Translating images to words

Posted to Statistics  |  Tags: , ,  |  Nathan Yau

With Google’s image search, the results kind of exist in isolation. There isn’t a ton of context until you click through to see how an image is placed among words. So, researchers at Google are trying an approach similar to how they translate languages to automatically create captions for the images.

Now Oriol Vinyals and pals at Google are using a similar approach to translate images into words. Their technique is to use a neural network to study a dataset of 100,000 images and their captions and so learn how to classify the content of images.

But instead of producing a set of words that describe the image, their algorithm produces a vector that represents the relationship between the words. This vector can then be plugged into Google’s existing translation algorithm to produce a caption in English, or indeed in any other language. In effect, Google’s machine learning approach has learnt to “translate” images into words.

Favorites

Best Data Visualization Projects of 2016

Here are my favorites for the year.

Years You Have Left to Live, Probably

The individual data points of life are much less predictable than the average. Here’s a simulation that shows you how much time is left on the clock.

The Changing American Diet

See what we ate on an average day, for the past several decades.

10 Best Data Visualization Projects of 2015

These are my picks for the best of 2015. As usual, they could easily appear in a different order on a different day, and there are projects not on the list that were also excellent.