Negative pseudo-relevance feedback in content-based video retrieval

ABSTRACT

Video information retrieval requires a system to find information relevant to a query which may be represented simultaneously in different ways through a text description, audio, still images and/or video sequences. We present a novel approach that uses pseudo-relevance feedback from retrieved items that are NOT similar to the query items without further inquiring user feedback. We provide insight into this approach using a statistical model and suggest a score combination scheme via posterior probability estimation. An evaluation on the 2002 TREC Video Track queries shows that this technique can improve video retrieval performance on a real collection. We believe that negative pseudo-relevance feedback shows great promise for very difficult multimedia retrieval tasks, especially when combined with other different retrieval algorithms.

REFERENCES

• 1: Christopher J. C. Burges, A Tutorial on Support Vector Machines for Pattern Recognition, Data Mining and Knowledge Discovery, v.2 n.2, p.121-167, June 1998 [doi>10.1023/A:1009715923555]
• 2: J. Platt. Probabilistic outputs for support vector machines and comparison to regularized likelihood methods. In B.S.A. Smola, P. Bartlett and D. Schuurmans, editors, Advances in Large Margin Classiers MIT Press, 1999.
• 3: S.E. Robertson, S. Walker, M. Hancock-Beaulieu, A. Gull, and M. Lau. Okapi at TREC4. In Text REtrieval Conference pages 21--30, 1992.
• 4: Y. Rui, T.S. Huang, and S. Mehrotra. Relevance feedback: A power too for interactive content-based image retrieval. IEEE Trans. on Circuits and Systems for Video Technology 8:644--655, September 1998.
• 5: Bernt Schiele , James L. Crowley, Object Recognition Using Multidimensional Receptive Field Histograms, Proceedings of the 4th European Conference on Computer Vision-Volume I, p.610-619, April 15-18, 1996
• 6: M.A. Stricker and M. Orengo. Similarity of color images. In Storage and Retrieval for Image and Video Databases (SPIE),pages 381--392, 1995.
• 7: Jean-Philippe Tarel , Sabri Boughorbel, On the choice of similarity measures for image retrieval by example, Proceedings of the tenth ACM international conference on Multimedia, December 01-06, 2002, Juan-les-Pins, France [doi>10.1145/641007.641105]
• 8: K. Tieu and P. Viola. Boosting image retrieval. In Intl. Conf. on Computer Vision pages 228--235, 2001.
• 9: Simon Tong , Edward Chang, Support vector machine active learning for image retrieval, Proceedings of the ninth ACM international conference on Multimedia, September 30-October 05, 2001, Ottawa, Canada [doi>10.1145/500141.500159]
• 10: TREC2002. TREC2002 video track, http://www.nlpir.nist.gov/projects/t2002v/t2002v.html.
• 11: L. Wu, C. Faloutsos, K.P. Sycara, and T.R. Payne. Multimedia queries by example and relevance feedback. IEEE Data Engineering Bulletin 24(3), 2001.
• 12: R. Yan, A. Hauptmann, and R. Jin. Multimedia search with pseudo-relevance feedback. In Intl Conf on Image and Video Retrieval pages 238--247, 2003.
• 13: R. Yan, A. Hauptmann,and R. Jin. Pseduo-relevance feedbackfor multimedia retrieval. In A. Rosenfeld, D. Doermann, and D. DeMenthon, editors, Video mining Kluwer Academic Publishers, 2003.
• 14: Hwanjo Yu , Jiawei Han , Kevin Chen-Chuan Chang, PEBL: positive example based learning for Web page classification using SVM, Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, July 23-26, 2002, Edmonton, Alberta, Canada [doi>10.1145/775047.775083]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Relevance feedback

General Terms:
Algorithms, Performance