Meloria • Ever Better
Search Tools Main Menu

Currents

April 05, 2016

Research News

Grant supports pediatric asthma research

Jill Halterman, professor of pediatrics, has received a $3.6 million grant from the National Institutes of Health to research a preventive asthma intervention that could help patients better manage their condition while reducing acute emergency room visits.

The five-year study will help connect pediatric asthma patients with primary care providers to follow up after emergency visits for asthma. The follow-ups would take place via telemedicine in children’s school health offices, ensuring easy access.

The research builds on several of Halterman’s previous studies, which have attempted to improve the delivery of preventive asthma care, particularly for those from low-income families. She has also explored methods to promote the proper use of and adherence to asthma medications through partnerships with schools and school nurses.

First ‘real big test’ of immunotherapy for lymphoma under way

Wilmot Cancer Institute is part of a national clinical trial for an innovative new therapy that involves engineering a patient’s own immune cells to attack cancer, in this case lymphoma. Called CAR T-cell therapy, the approach is touted as one of the most powerful cancer treatments to emerge from research laboratories in years.

Jonathan Friedberg, director of the Wilmot Cancer Institute who holds the Samuel E. Durand Chair in Medicine, and Patrick Reagan, a senior instructor, are leading the study at Wilmot.

Rochester team leads competition for best computer-generated captions

A team of Rochester and Adobe researchers is outperforming teams with other approaches to creating computer-generated image captions in an international competition. The key to their winning approach? Thinking about words—what they mean and how they fit in a sentence structure—just as much as thinking about the image itself.

The Rochester/Adobe model mixes the two approaches that are often used in image captioning: the “top-down” approach, which starts from the “gist” of the image and then converts it into words, and the “bottom-up” approach, which first assigns words to different aspects of the image and then combines them to form a sentence.

The Rochester/Adobe model is currently beating Google, Microsoft, Baidu/UCLA, Stanford University, University of California Berkeley, University of Toronto/Montreal, and others in an image- captioning competition run by Microsoft called the Microsoft COCO Image Captioning Challenge.

The team is formed by Jiebo Luo, associate professor of computer science; doctoral student Quanzeng You; and Adobe collaborators Hailin Jin, Zhaowen Wang, and Chen Fang.

Previous story    Next story