☆ 4.5 Article

ASYv3: Attention-enabled pooling embedded Swin transformer-based YOLOv3 for obscenity detection

EXPERT SYSTEMS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

SBMYv3: Improved MobYOLOv3 a BAM attention-based approach for obscene image and video detection

Sonali Samal et al.

Summary: This paper proposes a deep learning approach for detecting and labelling obscene content, and generates a well-labelled dataset with various augmentation strategies. It also introduces modifications to the backend architecture and pooling strategy to improve recognition accuracy. The proposed model outperforms other state-of-the-art models in testing accuracy, recall, precision, and IoU values.

EXPERT SYSTEMS (2023)

添加到收藏夹

Article Remote Sensing

Preserving Privacy of Classified Authentic Satellite Lane Imagery Using Proxy Re-Encryption and UAV Technologies

Yarajarla Nagasree et al.

Summary: With the rapid growth of technology, the privacy preservation of image data has become crucial due to the increased possibility of creating fake images on social media. This research proposes a real-time solution that classifies lane images as fake or bona fide using ELA and ANN algorithms, and ensures privacy by detecting lanes using the U-Net model.

DRONES (2023)

添加到收藏夹

Article Computer Science, Information Systems

Obscene image detection using transfer learning and feature fusion

Sonali Samal et al.

Summary: In this study, an automatic pornographic image detection method using transfer learning and feature fusion is proposed. The method improves model performance and reduces computational burden by fusing low-level and mid-level features. Experimental results show that the proposed method achieves excellent performance in detecting pornographic images with an average classification accuracy of 98.50%.

MULTIMEDIA TOOLS AND APPLICATIONS (2023)

添加到收藏夹

Article Astronomy & Astrophysics

Benchmarking deep learning approaches for all-vs-all conjunction screening

Emma Stevenson et al.

ADVANCES IN SPACE RESEARCH (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

LEOBAT: Lightweight encryption and OTP based authentication technique for securing IoT networks

Aarti Goel et al.

Summary: This research proposes an authentication-based solution for designing a secure communication network to ensure safe access to data and prevent attackers from unauthorized access to various IoT applications. The proposed technique, LEOBAT, is shown to be fast and efficient through comparison with other popular cryptosystems.

EXPERT SYSTEMS (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Efficient Fake News Detection using Bagging Ensembles of Bidirectional Echo State Networks

Javier Del Ser et al.

Summary: The dissemination of fake news is a concerning issue in digital media, and researchers have been working on automating the identification of fake news using AI methods. This study proposes a novel approach based on randomization-based recurrent neural networks, which achieve competitive detection results with lower computational complexity compared to deep learning models.

2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) (2022)

添加到收藏夹

Article Automation & Control Systems

A comprehensive survey on digital video forensics: Taxonomy, challenges, and future directions

Abdul Rehman Javed et al.

Summary: This paper presents a comprehensive survey on information extraction from video contents and forgery detection, reviewing various modern techniques such as computer vision and different machine learning algorithms, including deep learning for video forgery detection.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Transfer Detection of YOLO to Focus CNN's Attention on Nude Regions for Adult Content Detection

Nouar AlDahoul et al.

Summary: This study explores the use of deep learning techniques in automatically detecting and classifying pornography and nudity content in videos for censorship purposes. By utilizing convolutional neural networks, support vector machines, and the YOLO object detector, the research found that ResNet101 with random forest outperforms other models in nude/normal classification, achieving an accuracy of 87.75%.

SYMMETRY-BASEL (2021)

添加到收藏夹

Article Chemistry, Multidisciplinary

An Enhanced Multimodal Stacking Scheme for Online Pornographic Content Detection

Kwangho Song et al.

APPLIED SCIENCES-BASEL (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Adult content detection in videos with convolutional and recurrent neural networks

Jonatas Wehrmann et al.

NEUROCOMPUTING (2018)

添加到收藏夹

Article Metallurgy & Metallurgical Engineering

Detection of artificial pornographic pictures based on multiple features and tree mode

Mao Xing-liang et al.

JOURNAL OF CENTRAL SOUTH UNIVERSITY (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Explicit Content Detection System: An Approach towards a Safe and Ethical Environment

Ali Qamar Bhatti et al.

APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Video pornography detection through deep learning techniques and motion information

Mauricio Perez et al.

NEUROCOMPUTING (2017)

添加到收藏夹

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

添加到收藏夹

Article Sociology

Characterizing Cyberbullying among College Students: Hacking, Dirty Laundry, and Mocking

Rajitha Kota et al.

SOCIETIES (2014)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Pooling in image representation: The visual codeword point of view

Sandra Avila et al.

COMPUTER VISION AND IMAGE UNDERSTANDING (2013)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.