End-user interactive machine learning is a promising tool for enhancing human productivity and capabilities with large unstructured data sets. Recent work has shown that we can cr...
Saleema Amershi, James Fogarty, Ashish Kapoor, Des...
Abstract. The wide spread of Peer-to-Peer networks makes multimedia files available to users all around the world. However, Peer-to-Peer networks are often used to spread illegal ...
We present a holistic data-driven approach to image description generation, exploiting the vast amount of (noisy) parallel image data and associated natural language descriptions ...
Polina Kuznetsova, Vicente Ordonez, Alexander C. B...
The problem addressed in this paper is to segment a given multilingual document into segments for each language and then identify the language of each segment. The problem was mot...
This paper presents a new algorithm for sequence prediction over long categorical event streams. The input to the algorithm is a set of target event types whose occurrences we wis...