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

Non-Destructive Blade Sharpness Characterization Using a High-Shear Responsive Fluid and Analytical Drag Modeling.

Nature communications·2026

Same author

Frequency-domain enhanced spatial multi-position moiré fringe alignment method.

Optics letters·2026

Same author

'Fuhui 631', a novel hybrid rice restorer line with multiple resistance genes, high combining ability, and superior grain quality developed with marker‑assisted breeding.

Molecular breeding : new strategies in plant improvement·2026

Same author

Diversity of fecal viromes and zoonotic risk assessment in captive wild felids using viral metagenomics.

Scientific reports·2026

Same author

An Evaluation Method for Partial Discharge in Generator Stator Bar Insulation Based on Fiber-Optic Acoustic Detection.

Sensors (Basel, Switzerland)·2026

Same author

A Non-Host Pathogen Elicitor Induces Blast Resistance Mediated by OsNAC78-Pir7b Module in Rice.

Plant, cell & environment·2026

Search research articles

Related Experiment Video

Updated: Oct 29, 2025

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

A temporal-spatial attention-based action recognition method for intelligent fault diagnosis.

Wentao Luo¹, Jianfu Zhang², Pingfa Feng³

¹Beijing Key Lab of Precision/Ultra-precision Manufacturing Equipments and Control, Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China.

ISA Transactions

|July 11, 2021

Summary

This study introduces a temporal-spatial attention-based action recognition method (TARM) for efficient industrial video fault diagnosis. TARM significantly reduces computational costs, making intelligent fault detection feasible in factories.

Keywords:

Long-short term model Spatial-attention model Temporal-attention model Video fault diagnosis

More Related Videos

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

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

Related Experiment Videos

Last Updated: Oct 29, 2025

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

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

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

Area of Science:

Computer Vision
Artificial Intelligence
Industrial Automation

Background:

Intelligent fault diagnosis using video data is crucial for industrial applications.
Existing methods face challenges due to high computational and memory demands, limiting practical factory implementation.

Purpose of the Study:

To propose an efficient temporal-spatial attention-based action recognition method (TARM) for industrial video fault diagnosis.
To overcome the computational and memory limitations of current video analysis techniques.

Main Methods:

The proposed TARM integrates three modules: Temporal-Attention-based Frame Splitting (TAB), Spatial-Attention-based Agent Focusing (SAB), and Long-Short Term feature learning (LSB).
TAB extracts key frames, SAB refines features by focusing on essential information, and LSB uses recurrent convolutional architectures for action monitoring.

Main Results:

TARM demonstrates improved performance in terms of training time and fault diagnosis accuracy.
Comparative analysis against six state-of-the-art methods validates TARM's effectiveness.

Conclusions:

TARM offers a computationally efficient and accurate solution for intelligent fault diagnosis in industrial video data.
The method addresses the practical limitations of applying advanced video analysis in factory settings.