In this paper, we propose a framework for isolating text regions from natural scene images. The main algorithm has two functions: it generates text region candidates, and it veriļ...
We investigate the automatic labelling of āeventsā from an audio recording of a sports game. We describe a technique that utilises a hierarchy of language models, which are a ...
In this paper, we propose a support vector machine with automatic confidence (SVMAC) for gender classification based on facial images. Namely, we explore how to incorporate confide...
The goal of emotion classiļ¬cation is to estimate an emotion label, given representative data and discriminative features. Humans are very good at deriving high-level representat...
Various semi-supervised learning methods have been proposed recently to solve the long-standing shortage problem of manually labeled data in sentiment classification. However, mos...