Pornography Detection in Video Benefits (a lot) from a Multi-modal Approach

Adrian Ulges, Christian Schulze, Damian Borth, Armin Stahl
Proceedings of the International Conference on Multimedia, Nara, Japan, ACM, ACM, 10/2012


We address the challenge of detecting pornographic content in video streams. On offensive material crawled from dif- ferent pornographic websites and non-offensive clips from YouTube (a total of 500 hours of video), we first study a compressed-domain activity descriptor based on MPEG motion compensation vectors. We show that the approach offers an interesting alternative but generalizes poorly be- tween videos compressed with different codecs, a problem that can be overcome to some extent by adding noise to the image data prior to video compression. Our main contribution is an evaluation that benchmarks the above motion-based descriptor as well as three other widely used features (audio-based MFCC features, skin color detection, and visual words). Here, we show that a multi- modal approach is a key strategy for an accurate detection or adult content: A combination of the different features gives considerable improvements in accuracy, reducing equal error by 36–56% compared to the best uni-modal system.




@inproceedings{ ULGE2012,
	Title = {Pornography Detection in Video Benefits (a lot) from a Multi-modal Approach},
	Author = {Adrian Ulges and Christian Schulze and Damian Borth and Armin Stahl},
	BookTitle = {Proceedings of the International Conference on Multimedia},
	Month = {10},
	Year = {2012},
	Publisher = {ACM},
	Organization = {ACM}

Last modified:: 30.08.2016