In this paper we describe a technique that allows the extraction of multiple local shift-invariant features from analysis of non-negative data of arbitrary dimensionality. Our app...
Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Sh...
In this paper, we present a facial expression recognition method using feature-adaptive motion energy analysis. Our method is simplicityoriented and avoids complicated face model r...
Sungkyu Noh, Hanhoon Park, Yoonjong Jin, Jong-Il P...
In this paper we will show how constraint solving methods can be applied for the recognition of buildings in aerial images. Object models are transformed to constraint representati...
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...