Spatiotemporal CNNs for Pornography Detection in Videos

TL;DR

This paper evaluates two spatiotemporal CNNs, VGG-C3D and ResNet R(2+1)D, for pornography detection in videos, demonstrating their superior performance over traditional methods with an accuracy of 95.1%.

Contribution

It introduces and assesses the effectiveness of two specific spatiotemporal CNN architectures for video pornography detection.

Findings

VGG-C3D and ResNet R(2+1)D CNNs outperform bag of visual words methods.

Achieve 95.1% accuracy on Pornography-800 dataset.

Competitive with other CNN-based approaches.

Abstract

With the increasing use of social networks and mobile devices, the number of videos posted on the Internet is growing exponentially. Among the inappropriate contents published on the Internet, pornography is one of the most worrying as it can be accessed by teens and children. Two spatiotemporal CNNs, VGG-C3D CNN and ResNet R(2+1)D CNN, were assessed for pornography detection in videos in the present study. Experimental results using the Pornography-800 dataset showed that these spatiotemporal CNNs performed better than some state-of-the-art methods based on bag of visual words and are competitive with other CNN-based approaches, reaching accuracy of 95.1%.