Computing iconic summaries of general visual concepts

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Raguram, R., Lazebnik, S.
Format: Conference Proceeding
Language:English
Subjects:
Computer science
Cultural differences
Heart
Image quality
Image retrieval
Large-scale systems
Multidimensional systems
Performance analysis
Positron emission tomography
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 ldquothemerdquo 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 ldquoloverdquo and ldquobeautyrdquo.
ISSN:2160-7508
2160-7516
DOI:10.1109/CVPRW.2008.4562959