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

An extracellular polysaccharide from Aspergillus versicolor ameliorates palmitate-induced insulin resistance in HepG2 cells.

Scientific reports·2026
Same author

Dual-Function Halide Exchange Strategy for Simultaneous Sn<sup>4+</sup> Elimination and Stability Enhancement in Pb-Sn Mixed Perovskite Solar Cells.

ACS nano·2026
Same author

Longitudinal symptom dynamics in postoperative patients with liver cancer: A cross-lagged panel network analysis.

Asia-Pacific journal of oncology nursing·2026
Same author

A rare case of massive upper gastrointestinal bleeding caused by Brunner's gland adenomas combined with a neuroendocrine tumor.

Endoscopy·2026
Same author

Barriers and facilitators of the implementation of a leadership training program based on the Developing and Sustaining Nursing Leadership Best Practice Guideline: A qualitative study.

International journal of nursing sciences·2026
Same author

A Prosthetic Hand System by Contralateral-Collaborative Control Based on Multi-task Learning.

IEEE journal of biomedical and health informatics·2026

相关实验视频

Updated: Jun 29, 2025

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

529

一项基于改进的移动网络V2网络的表情识别研究.

Qiming Zhu1, Hongwei Zhuang2, Mi Zhao3

  • 1College of Equipment Support and Management, Engineering University of PAP, Xi'an, 710086, China.

Scientific reports
|April 6, 2024
PubMed
概括
此摘要是机器生成的。

这项研究引入了一个改进的MobileNetV2 (I-MobileNetV2) 面部情绪识别,显著减少参数,同时提高准确性. 增强型号解决了功能丢失,并改善了实时性能,以更好地检测情绪.

关键词:
注意力机制注意力机制表情识别功能表达式识别功能移动网络V2 移动网络V2反向核聚变可以实现.塞卢 (SELU) 是一种葡萄酒.

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.1K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.1K

相关实验视频

Last Updated: Jun 29, 2025

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

529
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.1K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.1K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 深层卷积神经网络通常具有很大的参数数量.
  • 像MobileNetV2这样的轻量级神经网络可能会遭受功能信息丢失,实时性能差以及面部情绪识别的准确性低.

研究的目的:

  • 为面部情绪识别提出一个改进的MobileNetV2 (I-MobileNetV2) 策略.
  • 解决现有模型的局限性,包括大参数数量和特征信息丢失.

主要方法:

  • 从MobileNetV2中继承了深度可分离的卷积,以减少计算负载.
  • 整合了反向融合机制,以保留负面特征并最大限度地减少信息丢失.
  • 用SELU取代RELU6激活功能,以防止梯度消失.
  • 整合了Squeeze-and-Excitation Networks (SE-Net) 的注意力道机制,以提高特征识别.

主要成果:

  • 在FER2013上,I-MobileNetV2模型实现了68.62%的准确性,在CK+数据集上达到95.96%.
  • 与原来的MobileNetV2.2.相比,精度提高了0.72% (FER2013) 和6.14% (CK+),比原来的MobileNetV2.2.更准确.
  • 参数数量减少了83.8%,表明更轻的模型.

结论:

  • 拟议的I-MobileNetV2模型显示了面部情绪识别准确性和效率的显著改进.
  • 反向融合,SELU激活和SE-Net的集成有效地提高了特征识别,并降低了模型的复杂性.