Unsupervised Rank Aggregation for Cold-Start Reduction in Multimodal Image Retrieval
Abstract
In content-based image retrieval systems, the objective of relevance feedback techniques is to enable the user to express her need without specific knowledge of the low-level image features. For a proper behaviour of this technique, the result set prior to the first interaction of the user must present relevant results. Aiming at attenuating the cold-start problem and improving the initial set, this work experimentally evaluated several rank aggregation methods to combine results obtained with different image ranking features. The results showed promising effectiveness when compared to the baselines considering different modalities of features.
Keywords:
Rank Aggregation, Cold-Start, Image Retrieval
References
Arni, T., Clough, P., Sanderson, M., and Grubinger, M. (2009). Overview of the imageclefphoto 2008 photographic retrieval task. In Evaluating Systems for Multilingual and Multimodal Information Access, pages 500–511. Springer Berlin Heidelberg. DOI: https://doi.org/10.1145/2964797.2964811
Atrey, P. K., Hossain, M. A., El Saddik, A., and Kankanhalli, M. S. (2010). Multimodal fusion for multimedia analysis: A survey. Multimedia Syst., 16(6):345–379. DOI: https://doi.org/10.1007/s00530-010-0182-0
Baeza-Yates, R. and Ribeiro-Neto, B. (2008). Modern Information Retrieval: The Concepts and Technology Behind Search. USA, 2nd edition. DOI: https://doi.org/10.5860/choice.48-6950
Calumby, R., R. da S, T., and M. A, G. (2014). Multimodal retrieval with relevance feedback based on genetic programming. MTAP, (69):991–1019. DOI: https://doi.org/10.1007/s11042-012-1152-7
Calumby, R. T., Gonc¸alves, M. A., and da Silva Torres, R. (2017). Diversity-based interactive learning meets multimodality. Neurocomputing, 259:159 – 175. DOI: https://doi.org/10.13039/501100002322
Cormack, G. V., Clarke, C. L. A., and Buettcher, S. (2009). Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In Proceedings of the 32Nd SIGIR, pages 758–759. ACM. DOI: https://doi.org/10.1145/1571941.1572114
dos Santos, K. C. L., de Almeida, H. M., Gonçalves, M. A., and da Silva Torres, R. (2009). Recuperacão de imagens da web utilizando múltiplas evidências textuais e programação genética. In Proceedings of the XXIV SBBD, pages 91–105. DOI: https://doi.org/
Fagin, R., Kumar, R., and Sivakumar, D. (2003). Efficient similarity search and classification via rank aggregation. In Proceedings of the SIGMOD, pages 301–312. ACM. DOI: https://doi.org/10.1145/872757.872795
Ferreira, C., Santos, J., da S. Torres, R., Gonçalves, M., Rezende, R., and Fan, W. (2011). Relevance feedback based on genetic programming for image retrieval. Pattern Recognition Letters, 32(1):27 – 37. DOI: https://doi.org/10.1016/j.patrec.2010.05.015
Lewis, J., Ossowski, S., Hicks, J., Errami, M., and Garner, H. R. (2006). Text similarity: an alternative way to search MEDLINE. Bioinformatics, 22(18):2298–2304. DOI: https://doi.org/10.1093/bioinformatics/btl388
Lin, S. (2010). Rank aggregation methods. Wiley Interdisciplinary Reviews: Computational Statistics, 2(5):555–570. DOI: https://doi.org/10.1002/wics.111
Mei, T., Rui, Y., Li, S., and Tian, Q. (2014). Multimedia search reranking: A literature survey. ACM Comput. Surv., 46(3):38:1–38:38. DOI: https://doi.org/10.1145/2536798
Penatti, O. A., Valle, E., and da S. Torres, R. (2012). Comparative study of global color and texture descriptors for web image retrieval. Journal of Visual Communication and Image Representation, 23(2):359 – 380. DOI: https://doi.org/10.1016/j.jvcir.2011.11.002
Shaw, J. A. and Fox, E. A. (1994). Combination of multiple searches. In TREC-2, pages 243–252. DOI: https://doi.org/
Torres, R. D. S. and Falcão, A. X. (2006). Content-based image retrieval: Theory and applications. Revista de Informática Teórica e Aplicada, 13:161–185. DOI: https://doi.org/
