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

SHP2 Inhibition Reveals Compensatory PI3K-AKT Activation in KRAS-Driven Pancreatic Cancer: Discovery of <b>SDUY104</b> and Rational Approaches for Combination Therapy.

Journal of medicinal chemistry·2026
Same author

miR-27a Suppresses Mitochondrial Function to Promote Hepatic Steatosis in High-Fat-Diet-Induced Obesity.

Molecules (Basel, Switzerland)·2026
Same author

SHP2-targeted cancer therapeutics: Structural insights, inhibitor development and emerging modalities.

Bioorganic & medicinal chemistry·2026
Same author

Dual Allosteric Targeting of SHP2: Development of Bivalent Inhibitors with Enhanced Potency for Cancer Treatment.

Journal of medicinal chemistry·2026
Same author

Variable effects of biochar on soil greenhouse gas emissions: A meta-analysis of climate, soil, and biochar property interactions.

Environmental research·2026
Same author

CO<sub>2</sub>-sensitive K<sup>+</sup> channel traffic affects stomata and whole-plant water use.

Journal of integrative plant biology·2026

Related Experiment Video

Updated: Jan 8, 2026

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

14.1K

ADP-Net: a hierarchical attention-diffusion-prediction framework for human trajectory prediction.

Zhenggui Zhang1, Shanlin Xiao1, Zhiyi Yu1

  • 1School of Microelectronics Science and Technology, Sun Yat-sen University, Guangzhou, China.

Frontiers in Artificial Intelligence
|December 15, 2025
PubMed
Summary

Accurate crowd behavior prediction for autonomous systems is improved by the attention diffusion-prediction network (ADP-Net). This novel framework enhances spatial-temporal modeling, outperforming existing methods in prediction accuracy.

Keywords:
Personalized PageRankgraph diffusion convolutiongraph neural networksmulti-hoprepresentation learningspatio-temporal relational modelingtrajectory prediction

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

723

Related Experiment Videos

Last Updated: Jan 8, 2026

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

14.1K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

723

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Robotics

Background:

  • Human crowd behavior prediction is crucial for autonomous systems.
  • Current spatial-temporal graph convolutional networks (STGCNs) have limitations including restricted receptive fields and poor topological extensibility.
  • These limitations lead to suboptimal performance in modeling complex crowd dynamics.

Purpose of the Study:

  • To develop a novel computational framework for accurate human crowd behavior prediction.
  • To address the limitations of existing STGCNs in capturing spatial-temporal dynamics.
  • To propose the attention diffusion-prediction network (ADP-Net) for enhanced crowd behavior modeling.

Main Methods:

  • Established theoretical connections between graph convolutional networks (GCNs) and personalized propagation neural architectures.
  • Introduced the attention diffusion-prediction network (ADP-Net) with consistent graph convolution layers, multi-scale attention diffusion layers (implementing graph diffusion convolution - GDC), and adaptive temporal convolution modules.
  • Employed polynomial approximation for GCN operations and an approximate personalized propagation scheme for GDC to enable efficient multi-hop interaction modeling.

Main Results:

  • Achieved state-of-the-art results on standard benchmarks (ETH/UCY and Stanford Drone Dataset).
  • Demonstrated significant improvements with a 4% enhancement in average displacement error (ADE) and a 26% enhancement in final displacement error (FDE) compared to prior approaches.
  • Validated the framework's effectiveness in modeling spatial-temporal crowd dynamics.

Conclusions:

  • The proposed ADP-Net offers a robust theoretical framework and practical implementation for crowd behavior prediction in autonomous systems.
  • ADP-Net overcomes the limitations of traditional STGCNs by enabling efficient multi-hop interaction modeling and maintaining structural consistency.
  • This advancement contributes to safer and more effective autonomous system operation in human environments.