Search research articles

Search research articles

Related Experiment Video

Updated: Jul 9, 2025

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

Object Counting via Group and Graph Attention Network.

Xiangyu Guo, Mingliang Gao, Guofeng Zou

IEEE Transactions on Neural Networks and Learning Systems

|December 5, 2023

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

MOF glass-based membranes: a promising platform for advanced separation.

Materials horizons·2026

Same author

Photocatalytic Cascade Nitrogen Fixation for Selective Purification of Methane-Rich Coal-Bed Gas Over a Bimetallic MOF.

Angewandte Chemie (International ed. in English)·2026

Same author

Modest contribution of metabolomic data to genomic prediction of breeding values for feed conversion ratio in pigs.

Genetics, selection, evolution : GSE·2026

Same author

The novel oleanolic acid derivative ZQL-4c modulates trastuzumab resistance in HER2+ breast cancer by inhibiting SCD-mediated lipid metabolism disorders.

Cancer cell international·2026

Same author

Theoretical Insights into Hydrazine Oxidation on Single-Atom Catalysts Enabling Efficient Electrochemical Hydrogen Production.

Langmuir : the ACS journal of surfaces and colloids·2026

Same author

The conditional benefit of being alive and disease free at 2 years after transplant: a long term survival evaluation among 456 patients affected by acute myeloid leukemia.

Frontiers in immunology·2026

Same journal

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

IEEE transactions on neural networks and learning systems·2026

Same journal

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

IEEE transactions on neural networks and learning systems·2026

Same journal

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

IEEE transactions on neural networks and learning systems·2026

Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026

See all related 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

Researchers developed a novel Group and Graph Attention Network (GGANet) to improve object counting accuracy by reducing background noise. This new method enhances performance across various counting tasks, including crowd and vehicle counting.

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Object counting in images and videos is crucial but hindered by background noise.
Existing methods struggle to achieve high accuracy due to interference from irrelevant pixels.

Purpose of the Study:

To develop an advanced deep learning model for accurate dense object counting.
To mitigate the impact of background noise on object counting performance.

Main Methods:

Introduced a Group and Graph Attention Network (GGANet) with an encoder-decoder architecture.
Incorporated a Group Channel Attention (GCA) module for feature map grouping and attention.
Utilized a Learnable Graph Attention (LGA) module to model feature map channels as a graph structure.

More Related Videos

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

Methods to Test Visual Attention Online

Methods to Test Visual Attention Online

Published on: February 19, 2015

Related Experiment Videos

Last Updated: Jul 9, 2025

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

Methods to Test Visual Attention Online

Methods to Test Visual Attention Online

Published on: February 19, 2015

Main Results:

GGANet effectively suppresses background noise and irrelevant pixel interference.
Demonstrated superior counting performance on diverse datasets (crowd, vehicle, remote-sensing, few-shot).

Conclusions:

The proposed GGANet significantly advances the state-of-the-art in dense object counting.
The combination of GCA and LGA modules offers a robust solution for noise reduction in counting tasks.