Features Fusion for Diversity Gap Reduction

• Iago Breno Alves do Carmo Araujo Universidade de Feira de Santana
• Rodrigo Tripodi Calumby Universidade de Feira de Santana

DOI: https://doi.org/10.5753/sbbd.2016.24324

Resumo

Diversity has been promoted in image retrieval results using clustering algorithms to tackle queries, which refer to multiple information needs, e.g., due to ambiguity. Despite the effective results of diversity-aware methods, the image wealth of large collections and the subjectivity of human perception bring the semantic gap problem. This paper presents multimodal fusion approaches aimed at reducing the diversity gap with ensemble clustering and dimensionality reduction. The applied methods were evaluated by quantifying the clustering effectiveness in comparison to human decisions. The experimental results demonstrate the potential of these approaches to boost diversity-oriented engines and that they could improve state-of-the-art systems.

Palavras-chave: Clustering, Semantic gap problem

Referências

Boteanu, B., Mironica, I., and Ionescu, B. (2015). Hierarchical clustering pseudo-relevance feedback for social image search result diversification. In CBMI, pages 1–6.

Calumby, R. T., Araujo, I. B. A. d. C., Santana, V. P., Munoz, J. A., Penatti, O. A., Li, L. T., Almeida, J., Chiachia, G., Gonçalves, M. A., and Torres, R. d. S. (2015). Recod @ mediaeval 2015: Diverse social images retrieval. Working Notes of MediaEval.

Gan, G., Ma, C., and Wu, J. (2007). Data clustering: theory, algorithms, and applications, volume 20. Siam.

Han, J., Kamber, M., and Pei, J. (2012). Data Mining: Concepts and techniques. Morgan Kaufmann.

Ionescu, B., Popescu, A., Lupu, M., Gînsca, A.-L., and Müller, Henning, B. B. (2015). Retrieving diverse social images at mediaeval 2015: Challenge, dataset and evaluation. In MediaEval.

Jain, A. K. (2010). Data clustering: 50 years beyond k-means. Pattern Recogn. Lett., 31(8):651–666.

Karypis, G., Han, E.-H., and Kumar, V. (1999). Chameleon: Hierarchical clustering using dynamic modeling. Computer, 32(8):68–75.

Liang, S., Ren, Z., and De Rijke, M. (2014). Fusion helps diversification. In ACM SIGIR, pages 303–312. ACM.

Ounis, I., Macdonald, C., and Santos, R. L. (2015). Search result diversification. Found Trends Inf Ret, 9(1):1–90.

Sabetghadam, S., Palotti, J., Rekabsaz, N., Lupu, M., and Hanburry, A. (2015). Tuw @ mediaeval 2015 retrieving diverse social images. Working Notes of MediaEval.

Spyromitros-Xioufis, E., Popescu, A., Papadopoulos, S., and Kompatsiaris, I. (2015). Usemp: Finding diverse images at mediaeval 2015. Working Notes of MediaEval.

Strehl, A. and Ghosh, J. (2002). Cluster ensembles—a knowledge reuse framework for combining multiple partitions. JMLR, 3(Dec):583–617.

Veltkamp, R. C. and Tanase, M. (2002). Content-Based Image and Video Retrieval, chapter A Survey of Content-Based Image Retrieval Systems, pages 47–101.

Zaki, M. J. and Meira Jr, W. (2014). Data Mining and Analysis: Fundamental Concepts and Algorithms. Cambridge University Press, New York, NY.

Zhang, T., Ramakrishnan, R., and Livny, M. (1996). Birch: an efficient data clustering method for very large databases. In ACM SIGMOD, volume 25, pages 103–114.