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

Automatic Processing and Automatic Social Behavior01:28

Automatic Processing and Automatic Social Behavior

210
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
210

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

Three-Dimensional Posture Estimation of Vehicle Occupants Using Depth and Infrared Images.

Sensors (Basel, Switzerland)·2024
Same author

Efficient Model-Based Anthropometry under Clothing Using Low-Cost Depth Sensors.

Sensors (Basel, Switzerland)·2024
Same author

Longitudinal Degradation of Pavement Marking Detectability for Mobile LiDAR Sensing Technology in Real-World Use.

Sensors (Basel, Switzerland)·2023
查看所有相关文章

相关实验视频

Updated: Jan 13, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

通过多模式序列建模进行强大的乘客行为识别:对车载监控系统的比较研究.

Jisu Kim1, Byoung-Keon D Park2

  • 1College of Engineering, University of Nebraska-Lincoln, Lincoln, NE 68588, USA.

Sensors (Basel, Switzerland)
|October 29, 2025
PubMed
概括

这项研究表明,基于注意力的变压器模型擅长使用多式联络数据识别乘客行为. 这些先进的模型为智能运输系统提供了卓越的性能和效率.

关键词:
这是一个2D姿势.这是LSTM的LSTM.在MLP中,MLP是MLP.变压器变压器变压器面部运动 面部运动凝视的估计估计.多模式学习是多模式学习.居住者行为识别识别 居住者行为识别车载人员监控 车载人员监控 车载人员监控序列分类是对序列的分类.时间建模时间建模

更多相关视频

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.3K
Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
07:15

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

4.9K

相关实验视频

Last Updated: Jan 13, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.3K
Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
07:15

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

4.9K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 人与计算机的交互

背景情况:

  • 了解乘客行为对于智能交通系统 (ITS) 的安全至关重要.
  • 多式联网数据融合增强了车辆的情境意识.
  • 当前的ITS系统需要强大的乘客监控.

研究的目的:

  • 为了比较静态,反复和基于注意力的模型,用于多式联网乘客行为识别.
  • 在大型数据集上评估模型性能.
  • 确定车载监控最有效的架构.

主要方法:

  • 利用来自2D姿势,2D目光和面部运动的顺序输入.
  • 比较了多层感知器 (MLP),长短期内存 (LSTM) 和变压器编码器架构.
  • 在使用者行为分类 (OBC) 数据集 (2.1M,79类) 上进行了实验.

主要成果:

  • 时间模型 (LSTM,变压器) 显著优于静态MLP基线.
  • 变压器编码器实现了0.9570.1的最新的Macro F1得分.
  • 变压器在性能和计算效率之间取得了很强的平衡.

结论:

  • 基于注意力的时间建模与多式联络融合对于乘客行为识别是优越的.
  • 变压器架构为高效的车载监控提供了一个实际的框架.
  • 这些发现有助于开发更安全,更有意识的智能交通系统.