A Multimodal CNN-based Tool to Censure Inappropriate Video Scenes

TL;DR

This paper introduces a multimodal CNN-based system that detects and censors inappropriate scenes in videos by analyzing audio and visual features, achieving high accuracy in classification.

Contribution

It presents a novel multimodal CNN architecture for identifying and automatically censoring inappropriate video segments, improving content moderation capabilities.

Findings

Achieved over 98.9% F1-score in classifying appropriate and inappropriate scenes.

Developed an automatic tool for censoring inappropriate video segments.

Demonstrated effectiveness of multimodal approach in content moderation.

Abstract

Due to the extensive use of video-sharing platforms and services for their storage, the amount of such media on the internet has become massive. This volume of data makes it difficult to control the kind of content that may be present in such video files. One of the main concerns regarding the video content is if it has an inappropriate subject matter, such as nudity, violence, or other potentially disturbing content. More than telling if a video is either appropriate or inappropriate, it is also important to identify which parts of it contain such content, for preserving parts that would be discarded in a simple broad analysis. In this work, we present a multimodal~(using audio and image features) architecture based on Convolutional Neural Networks (CNNs) for detecting inappropriate scenes in video files. In the task of classifying video files, our model achieved 98.95\% and 98.94\% of F1-score for the appropriate and inappropriate classes, respectively. We also present a censoring tool that automatically censors inappropriate segments of a video file.