In this paper, we propose a generative model to automatically discover the hidden associations between topics words and opinion words. By applying those discovered hidden associat...
This paper describes a new representation for the audio and visual information in a video signal. We reduce the dimensionality of the signals with singular-value decompositions (S...
The author proposed three studies (i.e. a large-N survey, a behavioral experiment, and a functional magnetic resonance imaging research) to investigate whether people read icons a...
Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...
In this paper, we propose a color image enhancement method that uses retinex with a robust envelope to improve the visual appearance of an image. The word "retinex" is h...