|November 8, 2007 |
Fisher & Dinh awarded NSF Grant to Develop Multimedia Search Technology
Professors Fisher from the Department of Art, Music, and Technology and H. Quynh Ding from the Department of Computer Science have been awarded a National Science Foundation (NSF) exploratory research grant of $150K over two years for their proposal entitled, "A Transderivational Search Engine for Creative Analogy Generation in Mixed-Media Design." This grant is funded through the NSF CreativeIT program which seeks "synergies between creativity and information technology, science, engineering, and design research."
Text-based search engines (e.g. Ask, Google, MS Live, Yahoo) are now reaching maturity. They have evolved beyond retrieving related websites to retrieving images and video using text labels associated with the media samples. More recently, content-based (non-textual) retrieval algorithms have been developed for music, images, video, and 3D shapes. Two important concepts remain beyond the reach of current text and content-based search engines. These are the ability to compare different media forms (e.g., audio and video) and the ability to retrieve analogical rather than exact matches. In psychology, analogical or fuzzy matches are achieved via transderivational search – a primary component of human language and cognitive processing which enables people to find contextual meaning in every stimulus.
Fisher and Dinh's grant will enable them to develop a transderivational search engine that suggests analogies across different media forms (e.g., text, audio, images, video, and 3D shapes) by looking at structural similarity within media content. The search engine will be developed in the context of designing interactive, mixed-media installations and in a brainstorming application for artists and designers. The result will be a transformative technology at the intersection of art, computer graphics, machine learning, cognitive psychology, and human-computer interaction (HCI).
With help from Julie Harrison, director of the Art & Technology (ARTC) program at Stevens, Fisher and Dinh will introduce this technology into mixed-media design courses in ARTC. Transderivational search will also be used to explore algorithms in search technology, machine learning, computer vision, and computer graphics in CS courses.
Professor Fisher is an Affiliate Associate Professor in the Department of Art, Music & Technology at Stevens. Fisher began studying the impact of high technology on culture at MIT's Media Lab and the Center for Advanced Visual Studies where he also taught the Media Lab's first undergraduate class, Creative Seeing. After MIT, Fisher fronted a multimedia rock band, Nerve Circle, and moved to Brooklyn, NY where he explored community-based media rituals, including the Media Compressions, (718) SUBWIRE and the Web Jam. Fisher’s work has been presented by the Guggenheim Museum, P.S. 1/MOMA, Boston’s Institute of Contemporary Art and at international venues. It has been discussed in Newsweek, Wired, Domus, Die Zeit, FlashArt, the Drama Review, the Performing Arts Journal and New York Magazine. Fisher is also a writer and lecturer on transmedia and interactive art.
Dr. H. Quynh Dinh, Assistant Professor in the Department of Computer Science at Stevens, is part of the Multimedia, Vision, and Visualization (MVV) Group within the department. Her research is in the area of computer graphics, specializing in shape representations, shape matching, morphing, surface reconstruction, and vector field matching. Her work has been published in the ACM Transactions on Graphics, IEEE journal on Pattern Analysis and Machine Intelligence, and the proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) and the International Conference on Computer Vision (ICCV). She has taught introductory and advanced computer graphics for 5 years and has supervised both undergraduate and PhD students in research.