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

Correction: Reciprocal cooperative gating fusion of SqueezeNet and ShuffleNetV2 for breast cancer detection in histopathology images.

Scientific reports·2026
Same author

A two-stage preprocessing and classification approach for accurate COVID-19 detection in X-ray images.

Scientific reports·2026
Same author

A dual-branch deep learning framework for emotion recognition from EEG signals.

Scientific reports·2026
Same author

Reciprocal cooperative gating fusion of SqueezeNet and ShuffleNetV2 for breast cancer detection in histopathology images.

Scientific reports·2026
Same author

Corrigendum to "Image segmentation with Cellular Automata" [Heliyon Volume 10, Issue 10, May 2024, Article e31152].

Heliyon·2025
Same author

JUHCCR-v1: a database for hand-drawn electrical and electronics circuit component recognition.

Scientific reports·2025
Same journal

Novel Parent Survey Measures Sensory Behaviors Incorporating Sensory Modality and Stimulus Intensity.

Heliyon·2026
Same journal

Expression of concern: "SQSTM1/p62 promotes the progression of gastric cancer through epithelial-mesenchymal transition" [Heliyon 10 (2024) e24409].

Heliyon·2026
Same journal

Expression of concern: "TL1A promotes metastasis and EMT process of colorectal cancer" [Heliyon 10 (2024) e24392].

Heliyon·2026
Same journal

Expression of concern: "Factors affecting timing of surgery following neoadjuvant chemoradiation for esophageal cancer" [Heliyon 9 (2023) e23212].

Heliyon·2026
Same journal

Expression of concern: "On stratified single-valued soft topogenous structures" [Heliyon 10 (2024) e27926].

Heliyon·2026
Same journal

Expression of concern: "Artifact removal and motor imagery classification in EEG using advanced algorithms and modified DNN" [Heliyon 10 (2024) e27198].

Heliyon·2026
查看所有相关文章

相关实验视频

Updated: Jun 5, 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

468

使用深度特征堆叠和元学习进行深度假冒检测.

Gourab Naskar1, Sk Mohiuddin2, Samir Malakar3

  • 1Department of Computer Science and Engineering, Jadavpur University, Kolkata, 700032, India.

Heliyon
|December 13, 2024
PubMed
概括
此摘要是机器生成的。

这项研究引入了一种新的深度假冒检测方法,该方法结合了Xception和EfficientNet-B7的功能. 该方法在识别假视频方面实现了高准确性,优于单个模型.

关键词:
深度学习是一种深度学习.这是一个深度假的Deepfake.功能选择 功能选择超级学习 (Meta-learning) 是一种学习方式.基于堆叠的合奏组合.

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

9.0K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

954

相关实验视频

Last Updated: Jun 5, 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

468
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

954

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:

  • 深度假冒技术使视频中的真实面部操纵成为可能.
  • 恶意使用深度假冒可以导致错误信息和网络欺凌.
  • 有效的深度假冒检测对于数字安全至关重要.

研究的目的:

  • 开发一种准确和强大的方法来检测视频序列中的深度假冒.
  • 为满足对合成介质可靠识别的日益增长的需求.

主要方法:

  • 一种堆叠组合方法,结合了Xception和EfficientNet-B7深度学习模型的功能.
  • 一种使用基于排名的方法来识别最佳特征子集的特征选择技术.
  • 使用元学习器,特别是多层感知器,对真实和假的视频进行最终分类.

主要成果:

  • 在Celeb-DF (V2) 数据集上实现了96.33%的准确性.
  • 在FaceForensics++数据集上实现了98.00%的准确性.
  • 与单个基础模型相比,超级学习模型表现出更高的性能.

结论:

  • 拟议的组合方法与meta-learning对于深度假冒的检测非常有效.
  • 该方法在基准数据集上显示出稳定性和高准确性.
  • 这种技术为打击恶意深度假冒内容提供了一个有希望的解决方案.