We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
We present a general learning-based approach for phrase-level sentiment analysis that adopts an ordinal sentiment scale and is explicitly compositional in nature. Thus, we can mod...
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...
Multilingual parallel text corpora provide a powerful means for propagating linguistic knowledge across languages. We present a model which jointly learns linguistic structure for...
Resource limited DRE (Distributed Real-time Embedded) systems can benefit greatly from dynamic adaptation of system parameters. We propose a novel approach that employs iterative t...
Minyoung Kim, Mark-Oliver Stehr, Carolyn L. Talcot...