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

Parallel Processing01:20

Parallel Processing

182
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
182

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

Concrete Crack Detection and Segregation: A Feature Fusion, Crack Isolation, and Explainable AI-Based Approach.

Journal of imaging·2024
Same author

A Lightweight Image Encryption Algorithm Based on Chaotic Map and Random Substitution.

Entropy (Basel, Switzerland)·2023
Same author

A 3DCNN-Based Knowledge Distillation Framework for Human Activity Recognition.

Journal of imaging·2023
Same author

Automatic 360° Mono-Stereo Panorama Generation Using a Cost-Effective Multi-Camera System.

Sensors (Basel, Switzerland)·2020

相关实验视频

Updated: Jul 21, 2025

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

3.8K

人类活动识别使用级联双重注意力CNN和双向GRU框架

Hayat Ullah1, Arslan Munir1

  • 1Department of Computer Science, Kansas State University, Manhattan, KS 66506, USA.

Journal of imaging
|July 28, 2023
PubMed
概括

这项研究引入了一种高效的双注意力卷积神经网络 (DA-CNN) 和双向封闭循环单元 (Bi-GRU) 框架,用于人类活动识别 (HAR). 该模型提高了准确性和计算效率,达到167倍更快的推断速度.

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 基于视觉的人类活动识别 (HAR) 对视频分析至关重要.
  • 现有的HAR深度学习方法通常在准确性和计算效率之间进行权衡.
  • 需要HAR模型,既准确又计算高效.

研究的目的:

  • 为HAR提出一个计算效率高和通用的时空级联框架.
  • 提高人类活动识别模型的准确性和计算效率.
  • 为了解决当前HAR方法的局限性,优先考虑性能或效率.

主要方法:

  • 开发了一种高效的双注意力卷积神经网络 (DA-CNN),用于使用统一的通道空间注意力机制提取突出特征.
  • 采用堆叠的双向封闭循环单元 (Bi-GRU) 进行长期时间建模和动作识别.
  • 将DA-CNN和Bi-GRU集成到一个级联的空间时间特征利用框架中.

主要成果:

  • 拟议的DA-CNN+Bi-GRU框架在三个公开的HAR数据集上表现出优于最先进的方法的性能.
  • 在模型准确性和推理运行时间方面取得了显著的改进.
  • 与当代方法相比,表现出高达167倍的每秒的执行时间改进.
关键词:
活动识别活动识别道空间注意力卷积神经网络是一种卷积神经网络.深度学习是一种深度学习.有门的循环单元.模式识别 模式识别 模式识别

更多相关视频

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

572
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

相关实验视频

Last Updated: Jul 21, 2025

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

3.8K
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

572
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

结论:

  • DA-CNN+Bi-GRU框架有效地平衡了HAR的准确性和计算效率.
  • 拟议的模型为实时视频分析任务提供了强大的解决方案.
  • 这种方法通过提供高效和准确的模型来推进基于视觉的人类活动识别领域.