Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Feb 19, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K

Dual Temporal Scale Convolutional Neural Network for Micro-Expression Recognition.

Min Peng1,2, Chongyang Wang1,2, Tong Chen1,2,3

  • 1Chongqing Key Laboratory of Non-linear Circuit and Intelligent Information Processing, Southwest University, Chongqing, China.

Frontiers in Psychology
|October 31, 2017
PubMed
Summary
This summary is machine-generated.

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

Perioperative outcomes of neoadjuvant immunochemoradiotherapy versus immunochemotherapy followed by surgery in elderly patients with locally advanced esophageal squamous cell carcinoma.

Surgery·2026
Same author

Donkey Milk Exosomes Protect Against Dextran Sulfate Sodium-Induced Colitis by Delivering Anti-Inflammatory miRNAs and Reshaping Gut Microbiota.

Journal of food science·2026
Same author

Immune - cell death index in hepatocellular carcinoma: a multi-omics and machine learning study for prognosis and immunotherapy prediction.

Frontiers in immunology·2026
Same author

Research progress and applications of functional hydrogels in nasal wound healing.

Journal of biological engineering·2026
Same author

PCK2-Mediated PQBP1 Lactylation Promotes Asthmatic Inflammation through PRMT5 Inhibition.

Research (Washington, D.C.)·2026
Same author

Clinical characteristics of <i>Pneumocystis jirovecii</i> pneumonia in non-HIV patients: a retrospective study.

Frontiers in cellular and infection microbiology·2026
Same journal

Adverse and positive childhood experiences in relation to adolescent mental health: sequential indirect associations.

Frontiers in psychology·2026
Same journal

Personality profiles and usage experience are associated with trust and dependence on generative AI: a latent profile analysis.

Frontiers in psychology·2026
Same journal

Editorial: Promoting replicability: empowering method and applied researchers in driving reliable results.

Frontiers in psychology·2026
Same journal

The mediating roles of the challenge appraisal in the relationship between the coach-athlete relationship and adolescent athletes' burnout.

Frontiers in psychology·2026
Same journal

Unpacking GenAI-enabled deep learning engagement: role perceptions, human-GenAI synergy strategies, and underlying mechanisms.

Frontiers in psychology·2026
Same journal

Violence exposure and cyberbullying among Chinese adolescents: the mediating role of moral disengagement.

Frontiers in psychology·2026
See all related articles

This study introduces a Dual Temporal Scale Convolutional Neural Network (DTSCNN) for recognizing subtle facial micro-expressions. The new method significantly improves accuracy by analyzing different video frame rates, outperforming existing techniques.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Facial micro-expressions are involuntary facial movements that can betray concealed emotions.
  • Current spontaneous micro-expression recognition methods struggle with accuracy due to reliance on complex, hand-crafted features.

Purpose of the Study:

  • To develop a more accurate and practical method for spontaneous micro-expression recognition.
  • To address the limitations of traditional feature engineering in micro-expression analysis.

Main Methods:

  • Proposed a novel Dual Temporal Scale Convolutional Neural Network (DTSCNN) for micro-expression recognition.
  • The DTSCNN utilizes a two-stream architecture, with each stream adapted to different video frame rates.
  • Employed shallow, independent networks within each stream to prevent overfitting and used optical-flow sequences to extract higher-level features.
Keywords:
convolutional neural networkdeep learningfeature fusionmicro-expression recognitionoptical flow

Related Experiment Videos

Last Updated: Feb 19, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K

Main Results:

  • The DTSCNN achieved a nearly 10% higher recognition rate compared to state-of-the-art methods.
  • Experimental validation was conducted on the CASME I and CASME II spontaneous micro-expression databases.
  • The proposed network demonstrated superior performance in spontaneous micro-expression recognition tasks.

Conclusions:

  • The Dual Temporal Scale Convolutional Neural Network (DTSCNN) offers a significant advancement in spontaneous micro-expression recognition.
  • This approach overcomes limitations of traditional methods by effectively processing multi-rate temporal information.
  • The findings suggest a more reliable and practical application of micro-expression analysis in various fields.