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

You might also read

Related Articles

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

Sort by

Same author

Prediction of Clinical Outcomes Based on Phenotypic Grouping Using Left Ventricular and Left Atrial Strains in Patients with HFpEF.

European heart journal. Cardiovascular Imaging·2026

Same author

Multitask Artificial Intelligence-Based Electrocardiogram Tool for Preoperative Cardiac Testing in Noncardiac Surgery: Retrospective Cohort Study of Health Care Utilization and Costs.

Journal of medical Internet research·2026

Same author

Fully automated artificial intelligence-based echocardiographic analysis substantially reduces workflow time while preserving measurement accuracy: a pilot study.

Journal of cardiovascular imaging·2026

Same author

Point tracking as a temporal Cue for robust myocardial segmentation in echocardiography videos.

International journal of computer assisted radiology and surgery·2026

Same author

Validation of AI-enhanced ECG image analysis for identifying extreme cardiac magnetic resonance metrics in a cross-ethnic UK biobank study.

Scientific reports·2026

Same author

Machine-learning-derived phenotypes of hypertensive patients using multidimensional clinical and echocardiographic data including strain imaging.

European heart journal. Digital health·2026

Search research articles

Related Experiment Video

Updated: Jul 9, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Anomaly Detection Based on a 3D Convolutional Neural Network Combining Convolutional Block Attention Module Using

In-Chang Hwang¹, Hyun-Soo Kang¹

¹Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Republic of Korea.

Sensors (Basel, Switzerland)

|December 9, 2023

Summary

This summary is machine-generated.

This study introduces a novel deep learning model for detecting violent behavior in videos, outperforming existing methods. The approach effectively addresses challenges in anomaly detection datasets for real-time video surveillance.

Keywords:

3D convolution UBI-Fights area under the curve computer vision convolutional block attention module equal error rate video surveillance

More Related Videos

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

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

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

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jul 9, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

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

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

Published on: December 15, 2023

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

The rise in violent crime necessitates advanced surveillance capabilities.
Closed-circuit television (CCTV) systems are crucial for real-time situation analysis.
Anomaly detection in video faces challenges due to imbalanced datasets (normal vs. abnormal events).

Purpose of the Study:

To develop an effective anomaly detection model for identifying violent acts in videos.
To address the challenge of limited abnormal event data in video datasets.
To improve real-time video monitoring systems for public safety.

Main Methods:

Anomaly detection was framed as a binary classification problem using datasets like UBI-Fights, RWF-2000, and UCSD Ped1/Ped2.
Video frames were reconstructed into image patches (e.g., 3x3, 4x4) mimicking light field and vision transformer inputs.
A 3D convolutional residual neural network (ResNet) with a convolutional block attention module (CBAM) was employed.

Main Results:

The proposed model demonstrated superior performance in detecting abnormal behaviors compared to existing methods.
On the UBI-Fights dataset, the model achieved high accuracy (0.9933), low loss (0.0010), and excellent AUC (0.9973).
The model achieved an equal error rate (EER) of 0.0027, indicating robust detection capabilities.

Conclusions:

The developed model offers a significant advancement in detecting violent behavior in video streams.
This research contributes to enhancing artificial intelligence systems for real-time video surveillance and crime prevention.
The findings have practical implications for improving public safety through intelligent monitoring solutions.