Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Efficient and Dynamically Consistent Joint Torque Estimation for Wearable Neurotechnology via Knowledge Distillation.

Bioengineering (Basel, Switzerland)·2026
Same author

Corrigendum to "Nanozyme-catalyzed SERS sensor combined with a competitive recognition strategy for diabetic retinopathy-associated VEGF detection" [Talanta 298 (2026) 129006].

Talanta·2026
Same author

Nanozyme-catalyzed SERS sensor combined with a competitive recognition strategy for diabetic retinopathy-associated VEGF detection.

Talanta·2025
Same author

Nanoenzymatic SERS bifunctional detection platform based on recognition competition strategy for ultrasensitive detection of diabetic retinopathy-related biomarkers.

Frontiers in bioengineering and biotechnology·2025
Same author

Estimation of lower limb torque: a novel hybrid method based on continuous wavelet transform and deep learning approach.

PeerJ. Computer science·2025
Same author

A brain structure learning-guided multi-view graph representation learning for brain network analysis.

Quantitative imaging in medicine and surgery·2024

Related Experiment Video

Updated: Nov 27, 2025

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

11.2K

PGNet: Pipeline Guidance for Human Key-Point Detection.

Feng Hong1,2, Changhua Lu1, Chun Liu1

  • 1College of computer and Information, Hefei University of Technology, Hefei 230009, China.

Entropy (Basel, Switzerland)
|December 8, 2020
PubMed
Summary

This study introduces PGNet, a novel network for human key-point detection. It addresses feature imbalance using a pipeline guidance strategy, Cross-Distance-IoU Loss, and a cascaded fusion feature model.

Keywords:
IoUfeature fusionkey-point detectionobject detection

More Related Videos

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
10:25

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Published on: September 2, 2025

300
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.7K

Related Experiment Videos

Last Updated: Nov 27, 2025

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

11.2K
Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
10:25

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Published on: September 2, 2025

300
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.7K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Deep Learning

Background:

  • Human key-point detection is a challenging computer vision task.
  • Convolutional neural networks (CNNs) excel at target detection but face challenges with feature imbalance (semantic vs. spatial) in deep networks.
  • Increasing network depth leads to communication overhead, impacting computational efficiency.

Purpose of the Study:

  • To propose a novel network structure, PGNet, to address feature imbalance and communication overhead in human key-point detection.
  • To improve the accuracy and efficiency of human key-point detection models.

Main Methods:

  • Developed PGNet, a novel network structure incorporating three key components.
  • Pipeline Guidance Strategy (PGS): Optimizes feature extraction and information flow.
  • Cross-Distance-IoU Loss (CIoU): Enhances localization accuracy.
  • Cascaded Fusion Feature Model (CFFM): Integrates multi-level features effectively.

Main Results:

  • PGNet effectively balances semantic and spatial information, mitigating feature extraction imbalance.
  • The proposed methods improve the precision and robustness of human key-point detection.
  • PGNet demonstrates enhanced efficiency by managing communication overhead in deep networks.

Conclusions:

  • PGNet offers a promising solution for human key-point detection by tackling feature imbalance and communication efficiency.
  • The integrated approach of PGS, CIoU, and CFFM contributes to state-of-the-art performance in this domain.