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,...

Frames: Problem Solving II

Frames: Problem Solving II

Consider a hydraulic hoist supporting a load of 1 kN. Assuming a simplified schematic representation of this frame structure, the force acting on BD and BF members can be determined.

Sequence Networks of Rotating Machines

Sequence Networks of Rotating Machines

A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...

You might also read

Related Articles

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

Sort by

Same author

Multimodal GPT-5 for Predicting Poor Functional Outcomes After Intracerebral Hemorrhage in the Emergency Department: Validation Study.

JMIR AI·2026

Same author

Multi-Agent DRL for Air-to-Ground Communication Planning in UAV-Enabled IoT Networks.

Sensors (Basel, Switzerland)·2024

Same author

Secure and Privacy-Preserving Intrusion Detection and Prevention in the Internet of Unmanned Aerial Vehicles.

Sensors (Basel, Switzerland)·2023

Same author

Bi<sub>2</sub>O<sub>2</sub>Se-Based Bimode Noise Generator for the Application of Generative Adversarial Networks.

ACS applied materials & interfaces·2023

Same author

Easy and Rapid Approach to Obtaining the Binding Affinity of Biomolecular Interactions Based on the Deep Learning Boost.

Analytical chemistry·2022

Same author

A Lightweight Passive Human Tracking Method Using Wi-Fi.

Sensors (Basel, Switzerland)·2022

Search research articles

Related Experiment Video

Updated: May 7, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Violent Video Recognition by Using Sequential Image Collage.

Yueh-Shen Tu¹, Yu-Shian Shen², Yuk Yii Chan²

¹Department of Electrical Engineering, Chang Gung University, Taoyuan 33302, Taiwan.

Sensors (Basel, Switzerland)

|March 28, 2024

Summary

This study introduces a new method for identifying violent activities using sequential image collages (SIC) with MLP-Mixer models. This approach effectively recognizes violent behavior using less data and computational power than Transformer models.

Keywords:

Transformers behavioral sciences computer architecture image recognition multilayer perceptrons neurons training

More Related Videos

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

Related Experiment Videos

Last Updated: May 7, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

Area of Science:

Computer Science
Artificial Intelligence
Behavior Recognition

Background:

Transformer models excel at behavior recognition but require extensive data.
Existing violent behavior datasets are insufficient for Transformer training.
Transformers can be computationally intensive and may miss temporal dynamics.

Purpose of the Study:

To develop an efficient method for violent behavior recognition using limited data.
To address the computational and data limitations of Transformer models in behavior analysis.
To improve the recognition of temporal features in violent activities.

Main Methods:

Proposed a novel dataset format: sequential image collage (SIC).
Utilized the MLP-Mixer architecture for behavior recognition.
Trained the model on diverse public datasets including hockey fights, CCTV violence, and real-life situations.

Main Results:

The MLP-Mixer model trained with SIC achieved high performance in violent behavior recognition.
The proposed SIC method requires fewer parameters and less computational power (FLOPs) compared to state-of-the-art models.
Demonstrated effective understanding of temporal features in violent actions.

Conclusions:

The sequential image collage (SIC) dataset combined with MLP-Mixer offers an efficient solution for violent behavior recognition.
This approach overcomes the data scarcity and computational challenges associated with Transformer models.
The method shows promise for real-world safety applications requiring robust behavior analysis.