This paper presents a decoupled two stage solution to the multiple-instance learning (MIL) problem. With a constructed affinity matrix to reflect the instance relations, a modified...
Given a classification problem, our goal is to find a low-dimensional linear transformation of the feature vectors which retains information needed to predict the class labels. We...
Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...
We propose a framework for large scale learning and annotation of structured models. The system interleaves interactive labeling (where the current model is used to semiautomate t...
We introduce a novel machine learning framework based on recursive autoencoders for sentence-level prediction of sentiment label distributions. Our method learns vector space repr...
Richard Socher, Jeffrey Pennington, Eric H. Huang,...