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

A dosimetric and treatment delivery comparisons of the Halcyon and TrueBeam stereotactic plans for one or more brain metastases.

Reports of practical oncology and radiotherapy : journal of Greatpoland Cancer Center in Poznan and Polish Society of Radiation Oncology·2026
Same author

Impact of mobile phone usage on dynamic postural control among South Indian college students.

Work (Reading, Mass.)·2024
Same author

CVD-HNet: Classifying Pneumonia and COVID-19 in Chest X-ray Images Using Deep Network.

Wireless personal communications·2022
Same author

A review on deep learning in medical image analysis.

International journal of multimedia information retrieval·2021
Same author

Region-Specific Microstructure in the Neonatal Ventricles of a Porcine Model.

Annals of biomedical engineering·2018
Same author

Evaluation of marginal and internal gaps of metal ceramic crowns obtained from conventional impressions and casting techniques with those obtained from digital techniques.

Indian journal of dental research : official publication of Indian Society for Dental Research·2017

相关实验视频

Updated: May 13, 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

434

一个全面的框架,用于多模式的仇恨言论检测在社交媒体使用深度学习的社交媒体.

R Prabhu1, V Seethalakshmi2

  • 1Department of Information Technology, Dr. Mahalingam College of Engineering and Technology, Pollachi, India. prabhu310591@gmail.com.

Scientific reports
|April 15, 2025
PubMed
概括
此摘要是机器生成的。

这项研究介绍了一种新的多模式仇恨言论检测框架 (MHSDF),使用CNN和RNN准确检测文本,图像和视频中的网上仇恨言论. MHSDF显著提高了复杂的多格式内容的检测准确性和可解释性.

关键词:
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.仇恨言论的识别 仇恨言论的识别经常性的神经网络.社交媒体 社交媒体

更多相关视频

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

2.5K
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

910

相关实验视频

Last Updated: May 13, 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

434
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

2.5K
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

910

科学领域:

  • 人工智能的人工智能
  • 自然语言处理自然语言处理.
  • 计算机视觉 计算机视觉

背景情况:

  • 在线仇恨言论越来越多地是多模式的,结合了文本,图像,音频和视频.
  • 传统的单模检测系统在处理复杂,异构的数据流方面遇到了困难.
  • 微妙的仇恨言论,如meme和刺视频,带来了重要的检测挑战.

研究的目的:

  • 提出一个新的多模式仇恨言论检测框架 (MHSDF),以加强在线仇恨言论的检测.
  • 利用混合深度学习模型 (CNN和RNN) 来分析多模式数据.
  • 提高仇恨言论检测系统的准确性,稳定性和可解释性.

主要方法:

  • 开发了一个混合框架,将卷积神经网络 (CNN) 集成到空间特征提取和循环神经网络 (RNN),特别是长短期记忆 (LSTM),用于序列数据.
  • 使用高级文字嵌入 (Word2Vec,BERT) 来进行文本分析和光学字符识别 (OCR) 来进行图像文本.
  • 实施了注意力机制,以便在各种模式 (文本,图像,音频,视频) 中有效地融合功能.

主要成果:

  • 实现了98.53%的检测精度比,97.64%的稳定性比和99.21%的性能比.
  • 与现有模型相比,可解释性 (97.71%) 和可扩展性 (98.67%) 显著改善.
  • 基于注意力的解释提供了多模式仇恨言论识别的见解,提高了透明度.

结论:

  • 拟议的MHSDF有效地解决了多模式仇恨言论检测的挑战.
  • 混合CNN-RNN方法与注意力机制提供了卓越的性能和可解释性.
  • 这一框架为打击复杂的网上仇恨言论提供了更加透明和强大的解决方案.