Attriblt: Content creation with semantic attributes

Siddhartha Chaudhuri, Evangelos Kalogerakis, Stephen Giguere, Thomas Allen Funkhouser

Research output: Chapter in Book/Report/Conference proceedingConference contribution

72 Scopus citations

Abstract

We present ATTRIBIT, an approach for people to create visual content using relative semantic attributes expressed in linguistic terms. During an off-line processing step, ATTRIBIT learns semantic attributes for design components that reflect the high-level intent people may have for creating content in a domain (e.g. adjectives such as "dangerous", "scary" or "strong") and ranks them according to the strength of each learned attribute. Then, during an interactive design session, a person can explore different combinations of visual components using commands based on relative attributes (e.g. "make this part more dangerous"). Novel designs are assembled in real-time as the strengths of selected attributes are varied, enabling rapid, in-situ exploration of candidate designs. We applied this approach to 3D modeling and web design. Experiments suggest this interface is an effective alternative for novices performing tasks with high-level design goals.

Original languageEnglish (US)
Title of host publicationUIST 2013 - Proceedings of the 26th Annual ACM Symposium on User Interface Software and Technology
Pages193-202
Number of pages10
DOIs
StatePublished - Nov 20 2013
Event26th Annual ACM Symposium on User Interface Software and Technology, UIST 2013 - St. Andrews, United Kingdom
Duration: Oct 8 2013Oct 11 2013

Publication series

NameUIST 2013 - Proceedings of the 26th Annual ACM Symposium on User Interface Software and Technology

Other

Other26th Annual ACM Symposium on User Interface Software and Technology, UIST 2013
CountryUnited Kingdom
CitySt. Andrews
Period10/8/1310/11/13

All Science Journal Classification (ASJC) codes

  • Software

Keywords

  • Assembly-based modeling
  • Content creation
  • Exploratory interfaces
  • High-level attributes
  • Interactive modeling
  • Relative attributes
  • Semantic attributes

Fingerprint Dive into the research topics of 'Attriblt: Content creation with semantic attributes'. Together they form a unique fingerprint.

Cite this