Transderivational Search: Looking for Analogies in Multimedia Data

Transderivational Search:
Looking for Analogies in Multimedia Data

   Home

   Participants

   Perception Surveys

   Related Resources

   Educational Initiatives

   Publications

   Sponsors

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.
The goal of this project is 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).

   In the News:
     June 6, 2008
     October 1, 2007

Participants

H. Quynh Dinh
Assistant Professor, Department of Computer Science, Stevens

Ebon Fisher
Associate Affiliate Professor, College of Arts & Letters, Stevens

Lucy (Liefei) Xu
Computer Science PhD student, Department of Computer Science, Stevens

Victoria Petite
Technogenesis Summer Scholar and Art & Technology student, Stevens

Sponsors

National Science Foundation (NSF) Creative IT Program, Award# 0742440.

		Transderivational Search: Looking for Analogies in Multimedia Data
Home Participants Perception Surveys Related Resources Educational Initiatives Publications Sponsors		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. The goal of this project is 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).
*In the News:* June 6, 2008 October 1, 2007		Participants H. Quynh Dinh Assistant Professor, Department of Computer Science, Stevens Ebon Fisher Associate Affiliate Professor, College of Arts & Letters, Stevens Lucy (Liefei) Xu Computer Science PhD student, Department of Computer Science, Stevens Victoria Petite Technogenesis Summer Scholar and Art & Technology student, Stevens Sponsors National Science Foundation (NSF) Creative IT Program, Award# 0742440.

Questions or comments? Please send email to: quynh (at) cs.stevens.edu