Full Panel
Panelists
Virginia Kuhn, University of Southern California; Alan Craig, University of Illinois, Urbana Champaign; Ritu Aurora, University of Texas; Michael Simeone, University of Illinois at Urbana Champaign
Biographies
Dr. Virginia Kuhn serves as associate director of the Institute for Multimedia Literacy, and assistant professor of cinema practice in the USC School of Cinematic Arts. She directs an undergraduate Honors program, oversees faculty in the IML Digital Studies minor and teaches a variety of graduate and undergraduate classes in new media, all of which marry theory and practice. She was the 2009 recipient of the USC Provost’s award for Teaching with Technology.
Dr. Alan Craig serves as Senior Associate Director for Human-‐Computer Interaction at ICHASS and a member of the Visualization and Virtual Reality Group at the National Center for Supercomputing Applications. He recently was named Digital Humanities Specialist for the Extreme Science and Engineering Discovery Environment (XSEDE) project. In this new role, Craig will bridge the gap between traditional supercomputing users and those in the humanities, arts, and social sciences.
Dr. Ritu Aurora works with the High Performance Computing (HPC) group at TACC as a Research Associate. At TACC, she uses her experience in developing distributed and shared memory scientific applications, and developing Domain-Specific Languages (DSLs) to provide consultancy to XSEDE users and iPlant Collaborative project developers. She specializes in the application of generative programming techniques for reengineering legacy scientific software.
Dr. Michael Simeone is the Associate Director for Research and Interdisciplinary Studies at ICHASS at the University of Illinois at Urbana-‐Champaign. Aside from his work on projects that engage the computational study of video, image-analysis of Great Lakes area historical maps, and the significance of social network analytics for the humanities, his research focuses on the intersection of humanities research procedures and data science. He received his PhD in English from the University of Illinois at Urbana-‐Champaign.
Panel Description
Contemporary culture is awash in moving images: there is more video uploaded to YouTube in a single day than one can ever view in a lifetime. But what are the implications of this storm of images on issues of identity, memory, history and politics? These are the questions taken up by this panel presentation which will center on the Large Scale Video Analytics project (LSVA), a research effort that finds cinema scholars and digital humanists working with supercomputing scientists to create processes and methods for making sense of vast filmic archives using a human-‐machine hybrid approach. The challenges to scholarly use of filmic archives remains both technical and human in nature: From a technical standpoint, the potential of high performance computing for the analysis of massive video archives is hamstrung by the low efficacy of machine-‐read image recognition and metadata extraction. Human image tagging, by contrast, is far more accurate, though traditionally has been too labor intensive and expensive to be a tenable solution. A combination of the two—a hybrid approach—would vastly expand the ability to critically engage with vast video data sets.
The LSVA, which is a collaboration between the IML (Institute for Multimedia Literacy), ICHASS (the Institute for Computing in the Humanities, Arts and Social Science) and XSEDE (Extreme Science and Engineering Discovery Environment) is customizing the Medici content management system, and exploring the potential of applying various algorithms for image recognition and visualization into the workflow that will allow real-‐time analysis of video, which can then deploy crowd-‐sourced content labeling such that the system becomes more valuable the more it is used. In addition, the LSVA team has created and customized visualization tools that enhance research in several ways: novel visualizations employ spatial and temporal simultaneity, revealing unique aspects of a single film sequence; comparative visualizations represent relationships among multiple films within an archive; and, finally, the integration of visualization imagery becomes an input tag and a front end process that feeds the Medici content management system and enhances word-‐based labels, helping to close the semantic gap that occurs when words are applied to images.
Given the disciplinary diversity of the LSVA team, the panelists will explore a wide range of issues from the context of their own institutional background and their role in the project.