Until now, Facebook’s photo captions were only able to use nouns to describe objects in pictures posted online. That’s okay, if you are only interested in the objects in the photos. But what if you are interested in the actions that take place in the images?
Facebook has added twelve verbs to its neural network that provide for more detailed description of the contents of all those photos on their website.
Per Facebook’s applied machine learning leader Joaquin Candela, image descriptions will now include things like people walking, people dancing, people riding horses, and people playing instruments,
It’s a good thing when blind people are provided with more information, especially on Facebook, where many feel excluded by a social network that communicates mainly by posting photos.
