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 Experiment Video

Updated: May 24, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

3D convolutional neural networks for human action recognition.

Shuiwang Ji1, Ming Yang, Kai Yu

  • 1Department of Computer Science, Old Dominion University, Suite 3300, 4700 Elkhorn Avenue, Norfolk, VA 23529-0162, USA. sji@cs.odu.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|March 7, 2012
PubMed
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

Efficient homing of T cells via afferent lymphatics requires mechanical arrest and integrin-supported chemokine guidance.

Nature communications·2020
Same author

Carbon doped Fe<sub>3</sub>O<sub>4</sub> peroxidase-like nanozyme for mitigating the membrane fouling by NOM at neutral pH.

Water research·2020
Same author

Rapid Monitoring Approach for Microplastics Using Portable Pyrolysis-Mass Spectrometry.

Analytical chemistry·2020
Same author

Mutations in the HPV16 genome induced by APOBEC3 are associated with viral clearance.

Nature communications·2020
Same author

Power calculation for the general two-sample Mendelian randomization analysis.

Genetic epidemiology·2020
Same author

A Facile Grinding Method for the Synthesis of 3D Ag Metal-Organic Frameworks (MOFs) Containing Ag<sub>6</sub> Mo<sub>7</sub> O<sub>24</sub> for High-Performance Supercapacitors.

Chemistry (Weinheim an der Bergstrasse, Germany)·2020
Same journal

A Unified and Fast-Sampling Diffusion Bridge Framework via Stochastic Optimal Control.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Robust 3D Semantic Occupancy Prediction With Calibration-Free Spatial Transformation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Image Restoration via Multi-domain Learning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a novel 3D convolutional neural network (CNN) for automated human action recognition in surveillance videos. The new model effectively captures motion dynamics, outperforming existing methods in real-world airport surveillance scenarios.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Current human action recognition methods often rely on handcrafted features, limiting their direct application to raw video data.
  • Two-dimensional Convolutional Neural Networks (CNNs) are effective but primarily handle 2D inputs, struggling to capture temporal motion dynamics.

Purpose of the Study:

  • To develop a novel 3D CNN model for automated human action recognition in surveillance videos.
  • To enhance the model's ability to extract spatio-temporal features for improved motion understanding.
  • To achieve superior performance in recognizing human actions in complex, real-world surveillance environments.

Main Methods:

  • Developed a novel 3D CNN architecture capable of performing 3D convolutions on video inputs.

Related Experiment Videos

Last Updated: May 24, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

  • Implemented feature extraction across both spatial and temporal dimensions to capture motion information from adjacent frames.
  • Integrated multi-channel information processing and combined predictions from diverse models for performance enhancement.
  • Utilized regularization with high-level features to further boost recognition accuracy.

    • Main Results:

    • The proposed 3D CNN model demonstrated superior performance in human action recognition compared to baseline methods.
    • The model successfully captured motion dynamics by processing information across spatial and temporal dimensions.
    • Application to airport surveillance videos validated the model's effectiveness in real-world scenarios.

    Conclusions:

    • The novel 3D CNN model offers a significant advancement in automated human action recognition.
    • The approach effectively extracts spatio-temporal features, crucial for understanding complex actions in videos.
    • This method shows great promise for surveillance applications, particularly in dynamic environments like airports.