Abstract
Traditional Content Based Multimedia Retrieval (CBMR) systems measure the relevance of visual samples using a binary scale (Relevant/Non Relevant). However, a picture can be relevant to a semantic category with different degrees, depending on the way such concept is represented in the image. In this paper, we build a CBMR framework that supports graded relevance judgments. In order to quickly build graded ground truths, we propose a measure to reassess binary-labeled databases without involving manual effort: we automatically assign a reliable relevance degree (Non, Weakly, Average, Very Relevant) to each sample, based on its position with respect to the hyperplane drawn by support vector machines in the feature space. We test the effectiveness of our system on two large-scale databases, and we show that our approach outperforms the traditional binary relevance-based frameworks in both scene recognition and video retrieval.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ayache, S., Quénot, G.: Trecvid 2007 collaborative annotation using active learning. In: Proceedings of the TRECVID 2007 Workshop (2007)
Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pp. 144–152. ACM (1992)
Elleuch, N., Zarka, M., Feki, I., Ammar, A.B., Alimi, A.: Regimvid at trecvid 2010: Semantic indexing. In: Proceedings of the TRECVID 2010 Workshop (2010)
Freund, Y., Iyer, R., Schapire, R.E., Singer, Y.: An efficient boosting algorithm for combining preferences. J. Mach. Learn. Res. 4, 933–969 (2003)
Ji, Z., Lu, B.-L.: Gender Classification Based on Support Vector Machine with Automatic Confidence. In: Leung, C.S., Lee, M., Chan, J.H. (eds.) ICONIP 2009, Part I. LNCS, vol. 5863, pp. 685–692. Springer, Heidelberg (2009)
Kekäläinen, J.: Binary and graded relevance in ir evaluations–comparison of the effects on ranking of ir systems. Information processing & management 41(5), 1019–1033 (2005)
Kelly, D., Teevan, J.: Implicit feedback for inferring user preference: a bibliography. SIGIR Forum 37, 18–28 (2003)
Lin, C., Wang, S.: Training algorithms for fuzzy support vector machines with noisy data. Pattern Recognition Letters 25(14), 1647–1656 (2004)
Lin, C.F., Wang, S.D.: Fuzzy support vector machines. IEEE Transactions on Neural Networks 13(2), 464–471 (2002)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)
Papageorgiou, C.P., Oren, M., Poggio, T.: A General Framework for Object Detection. In: Proceedings of the Sixth International Conference on Computer Vision, p. 555. IEEE Computer Society (1998)
Paterno, M.C.S., Lim, F.S., Leow, W.K.: Fuzzy semantic labeling for image retrieval. In: 2004 IEEE International Conference on Multimedia and Expo, ICME 2004, vol. 2, pp. 767–770. IEEE (2004)
Platt, J.: Probabilistic outputs for support vector machines. In: Bartlett, P., Schoelkopf, B., Schurmans, D., Smola, A.J. (eds.) Advances in Large Margin Classifiers, pp. 61–74
Redi, M., Merialdo, B., Wang, F.: Eurecom and ecnu at trecvid 2010: The semantic indexing task. In: Proceedings of the TRECVID 2010 Workshop (2010)
Redi, M., Merialdo, B.: Saliency moments for image categorization. In: Proceedings of the 1st ACM International Conference on Multimedia Retrieval, ICMR 2011, pp. 39:1–39:8. ACM, New York (2011)
Saracevic, T.: Relevance: A review of the literature and a framework for thinking on the notion in information science. part iii: Behavior and effects of relevance. Journal of the American Society for Information Science and Technology 58(13), 2126–2144 (2007)
Smeaton, A.F., Over, P., Kraaij, W.: Evaluation campaigns and trecvid. In: MIR 2006: Proceedings of the 8th ACM International Workshop on Multimedia Information Retrieval, pp. 321–330. ACM Press, New York (2006)
Snow, R., O’Connor, B., Jurafsky, D., Ng, A.Y.: Cheap and fast—but is it good?: evaluating non-expert annotations for natural language tasks. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 254–263. Association for Computational Linguistics (2008)
Sormunen, E.: Liberal relevance criteria of trec-: counting on negligible documents? In: Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 324–330. ACM (2002)
Stricker, M.A., Orengo, M.: Similarity of color images. In: Proceedings of SPIE, vol. 2420, p. 381 (1995)
Svore, K., Vanderwende, L., Burges, C.: Enhancing single-document summarization by combining ranknet and third-party sources. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 448–457 (2007)
Won, C.S., Park, D.K., Park, S.J.: Efficient use of MPEG-7 edge histogram descriptor. Etri Journal 24(1), 23–30 (2002)
Zheng, Z., Chen, K., Sun, G., Zha, H.: A regression framework for learning ranking functions using relative relevance judgments. In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 287–294. ACM (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Redi, M., Merialdo, B. (2012). A Multimedia Retrieval Framework Based on Automatic Graded Relevance Judgments. In: Schoeffmann, K., Merialdo, B., Hauptmann, A.G., Ngo, CW., Andreopoulos, Y., Breiteneder, C. (eds) Advances in Multimedia Modeling. MMM 2012. Lecture Notes in Computer Science, vol 7131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27355-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-27355-1_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27354-4
Online ISBN: 978-3-642-27355-1
eBook Packages: Computer ScienceComputer Science (R0)