![](/image/LogoVKU.png)
Please use this identifier to cite or link to this item:
https://elib.vku.udn.vn/handle/123456789/3828
Title: | Multi-Task Learning Model for Detecting and Filtering Internet Violent Images for Children |
Other Titles: | Xây dựng bộ nhận diện và lọc hình ảnh bạo lực, nhạy cảm trên website cho trẻ em |
Authors: | Nguyen, Huu Nhat Minh Le, Kim Hoang Trung Nguyen, Van Thanh Vinh Phan, Le Viet Hung Pham, Cong Tinh Ha, Van Viet |
Keywords: | Multi-task learning and Violence detection and Web extension |
Issue Date: | Jun-2024 |
Publisher: | Vietnam - Korea University of Information and Communication Technology |
Series/Report no.: | NCKHSV; |
Abstract: | The Internet has emerged as an essential daily information access, but exposing children to inappropriate content can impair their early development. Existing content filtering methods exhibit limitations in accurately and efficiently detecting diverse inappropriate internet content. In this paper, we propose a multi-task learning model for detecting and filtering violent images to provide safer online experiences. The multi-task model is developed from the pre-trained lightweight base model such as MobileNetv2 to enable proper integration within web browser extensions. Pure training to detect violent images could raise false alarms in the classification results when the landscape or object images don't contain any human, hence we develop two joint learning tasks such as detecting humans and detecting violent images simultaneously. Our experiments demonstrate that the proposed multi-task approach with binary rule achieves 98.5\% accuracy, outperforming the single-task model for detecting violent images by a margin. Thereafter, the multi-task model is also integrated into the web extension to detect and filter out violent images to prevent children from harmful content. |
Description: | Kỷ yếu Nghiên cứu khoa học của sinh viên Trường Đại học Công nghệ Thông tin và Truyền thông Việt - Hàn năm học 2023-2024; trang 41-45 |
URI: | https://elib.vku.udn.vn/handle/123456789/3828 |
Appears in Collections: | SV NCKH Năm học 2023-2024 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.