Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

Automatic visual categorization is critically dependent on labeled examples for supervised learning. As an alternative to traditional expert labeling, social-tagged multimedia is becoming a novel yet subjective and inaccurate source of learning examples. Different from existing work focusing on collecting positive examples, we study in this paper the potential of substituting social tagging for expert labeling for creating negative examples. We present an empirical study using 6.5 million Flickr photos as a source of social tagging. Our experiments on the PASCAL VOC challenge 2008 show that with a relative loss of only 4.3% in terms of mean average precision, expert-labeled negative examples can be completely replaced by social-tagged negative examples for consumer photo categorization.

REFERENCES

• 1: M. Everingham, L. Van Gool, C. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2008.
• 2: Xian-Sheng Hua , Guo-Jun Qi, Online multi-label active annotation: towards large-scale content-based video search, Proceeding of the 16th ACM international conference on Multimedia, October 26-31, 2008, Vancouver, British Columbia, Canada [doi>10.1145/1459359.1459379]
• 3: Lyndon S. Kennedy , Shih-Fu Chang , Igor V. Kozintsev, To search or to label?: predicting the performance of search-based automatic image classifiers, Proceedings of the 8th ACM international workshop on Multimedia information retrieval, October 26-27, 2006, Santa Barbara, California, USA [doi>10.1145/1178677.1178712]
• 4: L.-J. Li, G. Wang, and L. Fei-Fei. OPTIMOL: automatic online picture collection via incremental model learning. In CVPR, pages 1--8, 2007.
• 5: Xirong Li , Cees G.M. Snoek , Marcel Worring, Learning tag relevance by neighbor voting for social image retrieval, Proceeding of the 1st ACM international conference on Multimedia information retrieval, October 30-31, 2008, Vancouver, British Columbia, Canada [doi>10.1145/1460096.1460126]
• 6: David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, v.60 n.2, p.91-110, November 2004 [doi>10.1023/B:VISI.0000029664.99615.94]
• 7: Apostol (Paul) Natsev , Alexander Haubold , Jelena Tešić , Lexing Xie , Rong Yan, Semantic concept-based query expansion and re-ranking for multimedia retrieval, Proceedings of the 15th international conference on Multimedia, September 25-29, 2007, Augsburg, Germany [doi>10.1145/1291233.1291448]
• 8: David M. J. Tax , Robert P. W. Duin, Uniform object generation for optimizing one-class classifiers, The Journal of Machine Learning Research, 2, 3/1/2002
• 9: J. Uijlings, A. Smeulders, and R. Scha. Real-time bag-of-words, approximately. In CIVR, 2009.
• 10: A. Ulges, M. Koch, C. Schulze, and T. Breuel. Learning TRECVID'08 high-level features from YouTube. In TRECVID, 2008.
• 11: Luis von Ahn , Laura Dabbish, Labeling images with a computer game, Proceedings of the SIGCHI conference on Human factors in computing systems, p.319-326, April 24-29, 2004, Vienna, Austria [doi>10.1145/985692.985733]
• 12: Keiji Yanai , Kobus Barnard, Probabilistic web image gathering, Proceedings of the 7th ACM SIGMM international workshop on Multimedia information retrieval, November 10-11, 2005, Hilton, Singapore [doi>10.1145/1101826.1101838]
• 13: Rong Yan , Alexander G. Hauptmann , Rong Jin, Negative pseudo-relevance feedback in content-based video retrieval, Proceedings of the eleventh ACM international conference on Multimedia, November 02-08, 2003, Berkeley, CA, USA [doi>10.1145/957013.957087]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.4 Systems
          Subjects: Multimedia databases

General Terms:
Algorithms, Experimentation, Measurement

Keywords:
negative examples, social tagging, visual categorization