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

You might also read

Related Articles

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

Sort by

Same author

Flexible Prescribed-Time Optimal Control With Adaptive State-Input Constraint Bounds via Actor-Critic Learning.

IEEE transactions on neural networks and learning systems·2026

Same author

Toward Comprehensive Information-Theoretic Multi-View Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Functional connectivity-based classification and subtyping of major depression for precision mental health: An ensemble graph neural network approach.

PLOS digital health·2026

Same author

DAMind: Zero-Shot Visual Cross-Domain Alignment and Representation for EEG Decoding.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Beyond depression symptoms: the default mode network as a predictor of antidepressant response.

Npj mental health research·2026

Same author

Fast Multi-view Discrete Clustering via Spectral Embedding Fusion.

IEEE transactions on pattern analysis and machine intelligence·2025

Search research articles

Related Experiment Video

Updated: Oct 3, 2025

Topographical Estimation of Visual Population Receptive Fields by fMRI

Topographical Estimation of Visual Population Receptive Fields by fMRI

Published on: February 3, 2015

Region-aware network: Model human's Top-Down visual perception mechanism for crowd counting.

Yuehai Chen¹, Jing Yang², Dong Zhang¹

¹School of Automation Science and Engineering, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, 710049, Shanxi, China.

Neural Networks : the Official Journal of the International Neural Network Society

|February 13, 2022

Summary

This study introduces RANet, a novel feedback network for crowd counting that addresses background noise and scale variation. RANet effectively identifies crowd regions and estimates density by mimicking human visual perception.

Keywords:

Crowd counting Global context information Priority map Top-Down visual perception mechanism

More Related Videos

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Related Experiment Videos

Last Updated: Oct 3, 2025

Topographical Estimation of Visual Population Receptive Fields by fMRI

Topographical Estimation of Visual Population Receptive Fields by fMRI

Published on: February 3, 2015

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Crowd counting research faces challenges with background noise and scale variation.
Human visual perception efficiently handles crowd density and region identification using a global receptive field.

Purpose of the Study:

To propose a novel feedback network, RANet, for improved crowd counting.
To model the human top-down visual perception mechanism for crowd analysis.

Main Methods:

Introduced a feedback architecture generating priority maps to highlight potential crowd regions.
Designed a Region-Aware block to adaptively encode contextual information using a global receptive field.
Utilized a relevance matrix derived from input images and priority maps to establish global pixel relationships.

Main Results:

The proposed RANet method demonstrates superior performance compared to existing state-of-the-art crowd counting techniques.
Achieved significant improvements on multiple public crowd counting datasets.

Conclusions:

RANet effectively addresses common crowd counting challenges like noise and scale variation.
The network's ability to model human visual perception leads to enhanced crowd density estimation and localization.