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

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.

Association Areas of the Cortex

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

Enhancing mortality prediction in septic ICU patients with malignancies through ensemble machine learning: a retrospective cohort study.

Scientific reports·2026

Same author

The JAK-STAT pathway in allergic diseases: from pathogenesis to targeted therapy.

Biomarker research·2026

Same author

Complete Mitochondrial Genome of <i>Melophagus ovinus</i> from Qinghai-Tibet Plateau Provides Evidence for D-Loop Length Polymorphism.

Genes·2026

Same author

<i>Pulchragaricus rhodophyllus</i> gen. et sp. nov. (<i>Callistosporiaceae</i>, <i>Agaricales</i>) from Yunnan, China, Based on Morphological and Molecular Data.

Life (Basel, Switzerland)·2026

Same author

Tea consumption and major adverse cardiovascular events in coronary heart disease: a non-linear dose-response analysis with joint effect modification by lipoprotein(a) and systemic inflammation - a UK Biobank study.

Frontiers in nutrition·2026

Same author

Shenling Baizhu Decoction Improves Chemotherapy-Induced Sarcopenia by Regulating the NLRP3 Inflammasome and Muscle Metabolism.

Current medicinal chemistry·2026

Search research articles

Related Experiment Video

Updated: Jul 11, 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

CACNN: Capsule Attention Convolutional Neural Networks for 3D Object Recognition.

Kai Sun, Jiangshe Zhang, Shuang Xu

IEEE Transactions on Neural Networks and Learning Systems

|November 7, 2023

Summary

This study introduces a novel capsule attention layer (CAL) to improve 3D object recognition by preventing information loss during feature fusion. The proposed capsule attention convolutional neural network (CACNN) enhances speed and accuracy over existing methods.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Jul 11, 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

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

View-based 3D object recognition methods use 2D images but often lose information through feature aggregation.
Existing approaches like Multi-View Convolutional Neural Networks (MVCNN) employ pooling operations that can discard crucial visual data.

Purpose of the Study:

To address information loss in 3D object recognition by proposing a novel feature fusion mechanism.
To enhance the efficiency and performance of capsule networks for 3D object recognition tasks.

Main Methods:

Introduced a Capsule Attention Layer (CAL) that utilizes an attention mechanism for fusing capsule features, replacing traditional dynamic routing.
Developed a Capsule Attention Convolutional Neural Network (CACNN) integrating the CAL for 3D object recognition.
Demonstrated that the view pooling layer in MVCNN is a specific instance of CAL under certain weight configurations.

Main Results:

The proposed CAL effectively fuses features without significant information loss, improving upon standard pooling methods.
The CACNN achieved superior performance compared to state-of-the-art methods on three benchmark datasets for 3D object recognition.
The attention-based approach in CAL significantly speeds up capsule network processing.

Conclusions:

The novel Capsule Attention Layer (CAL) and the resulting Capsule Attention Convolutional Neural Network (CACNN) offer a more effective approach to 3D object recognition.
CACNN demonstrates significant improvements in both accuracy and speed, outperforming existing methods by mitigating information loss inherent in pooling operations.