Semi-supervised feature analysis for multimedia annotation by mining label correlation

Xiaojun Chang, Haoquan Shen, Sen Wang, Jiajun Liu, Xue Li

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

27 Citations (Scopus)


In multimedia annotation, labeling a large amount of training data by human is both time-consuming and tedious. Therefore, to automate this process, a number of methods that leverage unlabeled training data have been proposed. Normally, a given multimedia sample is associated with multiple labels, which may have inherent correlations in real world. Classical multimedia annotation algorithms address this problem by decomposing the multi-label learning into multiple independent single-label problems, which ignores the correlations between different labels. In this paper, we combine label correlation mining and semi-supervised feature selection into a single framework. We evaluate performance of the proposed algorithm of multimedia annotation using MIML, MIRFLICKR and NUS-WIDE datasets. Mean average precision (MAP), MicroAUC and MacroAUC are used as evaluation metrics. Experimental results on the multimedia annotation task demonstrate that our method outperforms the state-of-the-art algorithms for its capability of mining label correlations and exploiting both labeled and unlabeled training data.

Original languageEnglish
Title of host publicationAdvances in Knowledge Discovery and Data Mining
Subtitle of host publication18th Pacific-Asia Conference, PAKDD 2014 Tainan, Taiwan, May 13-16, 2014 Proceedings, Part II
EditorsVincent S. Tseng, Tu Bao Ho, Zhi-Hua Zhou, Arbee L.P. Chen, Hung-Yu Kao
Place of PublicationCham Switzerland
Number of pages12
ISBN (Electronic)9783319066059
Publication statusPublished - 2014
Externally publishedYes

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


  • Multi-label Feature Selection
  • Multimedia Annotation
  • Semi-supervised Learning

Cite this