Abstract--Recently, the following discrimination aware classification problem was introduced: given a labeled dataset and an attribute , find a classifier with high predictive accu...
We derive two variants of a semi-supervised model for fine-grained sentiment analysis. Both models leverage abundant natural supervision in the form of review ratings, as well as...
We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
Meeting summarization provides a concise and informative summary for the lengthy meetings and is an effective tool for efficient information access. In this paper, we focus on ext...
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...
Abhinav Gupta, Trista Chen, Francine Chen, Don Kim...