We systematically evaluate a recently proposed method for unsupervised discrimination power analysis for feature selection and optimization in multimedia applications. A series of...
This paper will describe an approach to the development of computer simulations - the 'four phase' approach - which aims to be more accessible than established approache...
We present a novel framework for learning to interpret and generate language using only perceptual context as supervision. We demonstrate its capabilities by developing a system t...
Inspired by our past manual aspect mining experiences, this paper describes a random walk model to approximate how crosscutting concerns can be discovered in the absence of domain...
Background: Most gene finders score candidate gene models with state-based methods, typically HMMs, by combining local properties (coding potential, splice donor and acceptor patt...
Qian Liu, Koby Crammer, Fernando C. N. Pereira, Da...