In this paper, we learn the components of dialogue POMDP models from data. In particular, we learn the states, observations, as well as transition and observation functions based o...
Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised man...
We propose a novel semi-supervised method for building a statistical model that represents the relationship between sounds and text labels (“tags”). The proposed method, named...
Jun Takagi, Yasunori Ohishi, Akisato Kimura, Masas...
Extensive labeled data for image annotation systems, which learn to assign class labels to image regions, is difficult to obtain. We explore a hybrid model framework for utilizing...
We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail we are given a set ...