Royal Army Medical Corps·2018

Search research articles

Related Experiment Video

Updated: Nov 9, 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

AFI-Net: Attention-Guided Feature Integration Network for RGBD Saliency Detection.

Liming Li^1,2, Shuguang Zhao¹, Rui Sun²

¹School of Information Science and Technology, Donghua University, Shanghai 201620, China.

Computational Intelligence and Neuroscience

|April 16, 2021

Summary

This summary is machine-generated.

This study introduces an attention-guided feature integration network (AFI-Net) for RGBD saliency detection. The model effectively enhances features using attention and fuses them with boundary details for superior saliency inference.

More Related Videos

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Nov 9, 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

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Area of Science:

Computer Vision
Artificial Intelligence

Background:

Saliency detection aims to identify visually prominent regions in images.
RGBD data, combining color and depth information, offers richer scene understanding for improved saliency detection.

Purpose of the Study:

To propose an innovative RGBD saliency model, the attention-guided feature integration network (AFI-Net).
To enhance feature extraction and fusion for more accurate saliency inference using both RGB and depth data.

Main Methods:

Extracting multi-level deep features from both RGB and depth modalities.
Employing attention modules to enhance these features, followed by hierarchical fusion.
Integrating RGB and depth boundary features to refine saliency inference with spatial details.

Main Results:

The AFI-Net demonstrates superior performance in saliency detection across five challenging RGBD datasets.
Attention-guided feature enhancement and boundary-aware inference effectively highlight salient objects.

Conclusions:

The proposed AFI-Net effectively leverages multi-modal features and attention mechanisms for robust RGBD saliency detection.
The model's ability to integrate low-level boundary details with deep features leads to well-characterized salient objects.