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...
This paper presents a novel approach to pedestrian classification which involves utilizing the synthesized virtual samples of a learned generative model to enhance the classificat...
We investigate the challenging issue of joint audio-visual analysis of generic videos targeting at semantic concept detection. We propose to extract a novel representation, the Sh...
Wei Jiang, Courtenay V. Cotton, Shih-Fu Chang, Dan...
This paper introduces a new method using dyadic decision trees for estimating a classification or a regression function in a multiclass classification problem. The estimator is bas...
We show that forms of Bayesian and MDL inference that are often applied to classification problems can be inconsistent. This means that there exists a learning problem such that fo...