Combining Visual and Text Features for Learning in Multimedia Direct Marketing Domain

Sebastiano Battiato, Giovanni Maria Farinella, Giovanni Giuffrida, Catarina Sismeiro, Giuseppe Tribulato

2008

Abstract

Direct marketing companies systematically dispatch the offers under consideration to a limited sample of potential buyers, rank them with respect to their performance and, based on this ranking, decide which offers to send to the wider population. Though this pre-testing process is simple and widely used, recently the direct marketing industry has been under increased pressure to further optimize learning, in particular when facing severe time and space constraints. Taking into account the multimedia nature of offers, which typically comprise both a visual and text component, we propose a two-phase learning strategy based on a cascade of regression methods. This proposed approach takes advantage of visual and text features to improve and accelerate the learning process. Experiments in the domain of a commercial Multimedia Messaging Service (MMS) show the effectiveness of the proposed methods that improve on classical learning techniques.

References

  1. Direct Marketing Association: The Power of Direct Marketing: ROI, Sales, Expenditures and Employment in the U.S., 2006-2007 Edition. Direct Marketing Association (2007)
  2. Netsize: Convergence: Everything is going mobile. The Netsize Guide 2007. Netsize (2007)
  3. Roberts, M., Berger, P.: Direct Marketing Management. Prentice-Hall (1989)
  4. Prinzie, A., Van Den Poel, D.: Constrained optimization of data-mining problems to improve model performance: A direct-marketing application. Expert Systems with Applications 29 (2005) 630-640
  5. Nash, E.: Direct Marketing. McGraw-Hill (2000)
  6. Battiato, S., Farinella, G., Giuffrida, G., Tribulato, G.: Data mining learning bootstrap through semantic thumbnail analysis. In: SPIE-IS&T Electronic Imaging Science and Technology 2007 - Multimedia Content Access: Algorithms and Systems. (2007)
  7. Julesz, B.: Textons, the elements of texture perception, and their interactions. Nature 290 (1981) 91-97
  8. Renninger, L.W., Malik, J.: When is scene recognition just texture recognition? Vision Research 44 (2004) 2301-2311
  9. Winn, J., Criminisi, A., Minka, T.: Object categorization by learned universal visual dictionary. In: ICCV 7805: Proceedings of the Tenth IEEE International Conference on Computer Vision, Washington, DC, USA, IEEE Computer Society (2005) 1800-1807
  10. Barnard, K., Forsyth, D.A.: Learning the semantics of words and pictures. In: ICCV. (2001) 408-415
  11. Biederman, I., Mezzanotte, R., Rabinowitz, J.: Scene perception: Detecting and judging objects undergoing relational violations. Cognitive Psychology 14 (1982) 143-177
  12. Biederman, I.: Recognition by components: Atheory of human image interpretation. Psychological Review 94 (1987) 115-148
  13. Potter, M.: Meaning in visual search. Science 187 (1975) 965-966
  14. Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. International Journal of Computer Vision 42 (2001) 145-175
  15. Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: IEEE Conference on Computer Vision and Pattern Recognition. (2005)
  16. Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: IEEE Conference on Computer Vision and Pattern Recognition. Volume 2. (2006) 2169-2178
  17. Bergen, J.R., Julesz, B.: Rapid discrimination of visual patterns. IEEE Transactions on Systems, Man, and Cybernetics 13 (1983) 857-863
  18. Varma, M., Zisserman, A.: A statistical approach to texture classification from single images. Int. J. Computer Vision 62 (2005) 61-81
  19. Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Wadsworth and Brooks, Monterey, CA (1984)
  20. Cleveland, W.S., Devlin, S.J., Grosse, E.: Regression by local fitting : Methods, properties, and computational algorithms. Journal of Econometrics 37 (1988) 87-114
  21. Shawe-Taylor, J., Cristianini, N.: Support Vector Machines and other kernel-based learning methods. Cambridge University Press (2000)
  22. Taylor, P., Caley, R., Black, A.W., King, S.: Wagon, edinburgh speech tools library (1999)
  23. Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 25 (2003) 564-575
  24. Oren, N.: Reexamining tf.idf based information retrieval with genetic programming. In: SAICSIT 7802. (2002) 224-234
  25. Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. (2001)
  26. Oza, N.C.: Online bagging and boosting. In: Systems, Man and Cybernetics, 2005 IEEE International Conference on. (2005) 2340-2345
Download


Paper Citation


in Harvard Style

Battiato S., Maria Farinella G., Giuffrida G., Sismeiro C. and Tribulato G. (2008). Combining Visual and Text Features for Learning in Multimedia Direct Marketing Domain . In Metadata Mining for Image Understanding - Volume 1: MMIU, (VISIGRAPP 2008) ISBN 978-989-8111-24-1, pages 34-47. DOI: 10.5220/0002337200340047


in Bibtex Style

@conference{mmiu08,
author={Sebastiano Battiato and Giovanni Maria Farinella and Giovanni Giuffrida and Catarina Sismeiro and Giuseppe Tribulato},
title={Combining Visual and Text Features for Learning in Multimedia Direct Marketing Domain},
booktitle={Metadata Mining for Image Understanding - Volume 1: MMIU, (VISIGRAPP 2008)},
year={2008},
pages={34-47},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002337200340047},
isbn={978-989-8111-24-1},
}


in EndNote Style

TY - CONF
JO - Metadata Mining for Image Understanding - Volume 1: MMIU, (VISIGRAPP 2008)
TI - Combining Visual and Text Features for Learning in Multimedia Direct Marketing Domain
SN - 978-989-8111-24-1
AU - Battiato S.
AU - Maria Farinella G.
AU - Giuffrida G.
AU - Sismeiro C.
AU - Tribulato G.
PY - 2008
SP - 34
EP - 47
DO - 10.5220/0002337200340047