Related Experiment Video
Updated: Jun 30, 2025
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
3.8K
A comprehensive bibliometric survey of micro-expression recognition system based on deep learning.
Adnan Ahmad1, Zhao Li1, Sheeraz Iqbal2
1Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education, School of Information Science and Engineering, Southeast University, Nanjing, 210096, China.
Heliyon
|March 18, 2024
Summary
This study reviews micro-expression (ME) recognition research, finding a significant increase in publications since 2012. Deep learning is key to advancing this field for applications in public safety and clinical diagnosis.
Area of Science:
- Computer Science
- Psychology
- Artificial Intelligence
Background:
- Micro-expressions (ME) are fleeting facial expressions revealing concealed emotions.
- ME recognition has critical applications in public safety and clinical diagnosis.
- A comprehensive review of ME recognition literature is needed.
Purpose of the Study:
- To conduct a bibliometric and network analysis of ME recognition research.
- To identify trends, key contributors, and influential publications in the field.
- To analyze the evolution and thematic content of ME research.
Main Methods:
- Bibliometric and network analysis of 735 publications (2012-2022) from WOS and Scopus.
- Data extraction for citation, coupling, co-authorship, co-occurrence, and co-citation analysis.
- Thematic and descriptive analysis of research findings and methodologies.
Main Results:
- A 24-fold increase in publications by 2021, with significant growth post-2017.
- Top journals: IEEE Transactions on Affective Computing, Neurocomputing, Multimedia Tools and Applications.
- China leads in publications; Zhao G is the most prolific author; University of Oulu leads in institutional contributions.
- Deep learning, facial expression recognition, and emotion recognition are dominant themes.
- Research is primarily in engineering, with major contributions from China and Malaysia.
Conclusions:
- ME recognition research has experienced exponential growth, particularly driven by deep learning.
- The field shows increasing international collaboration and productivity.
- Future research should leverage deep learning for enhanced ME recognition in diverse applications.
