From large scale image categorization to entry-level categories

Vicente Ordonez, Jia Deng, Yejin Choi, Alexander C. Berg, Tamara L. Berg

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

82 Scopus citations

Abstract

Entry level categories-the labels people will use to name an object-were originally defined and studied by psychologists in the 1980s. In this paper we study entry-level categories at a large scale and learn the first models for predicting entry-level categories for images. Our models combine visual recognition predictions with proxies for word 'naturalness' mined from the enormous amounts of text on the web. We demonstrate the usefulness of our models for predicting nouns (entry-level words) associated with images by people. We also learn mappings between concepts predicted by existing visual recognition systems and entry-level concepts that could be useful for improving human-focused applications such as natural language image description or retrieval.

Original languageEnglish (US)
Title of host publicationProceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2768-2775
Number of pages8
ISBN (Print)9781479928392
DOIs
StatePublished - 2013
Externally publishedYes
Event2013 14th IEEE International Conference on Computer Vision, ICCV 2013 - Sydney, NSW, Australia
Duration: Dec 1 2013Dec 8 2013

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Other

Other2013 14th IEEE International Conference on Computer Vision, ICCV 2013
Country/TerritoryAustralia
CitySydney, NSW
Period12/1/1312/8/13

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Keywords

  • categories
  • categorization
  • entry-level
  • images
  • language
  • prediction
  • retrieval

Fingerprint

Dive into the research topics of 'From large scale image categorization to entry-level categories'. Together they form a unique fingerprint.

Cite this