The paper describes the IBM systems submitted to the NIST Rich Transcription 2007 (RT07) evaluation campaign for the speechto-text (STT) and speaker-attributed speech-to-text (SAST...
In automated multi-label text categorization, an automatic categorization system should output a category set, whose size is unknown a priori, for each document under analysis. Ma...
Claudine Badue, Felipe Pedroni, Alberto Ferreira d...
— We target the problem of predicting resource usage in situations where the modeling data is scarce, non-stationary, or expensive to obtain. This scenario occurs frequently in c...
We present a novel, generic image classification method based on a recent machine learning algorithm (ensembles of extremely randomized decision trees). Images are classified usin...
Justus H. Piater, Louis Wehenkel, Pierre Geurts, R...
This paper addresses the problem of recognizing shadows from monochromatic natural images. Without chromatic information, shadow classification is very challenging because the in...