We present a novel approach for classifying documents that combines different pieces of evidence (e.g., textual features of documents, links, and citations) transparently, through...
Adriano Veloso, Wagner Meira Jr., Marco Cristo, Ma...
The ability to predict the quality of a software object can be viewed as a classification problem, where software metrics are the features and expert quality rankings the class lab...
Abstract--Context plays a valuable role in any image understanding task confirmed by numerous studies which have shown the importance of contextual information in computer vision t...
Sobhan Naderi Parizi, Ivan Laptev, Alireza Tavakol...
We describe an approach to unsupervised high-accuracy recognition of the textual contents of an entire book using fully automatic mutual-entropy-based model adaptation. Given imag...
Multilayered feedforward neural networks possess a number of properties which make them particularly suited to complex pattern classification problems. However, their application ...