My research interests lie at the boundary of computer vision and natural language processing, specifically focused on understanding the connections between these two related modalities. Today billions of images with associated text are available on web pages, captioned photographs, video with speech or closed captioning, and many others. In order to organize, search, and exploit these enormous collections we work on developing methods that combine information from both the visual and textual sources effectively. Past and current projects include: automatically identifying people in news photographs, classifying images from the web, selecting aesthetically pleasing or interesting images, generating natural language descriptions for images, visual social media analysis, and recognizing clothing and style.