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

Facial Feedback Hypothesis01:24

Facial Feedback Hypothesis

147
Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role...
147

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

Object-Aware Computational Integral Imaging for Improved Object Depth Estimation and Stereo Matching Training.

Sensors (Basel, Switzerland)·2026
Same author

From myth to model: Representation of "the Jew" in generative AI.

The American psychologist·2026
Same author

Concealed Face Analysis and Facial Reconstruction via a Multi-Task Approach and Cross-Modal Distillation in Terahertz Imaging.

Sensors (Basel, Switzerland)·2026
Same author

Beyond Valence and Arousal: Distributed Facial Patterns Linked to Specific Emotions Cannot be Reduced to Core Affect.

Affective science·2026
Same author

Memory justifications provide valid indicators of retrieval accuracy across time.

Communications psychology·2025
Same author

Do People Listen to Cassandra? Persuasion and Accuracy in Geopolitical Forecasts.

Personality & social psychology bulletin·2025

相关实验视频

Updated: Jun 27, 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

3.7K

基于通过深度学习从短视频中提取的脉动图像的情感分类.

Shlomi Talala1, Shaul Shvimmer1, Rotem Simhon2

  • 1Department of Electro-Optics and Photonics Engineering, School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva 84105, Israel.

Sensors (Basel, Switzerland)
|April 27, 2024
PubMed
概括

这项研究开发了一种使用面部视频来检测生理信号的远程情绪识别方法,提高了不依赖面部表情的准确性. 该方法使用EfficientNet-B0模型和RGB摄像头数据实现了47.36%的准确性.

关键词:
基于摄像头的个人防护服深度学习是一种深度学习.情绪的分类 情绪的分类脉动的信号信号是脉动的信号.rPPGG 这是一个很好的选择.远程情绪识别 远程情绪识别

更多相关视频

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

15.2K
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.0K

相关实验视频

Last Updated: Jun 27, 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

3.7K
Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

15.2K
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.0K

科学领域:

  • 物理计算的物理计算.
  • 情感计算是一种情感计算.
  • 机器学习用于情绪识别和识别.

背景情况:

  • 传统的情绪识别依赖于面部表情,这可能不反映真实的情绪状态.
  • 微妙或隐藏的情绪,特别是在被动观看时,很难用基于表达的方法来检测.
  • 物理信号的遥感为情绪分类提供了一个非侵入性的替代方案.

研究的目的:

  • 改进使用来自面部视频的生理信号的远程情绪分类方法.
  • 为了提高心率估计和心跳检测,以便更准确地分析情绪.
  • 为了实现更好的情绪分类准确度,使用只使用RGB相机数据的深度学习.

主要方法:

  • 利用了来自110名参与者被动观看引起情绪的视频的短视频数据.
  • 采用了通过皮肤传感的心血管空间时空面部模式的遥感.
  • 应用机器学习,特别是EfficientNet-B0模型,对五种情绪类型进行分类 (娱乐,厌恶,恐惧,性兴奋,没有情绪).
  • 整合了皮肤细分的改进,用于心率估计和心跳峰值/低谷检测.

主要成果:

  • 一个EfficientNet-B0模型在情绪分类方面实现了47.36%的整体平均准确率.
  • 这种准确性是使用RGB摄像机仅使用单个时空特征图得到的.
  • 这项研究证明了通过生理模式进行远程情绪感知的可行性.

结论:

  • 从面部视频中遥感生理模式是一种可行的情绪识别方法.
  • 像EfficientNet-B0这样的深度学习模型可以有效地使用RGB摄像头的生理数据来分类情绪.
  • 进一步的研究可以改进这些方法,以更准确和更强大的情绪检测.