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

Force Classification

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

You might also read

Related Articles

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

Sort by

Same author

The efficacy of different doses of citicoline in improving the prognosis of patients with acute ischemic stroke based on network meta-analysis.

Frontiers in pharmacology·2025

Same author

Determining metabolic mechanism linking phospholipids and docosahexaenoic acid through phosphatidylcholine synthesis by phosphocholine cytidylyltransferase (CCT) overexpression in Schizochytrium sp.

Microbial cell factories·2025

Same author

Retrieval of nighttime aerosol optical depth by simultaneous consideration of artificial and natural light sources.

The Science of the total environment·2023

Same author

Hierarchical attention network for multivariate time series long-term forecasting.

Applied intelligence (Dordrecht, Netherlands)·2022

Same author

An observer-based adaptive fault-tolerant control for hypersonic vehicle with unexpected centroid shift and input saturation.

ISA transactions·2022

Search research articles

Related Experiment Video

Updated: Sep 2, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

An effective behavior recognition method in the video session using convolutional neural network.

Yizhen Meng¹, Jun Zhang¹

¹Computer Science Department, Tangshan Normal University, Tangshan, China.

|August 1, 2022

Summary

This study introduces an improved convolutional neural network for video behavior recognition. The method enhances accuracy by integrating target detection, temporal modeling, and an optimized loss function, outperforming existing algorithms.

More Related Videos

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

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

Published on: February 6, 2020

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

Related Experiment Videos

Last Updated: Sep 2, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

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

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

Published on: February 6, 2020

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

Area of Science:

Computer Science
Artificial Intelligence

Background:

Video-based behavior recognition is crucial for various applications.
Existing methods face challenges with accuracy, background noise, and temporal modeling.

Purpose of the Study:

To propose an effective video-based behavior recognition method using convolutional neural networks.
To improve accuracy by addressing background interference and enhancing temporal understanding.

Main Methods:

Incorporated target detection for precise body region extraction and background noise reduction.
Implemented fragmentation and stochastic sampling for long-term temporal modeling.
Utilized an improved loss function to handle classification difficulties and sample imbalance.

Main Results:

Experimental results on benchmark datasets demonstrate the proposed method's effectiveness.
The approach achieved higher accuracy compared to other common behavior recognition algorithms.
Verified through hyperparameter, ablation, and contrast experiments.

Conclusions:

The proposed convolutional neural network method significantly enhances video-based behavior recognition accuracy.
The integration of target detection, temporal modeling, and optimized loss functions offers a robust solution.
The study provides a valuable contribution to the field, with implications for future research.