Multimedia Tools and Applications

, Volume 56, Issue 1, pp 91–108 | Cite as

Social image annotation via cross-domain subspace learning

Article

Abstract

In recent years, cross-domain learning algorithms have attracted much attention to solve labeled data insufficient problem. However, these cross-domain learning algorithms cannot be applied for subspace learning, which plays a key role in multimedia processing. This paper envisions the cross-domain discriminative subspace learning and provides an effective solution to cross-domain subspace learning. In particular, we propose the cross-domain discriminative locally linear embedding or CDLLE for short. CDLLE connects the training and the testing samples by minimizing the quadratic distance between the distribution of the training samples and that of the testing samples. Therefore, a common subspace for data representation can be preserved. We basically expect the discriminative information to separate the concepts in the training set can be shared to separate the concepts in the testing set as well and thus we have a chance to address above cross-domain problem duly. The margin maximization is duly adopted in CDLLE so the discriminative information for separating different classes can be well preserved. Finally, CDLLE encodes the local geometry of each training samples through a series of linear coefficients which can reconstruct a given sample by its intra-class neighbour samples and thus can locally preserve the intra-class local geometry. Experimental evidence on NUS-WIDE, a popular social image database collected from Flickr, and MSRA-MM, a popular real-world web image annotation database collected from the Internet by using Microsoft Live Search, demonstrates the effectiveness of CDLLE for real-world cross-domain applications.

