We explore the problem of budgeted machine learning, in which the learning algorithm has free access to the training examples’ labels but has to pay for each attribute that is s...
Kun Deng, Chris Bourke, Stephen D. Scott, Julie Su...
This paper presents a principled and practical method for the computation of visual saliency of spatiotemporal events in full motion videos. Based on the assumption that uniquenes...
We propose an unsupervised “local learning” algorithm for learning a metric in the input space. Geometrically, for a given query point, the algorithm finds the minimum volume ...
Our goal in this work has been to bring together the entertaining and flow characteristics of video game environments with proven learning theories to advance the state of the art ...
Jason Tan, Chris Beers, Ruchi Gupta, Gautam Biswas
Melodies provide an important conceptual summarization of polyphonic audio. The extraction of melodic content has practical applications ranging from content-based audio retrieval...