Every day large numbers of photos and videos are posted in social media. With the advent of modern deep learning, it is now possible to automatically analyze this content to get more in-depth insights.

In this talk I will present three hands-on examples of how deep neural networks can be applied for social media content analysis. First, I'll present our neural network architecture used to detect logotypes in the videos given a limited amount of training data. Then I will show a working example of text-in-the-wild extraction (detection and recognition) pipeline. Last but not least, I'll show how video thumbnails can be used to predict video popularity.