||In the last few years, deep convolutional neural networks have become ubiquitous in computer vision, achieving state-of-the-art results on problems like object detection, semantic segmentation, and image captioning. In this talk, I will present a system for word spotting based on convolutional neural networks. We train a network to extract a powerful image representation, which we then embed into a word embedding space. This allows us to perform word spotting using both query-by-string and query-by-example in a variety of word embedding spaces, both learned and handcrafted, for verbatim as well as semantic word spotting. Using this approach we outperform the previous state-of-the-art systems for word spotting on standard datasets. Finally, I will talk about some of the recent improvements made to this system.