Collaborative and content-based image labeling

Ning Zhou*, Kwok Wai CHEUNG, Xiangyang Xue, Guoping Qiu

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

3 Citations (Scopus)


Many on-line photo sharing systems allow users to tag their images so as to support semantic image search. In this paper, we study how one can take advantages of the already-tagged images to (semi-)automate the labeling of newly uploaded ones. In particular, we propose a hybrid approach for the prediction where user-provided tags and image visual contents are fused under a unified probabilistic framework. Kernel smoothing and collaborative filtering techniques are explored for improving the accuracy of the probabilistic models estimation. By comparing with some state-of-the-art content-based image labeling methods, we have empirically shown that 1) the proposed method can achieve comparable tag prediction accuracy when there is no user-provided tag, and that 2) it can significantly boost the prediction accuracy if the user can provide just a few tags.

Original languageEnglish
Title of host publication2008 19th International Conference on Pattern Recognition, ICPR 2008
ISBN (Electronic)9781424421756
ISBN (Print)9781424421749
Publication statusPublished - Dec 2008
Event2008 19th International Conference on Pattern Recognition, ICPR 2008 - Tampa, FL, United States
Duration: 8 Dec 200811 Dec 2008

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651


Conference2008 19th International Conference on Pattern Recognition, ICPR 2008
Country/TerritoryUnited States
CityTampa, FL

Scopus Subject Areas

  • Computer Vision and Pattern Recognition

User-Defined Keywords

  • Collaboration
  • Labeling
  • Filtering
  • Image retrieval
  • Computer science
  • Accuracy
  • Kernel
  • Smoothing methods
  • Content based retrieval
  • Tagging


Dive into the research topics of 'Collaborative and content-based image labeling'. Together they form a unique fingerprint.

Cite this