Report: PornHub Artificial Intelligence IDs Actors, Acts

Report: PornHub Artificial Intelligence IDs Actors, Acts
Stephen Yagielowicz

LOS ANGELES — An increasing number of top-tier adult companies are leveraging the power of artificial intelligence, computer vision, and machine learning, in an effort to better serve customers searching for something specific — a process akin to finding a needle in a haystack made up of millions of porn videos.

In an article for TechCrunch entitled “PornHub uses computer vision to ID actors, acts in its videos,” author John Biggs took a look at the popular tube site’s use of artificial intelligence and data analysis, exploring how the site, which receives a reported 80 million daily visitors, “found that its old, antiquated methods of tagging videos by hand was not sufficient.”

“Ultimately, we want to provide our fans with whatever it is they have a penchant for and our new model will be able to surface more accurate results for them, which will hopefully keep them coming back for more,” PornHub VP Corey Price told Biggs. “It’s all about continuously updating our platform to provide our fans with the latest in technology to make their experience on our platform as seamless as possible. The easier it is to navigate and access what they want, the happier they will be.”

Price says the company uses computer vision to identify specific actors, various positions, attributes and more in real time.

“So far we’ve used the model on about 500k featured videos which include user submitted and we plan to scan the whole library in the beginning of 2018,” Price adds. “Very shortly, the technology will also be used to detect various sex positions/categories and be able to properly tag them as well.”

PornHub is not alone in using AI to analyze, categorize, and make more readily accessible prodigious amounts of adult content, using facial recognition and other techniques to enhance the search and discovery process — illustrating how the industry remains at the forefront of technology.

Related: