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

Three-Dimensional Force System01:30

Three-Dimensional Force System

In mechanical engineering, a three-dimensional force system is a system of forces acting in three dimensions, with forces applied along the x, y, and z coordinate axes. The three-dimensional force system is an important concept in mechanical engineering, as it allows engineers to understand and analyze the behavior of objects and structures in three dimensions. By understanding the forces acting on a system, engineers can design more efficient and effective mechanical systems that can withstand...
Deformation of Member under Multiple Loadings01:11

Deformation of Member under Multiple Loadings

When a rod is made of different materials or has various cross-sections, it must be divided into parts that meet the necessary conditions for determining the deformation. These parts are each characterized by their internal force, cross-sectional area, length, and modulus of elasticity. These parameters are then used to compute the deformation of the entire rod.
In the case of a member with a variable cross-section, the strain is not constant but depends on the position. The deformation of an...

You might also read

Related Articles

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

Sort by
Same author

Treating amblyopia using altered reality enhances the fine-scale functional correlations in early visual areas.

Human brain mapping·2023
Same author

Examining the Efficacy of a Hierarchical Management Model in Enhancing Nursing Service Quality and Patient Satisfaction.

Alternative therapies in health and medicine·2023
Same author

Efficiency and ecological safety of herbicide haloxyfop-R-methyl on removal of coastal invasive plant Spartina alterniflora.

Marine pollution bulletin·2023
Same author

Plaque enhancement predicts recurrence in acute ischemic stroke patients with large artery intracranial atherosclerosis.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2023
Same author

Whole human-brain mapping of single cortical neurons for profiling morphological diversity and stereotypy.

Science advances·2023
Same author

The dual effect of disodium anthraquinone-2,6-disulfonate (AQDS) on the Cr(VI) removal by biochar: The enhanced electron transfer and the inhibited adsorption.

Chemosphere·2023

Related Experiment Video

Updated: May 22, 2026

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.0K

SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation.

Xiangyu Xu, Lijuan Liu, Shuicheng Yan

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |December 13, 2023
    PubMed
    Summary
    This summary is machine-generated.

    SMPLer, a new Transformer framework, enhances monocular 3D human shape and pose estimation by efficiently using high-resolution features. This approach achieves state-of-the-art results with significantly fewer parameters.

    More Related Videos

    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

    1.6K
    Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects
    06:36

    Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects

    Published on: October 18, 2024

    998

    Related Experiment Videos

    Last Updated: May 22, 2026

    Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
    05:12

    Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

    Published on: August 12, 2021

    2.0K
    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

    1.6K
    Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects
    06:36

    Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects

    Published on: October 18, 2024

    998

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Human Pose Estimation

    Background:

    • Existing Transformer models for 3D human estimation face computational challenges with high-resolution features.
    • Quadratic complexity limits the use of fine-grained details crucial for accurate reconstruction.

    Purpose of the Study:

    • To develop a Transformer framework that overcomes computational limitations for monocular 3D human shape and pose estimation.
    • To enable effective utilization of high-resolution features for improved reconstruction accuracy.

    Main Methods:

    • Proposed SMPLer, a Transformer framework incorporating a decoupled attention operation.
    • Introduced an SMPL-based target representation for effective high-resolution feature utilization.
    • Developed novel multi-scale and joint-aware attention modules.

    Main Results:

    • SMPLer demonstrates superior quantitative and qualitative performance compared to existing methods.
    • Achieved a Mean Per Joint Position Error (MPJPE) of 45.2mm on the Human3.6M dataset.
    • Outperformed the state-of-the-art by over 10% with less than one-third of the parameters.

    Conclusions:

    • SMPLer effectively addresses the computational constraints of Transformer models in 3D human estimation.
    • The proposed framework significantly advances the accuracy and efficiency of monocular 3D human shape and pose reconstruction.