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: May 9, 2026

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

Data-free prior model for upper body pose estimation and tracking.

Jixu Chen, Siqi Nie, Qiang Ji

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |July 30, 2013
    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

    Prevalence of sarcopenia in patients with rheumatoid arthritis: a cross-sectional study.

    RMD open·2026
    Same author

    Tissue-Specific Redistribution of Free Amino Acids in Mandarin Fish (<i>Siniperca chuatsi</i>) Under Acute Salinity, Alkalinity and Combined Saline-Alkaline Stress.

    Life (Basel, Switzerland)·2026
    Same author

    Interpretable machine learning for prognostic prediction in young women with triple-negative invasive ductal breast cancer: a Boruta-SHAP integrated approach.

    Gland surgery·2026
    Same author

    Respiratory chain gene mutations associated with global phylogenetic clustering of drug-resistant <i>Mycobacterium tuberculosis</i> revealed by whole-genome sequencing.

    Frontiers in immunology·2026
    Same author

    An Image-based Global Climate Sentiment Index.

    Scientific data·2026
    Same author

    High-Entropy Oxide Interlayers Enable Coordinated Regulation of Zn<sup>2+</sup> Interfacial Kinetics for Stable Zinc Metal Anodes.

    ACS applied materials & interfaces·2026

    This study introduces a new human body pose estimation prior model learned from physical constraints, not motion capture data. This approach improves generalization to new activities and subjects.

    Area of Science:

    • Computer Vision
    • Biomechanical Modeling
    • Human Pose Estimation

    Background:

    • Human body pose estimation from video is crucial for activity recognition.
    • Existing methods often rely on data-driven prior models from 3D motion capture.
    • Data-driven models struggle with generalization to unseen activities and subjects due to collection costs and limitations.

    Purpose of the Study:

    • To develop a novel prior model for human body pose estimation.
    • To overcome the generalization limitations of data-driven prior models.
    • To leverage anatomic, biomechanical, and physical constraints for robust pose tracking.

    Main Methods:

    • Learning a pose prior model from fundamental anatomic, biomechanical, and physical constraints.
    • Developing methods to effectively capture and encode these constraints into the prior model.

    Related Experiment Videos

    Last Updated: May 9, 2026

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
    09:41

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

    Published on: April 21, 2023

  • Systematically integrating the constraint-based prior model with image-based pose estimation.

    • Main Results:

    • The proposed constraint-based prior model achieves performance comparable to data-based models on known motions.
    • Demonstrates significantly improved generalization capabilities for novel body motions.
    • Shows superior performance across different subjects not included in traditional training datasets.

    Conclusions:

    • A physics-informed prior model offers a more generalizable solution for human body pose estimation.
    • Learning from constraints bypasses the need for extensive and costly motion capture data.
    • This approach enhances the robustness and applicability of pose estimation in diverse scenarios.