Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Elastic functional Cox regression model with shape predictors.

Journal of applied statistics·2026
Same author

Joint Registration and Conformal Prediction for Partially Observed Functional Data.

Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America·2026
Same author

Mini-Nutritional Assessment Test and Fat-Free-Mass Depletion in Tunisian Chronic Obstructive Pulmonary Disease Patients.

Tanaffos·2026
Same author

Assessment of Glioblastoma Multiforme Tumor Heterogeneity via MRI-derived Shape and Intensity Features.

Data science in science·2025
Same author

Topo-Geometric Analysis of Variability in Point Clouds Using Persistence Landscapes.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Geometric framework for statistical analysis of eye tracking heat maps, with application to a tobacco waterpipe study.

Journal of applied statistics·2024

相关实验视频

Updated: Jul 24, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.5K

几何深度神经网络使用刚性和非刚性转换用于基于地标的人类行为分析.

Rasha Friji, Faten Chaieb, Hassen Drira

    IEEE transactions on pattern analysis and machine intelligence
    |July 3, 2023
    PubMed
    概括

    KShapenet引入了一个用于人类运动分析的几何深度学习方法. 这种方法模拟了形状空间的里程碑数据,改善了动作,步态和表情识别的准确性.

    科学领域:

    • 计算机视觉 计算机视觉
    • 机器学习 机器学习
    • 几何深度学习 几何深度学习

    背景情况:

    • 深度学习模型通常假定欧几里得数据结构,这可能不适用于位于非线性空间的预处理运动数据.
    • 使用地标分析人类运动需要能够处理复杂,非线性数据配置的方法.

    研究的目的:

    • 提出KShapenet,一个新的几何深度学习框架,用于基于2D和3D地标的人类运动分析.
    • 为解决欧几里德深度学习架构对非线性运动数据的局限性.

    主要方法:

    • 将地标配置序列作为Kendall形状空间上的轨迹建模.
    • 将形状空间轨迹映射到线性触点空间,用于结构化数据表示.
    • 采用深度学习架构,一个层优化刚性/非刚性转换,其次是CNN-LSTM网络.

    主要成果:

    • KShapenet在动作和步态识别的3D人类地标序列上表现出了竞争力的表现.
    • 该方法在表情识别中的2D面部里程碑序列中取得了最先进的结果.

    结论:

    • 几何深度学习,特别是KShapenet,为分析复杂的人类运动数据提供了强大的替代方案.

    更多相关视频

    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
    10:23

    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

    Published on: September 8, 2023

    2.8K
    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

    583

    相关实验视频

    Last Updated: Jul 24, 2025

    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
    05:41

    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

    Published on: February 6, 2020

    9.5K
    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
    10:23

    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

    Published on: September 8, 2023

    2.8K
    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

    583
  • 该方法有效地处理里程碑数据中的非线性,推进人类运动分析领域.