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

1,12-cyclic-apelin-12 counters vascular smooth muscle cell proliferation and atherosclerosis through inhibiting aerobic glycolysis.

Toxicology and applied pharmacology·2026
Same author

Transcriptome-Inferred metabolic subtypes define prognostic and immune ecosystems in osteosarcoma at single-cell resolution.

Frontiers in pediatrics·2026
Same author

POU2F3-positive small cell neuroendocrine carcinoma of the urinary tract: a clinicopathological analysis of five cases.

Frontiers in oncology·2026
Same author

N-myristoyltransferase-mediated protein myristoylation: molecular mechanisms, pathological roles, and targeted therapeutic strategies.

Journal of advanced research·2026
Same author

Upregulation of ADAM19 in dendritic cells is associated with immune features and lower C-peptide levels in type 1 diabetes mellitus.

Diabetology & metabolic syndrome·2026
Same author

Construction and Validation of a Nomogram Based on Preoperative Inflammatory Indicators for Predicting Acute Kidney Injury After Pancreaticoduodenectomy.

Journal of inflammation research·2026

相关实验视频

Updated: Jun 25, 2025

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

10.6K

一个自我监督的时空注意力网络,用于基于视频的3D婴儿姿势估计.

Wang Yin1, Linxi Chen2, Xinrui Huang3

  • 1Department of Biomedical Informatics, School of Basic Medical Sciences, Peking University, Beijing 100191, China; Neuroscience Research Institute, Peking University and Key Laboratory for Neuroscience, Ministry of Education/National Health Commission, Beijing 100083, China.

Medical image analysis
|May 24, 2024
PubMed
概括

这项研究引入了用于婴儿姿势估计的先进人工智能模型,改善了对脑 (CP) 等疾病的早期检测. 3D姿势估计方法显著提高了婴儿运动的临床评估.

关键词:
一般的运动评估评估.婴儿姿势估计婴儿姿势估计多视频视频多视图视频.自我监督 自我监督

更多相关视频

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.6K

相关实验视频

Last Updated: Jun 25, 2025

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

10.6K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.6K

科学领域:

  • 计算机视觉 计算机视觉
  • 发育儿科 发育儿科
  • 机器学习 机器学习

背景情况:

  • 在婴儿中早期发现脑 (CP) 对于及时干预至关重要.
  • 现有的人类姿势估计方法缺乏足够的婴儿特定数据集和3D姿势注释.
  • 目前的方法主要集中在成人姿势估计上,限制了婴儿发育中的应用.

研究的目的:

  • 开发准确的2D和3D婴儿姿势估计模型,用于早期检测发育障碍.
  • 通过提出自我监督的学习技术来解决婴儿构成数据的稀缺问题.
  • 为了提高姿势估计的临床实用性,用于一般运动评估 (GMA).

主要方法:

  • 微调的YOLO-infantPose用于2D婴儿姿势估计.
  • 开发了STAPose3D,一个自主监督的3D婴儿姿势估计模型,使用多视图视频.
  • 用时间卷积,时间注意力和图表注意力来学习时空特征.
  • 实施了两阶段的方法:2D姿势估计,然后是3D姿势提升.

主要成果:

  • 微调的YOLO-infantPose在临床和公共婴儿数据集上表现出卓越的性能.
  • STAPose3D有效地利用多视图数据来提高3D婴儿姿势估计准确度.
  • 与2D方法相比,3D姿势估计显著提高了一般运动评估 (GMA) 预测.

结论:

  • 提出的YOLO-infantPose和STAPose3D模型为婴儿姿势估计提供了强大的解决方案.
  • 这些模型提升了早期发现脑和其他发育条件的潜力.
  • 开发的方法有望改善对婴儿一般运动的临床评估.