Computing iconic summaries of general visual concepts

Rahul Raguram, Svetlana Lazebnik

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

Abstract

This paper considers the problem of selecting iconic images to summarize general visual categories. We define iconic images as high-quality representatives of a large group of images consistent both in appearance and semantics. To find such groups, we perform joint clustering in the space of global image descriptors and latent topic vectors of tags associated with the images. To select the representative iconic images for the joint clusters, we use a quality ranking learned from a large collection of labeled images. For the purposes of visualization, iconic images are grouped by semantic "theme" and multidimensional scaling is used to compute a 2D layout that reflects the relationships between the themes. Results on four large-scale datasets demonstrate the ability of our approach to discover plausible themes and recurring visual motifs for challenging abstract concepts such as "love" and "beauty."

Original languageEnglish (US)
Title of host publication2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
DOIs
StatePublished - 2008
Externally publishedYes
Event2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops - Anchorage, AK, United States
Duration: Jun 23 2008Jun 28 2008

Publication series

Name2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops

Other

Other2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
Country/TerritoryUnited States
CityAnchorage, AK
Period6/23/086/28/08

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Computing iconic summaries of general visual concepts'. Together they form a unique fingerprint.

Cite this