Home > News > Gu and Wang Receive Best Paper Award at VDA 2015

Gu and Wang Receive Best Paper Award at VDA 2015

Virginia Watterson • DATE: December 12, 2014

Gu and Wang Receive Best Paper Award at VDA 2015

Yi Gu (left) and Jun Ma (right) looking at the visualization of the MIR Flickr image collection on the 24-tile display wall.

CSE graduate student Yi Gu and Associate Professor Chaoli Wang, along with Jun Ma (Michigan Tech), Robert Nemiroff (Michigan Tech), and David Kao (NASA Ames Research Center) will receive a Best Paper Award for their paper titled "iGraph: A Graph-Based Technique for Visual Analytics of Image and Text Collections", at the IS&T/SPIE Conference on Visualization and Data Analysis, February 9-11, 2015, in San Francisco, California. Yi Gu will present the award paper at the conference.

In our daily lives, images and texts are among the most commonly found data which we need to handle. This award paper presents iGraph, a graph-based approach for visual analytics of large image and text collections. iGraph is a compound graph representation which encodes the underlying relationships among images and texts. To enable effective visual navigation and comprehension of iGraph with tens of thousands of nodes and hundreds of millions of edges, the paper presents a progressive solution that offers collection overview, node comparison, and visual recommendation. iGraph not only allows users to explore the entire collection with representative images and keywords, but also supports detailed comparison for understanding and intuitive guidance for navigation. For performance speedup, the implementation utilizes multiple GPUs and CPUs for processing and visualization in parallel. In addition, a display wall of nearly 50 million pixels is leveraged to allow more than a dozen of people to comfortably view and discuss the results together in the collaborative environment.