Simple Tag-based Subclass Representations for Visually-varied Image Classes

Xinchao Li, Peng Xu, Yue Shi, Martha Larson, Alan Hanjalic

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

In this paper, we present a subclass-representation approach that predicts the probability of a social image belonging to one particular class. We explore the co-occurrence of user-contributed tags to find subclasses with a strong connection to the top level class. We then project each image onto the resulting subclass space, generating a subclass representation for the image. The advantage of our tag-based subclasses is that they have a chance of being more visually stable and easier to model than top-level classes. Our contribution is to demonstrate that a simple and inexpensive method for generating sub-class representations has the ability to improve classification results in the case of tag classes that are visually highly heterogenous. The approach is evaluated on a set of 1 million photos with 10 top-level classes, from the dataset released by the ACM Multimedia 2013 Yahoo! Large-scale Flickr-tag Image Classification Grand Challenge. Experiments show that the proposed system delivers sound performance for visually diverse classes compared with methods that directly model top classes.
Original languageEnglish
Title of host publication2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages1-6
Number of pages6
ISBN (Electronic)978-1-4673-8695-1
DOIs
Publication statusPublished - 30 Jun 2016
Event2016 14th International Workshop on Content-Based Multimedia Indexing - Bucharest, Romania
Duration: 15 Jun 201617 Jun 2016
http://cbmi2016.upb.ro/

Conference

Conference2016 14th International Workshop on Content-Based Multimedia Indexing
Abbreviated titleCBMI
CountryRomania
CityBucharest
Period15/06/1617/06/16
Internet address

Keywords

  • Visualization
  • Training
  • Predictive models
  • Tagging
  • Multimedia communication
  • Support vector machines
  • Flickr

Fingerprint Dive into the research topics of 'Simple Tag-based Subclass Representations for Visually-varied Image Classes'. Together they form a unique fingerprint.

Cite this