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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

[MSCNet: Coronary artery segmentation network with multi-scale cascade encoding and dynamic spatial context enhancement].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
Same author

Bone-derived Osterix+ osteolineage cells are a source of tumor-promoting myofibroblastic cancer-associated fibroblasts in breast cancer.

Nature communications·2026
Same author

Stepwise enhanced photoelectrochemical activity of BiOCl by Fe(III)-doping and aptamer immobilization for ultrasensitive detection of tetracycline.

Food chemistry·2026
Same author

Reverse-engineered ratiometric sensor assisted by dual redox-active DNA intercalators for ultrasensitive and reliable detection of mercury(II).

Analytica chimica acta·2026
Same author

Abnormal Temporal Variability Organization Associated with Compromised Verbal Memory and Psychotic Symptoms in Schizophrenia Patients and Their First-Degree Relatives.

International journal of neural systems·2026
Same author

A masked generative graph representation learning framework empowering precise spatial domain identification.

Bioinformatics (Oxford, England)·2026

Related Experiment Video

Updated: May 16, 2025

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

15.0K

CmdVIT: A Voluntary Facial Expression Recognition Model for Complex Mental Disorders.

Jiayu Ye, Yanhong Yu, Qingxiang Wang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |May 14, 2025
    PubMed
    Summary

    This study introduces a new dataset and model for facial expression recognition (FER) in patients with mental disorders. The CmdVIT model demonstrates improved accuracy in recognizing complex emotional expressions, aiding in treatment monitoring.

    More Related Videos

    Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
    05:51

    Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

    Published on: May 15, 2016

    8.9K
    Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
    08:31

    Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

    Published on: July 31, 2016

    13.0K

    Related Experiment Videos

    Last Updated: May 16, 2025

    Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
    10:28

    Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

    Published on: July 24, 2019

    15.0K
    Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
    05:51

    Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

    Published on: May 15, 2016

    8.9K
    Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
    08:31

    Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

    Published on: July 31, 2016

    13.0K

    Area of Science:

    • Computer Science
    • Psychiatry
    • Biomedical Engineering

    Background:

    • Facial Expression Recognition (FER) is vital for assessing mental health but faces data limitations and recognition challenges in patients with mental disorders due to privacy concerns and complex expression similarities.
    • Existing FER methods struggle with the nuanced expressions of individuals experiencing conditions like schizophrenia, depression, and anxiety.

    Purpose of the Study:

    • To establish the first dataset exclusively for FER tasks involving patients with mental disorders.
    • To develop an advanced FER model, CmdVIT, capable of accurately recognizing facial expressions in complex mental disorder patient populations.
    • To improve the monitoring and understanding of emotional states in patients with mental disorders through enhanced FER.

    Main Methods:

    • The Voluntary Facial Expression Mimicry (VFEM) experiment was conducted to collect facial expression data from patients with schizophrenia, depression, and anxiety.
    • A novel Vision Transformer model, CmdVIT, was proposed, incorporating explicit visual center positional encoding and an implicit sparse attention center loss function.
    • These mechanisms were designed to enhance positional information and reduce feature space distances, thereby mitigating inter-class and intra-class similarities.

    Main Results:

    • The VFEM dataset represents a significant contribution as the first FER dataset composed solely of patients with mental disorders.
    • CmdVIT demonstrated superior performance in FER tasks across various mental disorders within the VFEM dataset when compared to existing benchmark models.
    • The model effectively suppressed similarities between and within classes, leading to more accurate facial expression recognition.

    Conclusions:

    • The developed CmdVIT model and VFEM dataset offer a promising advancement for FER in clinical psychiatry.
    • Accurate FER in patients with mental disorders can significantly enhance treatment monitoring and therapeutic interventions.
    • The proposed methods provide a robust framework for addressing the unique challenges of FER in complex mental health populations.