Date Added: Oct 2012
Social information networks, such as YouTube, contains traces of both explicit online interaction (such as like, leaving a comment, or subscribing to video feed), and latent interactions (such as quoting, or remixing parts of a video). The authors propose visual memes, or frequently re-posted short video segments, for tracking such latent video interactions at scale. Visual memes are extracted by scalable detection algorithms that they develop, with high accuracy. They further augment visual memes with text, via a statistical model of latent topics. They model content interactions on YouTube with visual memes, defining several measures of influence and building predictive models for meme popularity. Experiments are carried out on with over 2 million video shots from tens of thousands of videos.