Vargas Muñoz, J. A., da Silva Torres, R., and Gonçalves, M. A. (2015). A soft computing approach for learning to aggregate rankings. In Proceedings of the 24th CIKM, pages 83–92. ACM. DOI: https://doi.org/10.1145/2806416.2806478
Young, H. (1974). An axiomatization of borda’s rule. Journal of Economic Theory, 9(1):43 – 52. DOI: https://doi.org/
Atrey, P. K., Hossain, M. A., El Saddik, A., and Kankanhalli, M. S. (2010). Multimodal fusion for multimedia analysis: A survey. Multimedia Syst., 16(6):345–379. DOI: https://doi.org/10.1007/s00530-010-0182-0
Baeza-Yates, R. and Ribeiro-Neto, B. (2008). Modern Information Retrieval: The Concepts and Technology Behind Search. USA, 2nd edition. DOI: https://doi.org/10.5860/choice.48-6950
Calumby, R., R. da S, T., and M. A, G. (2014). Multimodal retrieval with relevance feedback based on genetic programming. MTAP, (69):991–1019. DOI: https://doi.org/10.1007/s11042-012-1152-7
Calumby, R. T., Gonc¸alves, M. A., and da Silva Torres, R. (2017). Diversity-based interactive learning meets multimodality. Neurocomputing, 259:159 – 175. DOI: https://doi.org/10.13039/501100002322
Cormack, G. V., Clarke, C. L. A., and Buettcher, S. (2009). Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In Proceedings of the 32Nd SIGIR, pages 758–759. ACM. DOI: https://doi.org/10.1145/1571941.1572114
dos Santos, K. C. L., de Almeida, H. M., Gonçalves, M. A., and da Silva Torres, R. (2009). Recuperacão de imagens da web utilizando múltiplas evidências textuais e programação genética. In Proceedings of the XXIV SBBD, pages 91–105. DOI: https://doi.org/
Fagin, R., Kumar, R., and Sivakumar, D. (2003). Efficient similarity search and classification via rank aggregation. In Proceedings of the SIGMOD, pages 301–312. ACM. DOI: https://doi.org/10.1145/872757.872795
Ferreira, C., Santos, J., da S. Torres, R., Gonçalves, M., Rezende, R., and Fan, W. (2011). Relevance feedback based on genetic programming for image retrieval. Pattern Recognition Letters, 32(1):27 – 37. DOI: https://doi.org/10.1016/j.patrec.2010.05.015
Lewis, J., Ossowski, S., Hicks, J., Errami, M., and Garner, H. R. (2006). Text similarity: an alternative way to search MEDLINE. Bioinformatics, 22(18):2298–2304. DOI: https://doi.org/10.1093/bioinformatics/btl388
Lin, S. (2010). Rank aggregation methods. Wiley Interdisciplinary Reviews: Computational Statistics, 2(5):555–570. DOI: https://doi.org/10.1002/wics.111
Mei, T., Rui, Y., Li, S., and Tian, Q. (2014). Multimedia search reranking: A literature survey. ACM Comput. Surv., 46(3):38:1–38:38. DOI: https://doi.org/10.1145/2536798
Penatti, O. A., Valle, E., and da S. Torres, R. (2012). Comparative study of global color and texture descriptors for web image retrieval. Journal of Visual Communication and Image Representation, 23(2):359 – 380. DOI: https://doi.org/10.1016/j.jvcir.2011.11.002
Shaw, J. A. and Fox, E. A. (1994). Combination of multiple searches. In TREC-2, pages 243–252. DOI: https://doi.org/
Torres, R. D. S. and Falcão, A. X. (2006). Content-based image retrieval: Theory and applications. Revista de Informática Teórica e Aplicada, 13:161–185. DOI: https://doi.org/
Vargas Muñoz, J. A., da Silva Torres, R., and Gonçalves, M. A. (2015). A soft computing approach for learning to aggregate rankings. In Proceedings of the 24th CIKM, pages 83–92. ACM. DOI: https://doi.org/10.1145/2806416.2806478
Young, H. (1974). An axiomatization of borda’s rule. Journal of Economic Theory, 9(1):43 – 52. DOI: https://doi.org/
Published
2019-10-07
How to Cite
DA SILVA, Wanderson Bezerra; CALUMBY, Rodrigo Tripodi.
Unsupervised Rank Aggregation for Cold-Start Reduction in Multimodal Image Retrieval. In: BRAZILIAN SYMPOSIUM ON DATABASES (SBBD), 34. , 2019, Fortaleza.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 277-282.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2019.8836.