Keywords

Social image annotation Cross-domain learning Subspace learning 

References

  1. 1.
    Belkin M, Niyogi P, Sindhwani V (2006) Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples. J Mach Learn Res 7:2399–2434MATHMathSciNetGoogle Scholar
  2. 2.
    Cai D, He X, Han J (2007) Semi-supervised discriminant analysis. IEEE International Conference on Computer Vision, pp. 1-7Google Scholar
  3. 3.
    Caruana R (1997) Multitask learning. Mach Lear 28(1):41–75CrossRefMathSciNetGoogle Scholar
  4. 4.
    Chua T-S, Tang J, Hong R, Li H, Luo Z, Zheng Y-T (2009) NUS-WIDE: A real-world web image database from national university of Singapore. ACM International Conference on Image and Video Retrieval, pp. 1-8Google Scholar
  5. 5.
    Dai W, Yang Q, Xue G, Yu Y (2007) Boosting for transfer learning. Processing of the 24th international conference on Machine learning, pp. 193-200Google Scholar
  6. 6.
    Duan L, Tsang IW, Xu D, Maybank SJ (2009) Domain transfer svm for video concept detection. Proceeding of the 21th conference on Computer Vision and Pattern RecognitionGoogle Scholar
  7. 7.
    Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Eugen 7(2):179–188CrossRefGoogle Scholar
  8. 8.
    He X, Niyogi P (2003) Locality preserving projections. Adv Neural Inf Process Syst 16:1–8Google Scholar
  9. 9.
    Li H, Wang M, Hua X-S (2009) MSRA-MM 2.0: A large-scale web multimedia dataset. ICDM Workshop on Internet Multimedia MiningGoogle Scholar
  10. 10.
    Ling X, Dai W, Xue G, Yang Q, Yu Y (2008) Spectral domain-transfer learning. Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 488-496Google Scholar
  11. 11.
    Liu W, Tao D, Liu J (2008) Transductive component analysis. The 8th IEEE International Conference on Data Mining, pp. 433-442Google Scholar
  12. 12.
    Liu D, Hua XS, Yang L, Wang M, Zhang H-J (2009) Tag ranking. International World Wide Web Conference (WWW)Google Scholar
  13. 13.
    Mihalkova L, Mooney R (2006) Transfer learning with markov logic networks. ICML Workshop on Structural Knowledge Transfer for Machine LearningGoogle Scholar
  14. 14.
    Pan J, Kwok JT, Yang Q (2008) Transfer learning via dimensionality reduction. Proceedings of the 23th AAAI Conference on Artificial Intelligence, pp. 677-682Google Scholar
  15. 15.
    Parzen E (1962) On estimation of a probability density function and mode. Ann Math Stat 33(3):1065–1076CrossRefMATHMathSciNetGoogle Scholar
  16. 16.
    Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290:2323–2326CrossRefGoogle Scholar
  17. 17.
    Sebe N, Lew MS, Huijsmans DP (2000) Toward improved ranking metrics. IEEE Trans Pattern Anal Mach Intell 22(10):1132–1143CrossRefGoogle Scholar
  18. 18.
    Si S, Tao D, Chan KP Evolutionary cross-domain discriminative Hessian eigenmaps. IEEE Trans Image Process, to appearGoogle Scholar
  19. 19.
    Si S, Tao D, Geng B Bregmann divergence based regularization for transfer subspace learning. IEEE Trans Knowl Data Eng to appearGoogle Scholar
  20. 20.
    Snoek CG, Worring M, Smeulders AW (2005) Early versus late fusion in semantic video analysis. Proceeding of the 13th ACM international on Multimedia, pp. 399–402Google Scholar
  21. 21.
    Snoek CGM, Worring M, Geusebroek JM, Koelma DC, Seinstra FJ, Smeulders AWM (2006) The semantic pathfinder: Using an authoring metaphor for generic multimedia indexing. IEEE Trans Pattern Anal Mach Intell 28(10):1678–1689CrossRefGoogle Scholar
  22. 22.
    Song D, Tao D Biologically inspired feature manifold for scene classification. IEEE Trans Image Process, to appearGoogle Scholar
  23. 23.
    Tang J, Yan S, Hong R, Qi GJ, Chua TS (2009) Inferring semantic concepts from community-contributed images and noisy tags. Proceeding of the 17th ACM international on Multimedia, pp. 223–232Google Scholar
  24. 24.
    Tao D, Li X, Wu X, Maybank SJ (2007) General tensor discriminant analysis and gabor features for gait recognition. IEEE Trans Pattern Anal Mach Intell 29(10):1700–1715CrossRefGoogle Scholar
  25. 25.
    Wang M, Hua XS (2008) Study on the combination of video concept detectors. Proceeding of the 16th ACM International Conference on Multimedia, pp. 47–650Google Scholar
  26. 26.
    Wang M, Hua XS, Song Y, Yuan X, Li SP, Zhang HJ (2006) Automatic video annotation by semi-supervised learning with kernel density estimation. Proceeding of the 14th ACM International Conference on Multimedia, pp. 967–976Google Scholar
  27. 27.
    Wang M, Hua XS, Yuan X, Song Y, Dai LR (2007) Optimizing multi-graph learning: Towards a unified video annotation scheme. Proceeding of the 15th International Conference on Multimedia, pp. 862-871Google Scholar
  28. 28.
    Wang J, Jiang YG, Chang SF (2009) Label diagnosis through self tuning for web image search. Proceeding of the 21th conference on Computer Vision and Pattern RecognitionGoogle Scholar
  29. 29.
    Wang M, Yang K, Hua XS, Zhang H-J (2009) Visual tag dictionary: interpreting tags with visual words. ACM Workshop on Web-Scale Multimedia Corpus, in association with ACM MMGoogle Scholar
  30. 30.
    Wu Z, Ke QF, Isard M, Sun J (2009) Bundling features for large scale partial-duplicate web image search. Proceeding of the 21th conference on Computer Vision and Pattern RecognitionGoogle Scholar
  31. 31.
    Yang J, Hauptmann AG (2008) A framework for classifier adaptation and its applications in concept detection. Proceedings of the 1st ACM SIGMM International Conference on Multimedia Information Retrieval, pp. 467–474Google Scholar
  32. 32.
    Yang J, Yan R, Hauptmann AG (2007) Cross-domain video concept detection using adaptive svms. Proceeding of the 15th international conference on Multimedia, pp. 188-197Google Scholar
  33. 33.
    Zhang T, Tao D, Yang J (2008) Discriminative locality alignment. Proceeding of the 10th European Conference on Computer Vision, pp. 725-738Google Scholar
  34. 34.
    Zhang T, Tao D, Li X, Yang T (2008) A unifying framework for spectral analysis based dimensionality reduction. IEEE International Joint Conference on Neural Networks 1670-1677, JuneGoogle Scholar
  35. 35.
    Zhang T, Tao D, Yang J (2009) Patch alignment for dimensionality reduction. IEEE Trans Knowl Data Eng 21(9):1299–1313CrossRefGoogle Scholar
  36. 36.
    Zheng V, Yang E, Yang Q, Xiang W, Shen D (2008) Transferring localization models over time. Proceedings of the 23th international conference on Artificial intelligence, pp. 1421-1426Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of Hong KongPokfulamHong Kong
  2. 2.School of Computer EngineeringNanyang Technological UniversityNanyang AvenueSingapore
  3. 3.Microsoft Research AsiaBeijingChina

Personalised recommendations