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

Parallel Processing

Parallel Processing

The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...

You might also read

Related Articles

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

Sort by

Same author

Mining resistance genes of soybean cyst nematode based on genome-wide association study.

Frontiers in plant science·2026

Same author

Transient Plasmonic Photothermal Imaging Deciphers Dynamic Thermal Transfer during the Cell Cycle.

Chemical & biomedical imaging·2026

Same author

Conservation Tillage-Mediated Rhizosphere Microbial Community Remodeling Drives Soil Organic Carbon Accumulation and Nitrogen and Phosphorus Transformation in Farmland.

Microorganisms·2026

Same author

Bufalin post-transcriptionally suppresses STAT3 to alleviate renal ferroptosis and tubulointerstitial fibrosis in diabetic kidney disease.

Renal failure·2026

Same author

Dynamic Anion Space Gradient Distribution Drives Wide-Temperature-Range All-Solid-State Lithium-Ion Batteries.

Angewandte Chemie (International ed. in English)·2026

Same author

Analysis of the uniformity and stability of dust concentration calibration systems in instrument testing.

Environmental research·2026

Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026

Same journal

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 29, 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

DPNet: Dual-Path Network for Real-Time Object Detection With Lightweight Attention.

Quan Zhou, Huimin Shi, Weikang Xiang

IEEE Transactions on Neural Networks and Learning Systems

|March 27, 2024

Summary

This summary is machine-generated.

DPNet, a novel dual-path network, enhances real-time object detection by balancing accuracy and efficiency. It uses a lightweight attention scheme to capture both semantic features and object details, outperforming existing methods.

More Related Videos

Methods to Test Visual Attention Online

Methods to Test Visual Attention Online

Published on: February 19, 2015

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

Related Experiment Videos

Last Updated: Jun 29, 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

Methods to Test Visual Attention Online

Methods to Test Visual Attention Online

Published on: February 19, 2015

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

Area of Science:

Computer Vision
Deep Learning
Object Detection

Background:

Lightweight convolutional neural networks (CNNs) for real-time object detection face challenges with coarse feature maps and limited representation of large-scale data.
Single-path architectures in lightweight detectors often lead to inaccurate object localization due to continuous downsampling.
Existing lightweight networks struggle to effectively represent complex visual data, impacting detection performance.

Purpose of the Study:

To introduce DPNet, a dual-path network with a lightweight attention scheme for improved real-time object detection.
To address the limitations of single-path architectures in capturing both high-level semantics and low-level details.
To enhance the representation capability of lightweight networks for large-scale visual data.

Main Methods:

Developed a dual-path network (DPNet) architecture to extract high-level semantic and low-level object features in parallel.
Incorporated a lightweight self-correlation module (LSCM) for global interaction modeling with minimal computational overhead.
Extended LSCM to a lightweight cross-correlation module (LCCM) in the network's neck for inter-scale feature dependency capture.

Main Results:

DPNet achieves state-of-the-art trade-offs between detection accuracy and implementation efficiency on benchmark datasets.
Achieved 31.3% AP on MS COCO, 82.7% mAP on Pascal VOC 2007, and 41.6% mAP on ImageNet.
Maintained a small model size (approx. 2.5M) and low computational cost (1.04 GFLOPs), with high inference speeds (164-196 FPS).

Conclusions:

DPNet effectively overcomes the limitations of single-path lightweight detectors for real-time object detection.
The dual-path architecture and lightweight correlation modules significantly improve feature representation and localization accuracy.
DPNet offers a highly efficient and accurate solution for real-time object detection tasks.