Attribute rating for classification of visual objects

Jongpil Kim, Vladimir Pavlovic

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

4 Scopus citations

Abstract

Traditional visual classification approaches focus on predicting absence/presence of labels or attributes for images. However, it is sometimes useful to predict the ratings of the labels or attributes endowed with an ordinal scale (e.g., 'very important,' 'important' or 'not important'). The ordinal scale representation allows us to describe object classes more precisely than simple binary tagging. In this work, we propose a new method where each label/attribute can be assigned to a finite set of ordered ratings, from most to least relevant. Object classes are then predicted using these ratings. Experiments on Animals with Attributes dataset demonstrate the performance of the proposed method and show its advantages over previous methods based on binary tagging and multi-class classification.

Original languageEnglish (US)
Title of host publicationICPR 2012 - 21st International Conference on Pattern Recognition
Pages1611-1614
Number of pages4
StatePublished - 2012
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: Nov 11 2012Nov 15 2012

Publication series

NameProceedings - International Conference on Pattern Recognition

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
Country/TerritoryJapan
CityTsukuba
Period11/11/1211/15/12

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Attribute rating for classification of visual objects'. Together they form a unique fingerprint.

Cite this