We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...
Users frequently modify a previous search query in hope of retrieving better results. These modifications are called query reformulations or query refinements. Existing research h...
Action detection was formulated as a subvolume mutual information maximization problem in [8], where each subvolume identifies where and when the action occurs in the video. Desp...
Abstract. Sponsored search involves running an auction among advertisers who bid in order to have their ad shown next to search results for specific keywords. The most popular auct...
Gagan Aggarwal, Jon Feldman, S. Muthukrishnan, Mar...
The Rich News system, that can automatically annotate radio and television news with the aid of resources retrieved from the World Wide Web, is described. Automatic speech recogni...
Mike Dowman, Valentin Tablan, Hamish Cunningham, B...