A multimodal query expansion based on genetic programming for visually-oriented e-commerce applications |
| |
| Institution: | 1. Institute of Computing, Federal University of Amazonas, AM, Brazil;2. Department of Computer Science, Federal University of Minas Gerais, MG, Brazil;3. Institute of Computing, University of Campinas, SP, Brazil;1. Universidad Técnica Federico Santa María, Santiago, Chile;2. Universidad de Santiago de Chile, Santiago, Chile;3. CONICET, Universidad Nacional de San Luis, Argentina;4. Software Competence Center Hagenberg, Austria;1. Universitat Politècnica de València, 46022 Valencia, Spain;2. Sciling, 46022 Valencia, Spain;3. Brown University, Providence, RI 02912, United States;4. École Polytechnique de Montréal, QC 06079, Canada;1. Aix-Marseille Université, CNRS, Univ. Toulon, ENSAM (LSIS, UMR 7296), France;2. LIMSI, CNRS, Univ. Paris-Sud, Université Paris-Saclay, France;3. LIA, Université d’Avignon, France;4. IRIT UMR5505 CNRS, ESPE UT2J, Université de Toulouse, France |
| |
| Abstract: | We present a novel multimodal query expansion strategy, based on genetic programming (GP), for image search in visually-oriented e-commerce applications. Our GP-based approach aims at both: learning to expand queries with multimodal information and learning to compute the “best” ranking for the expanded queries. However, different from previous work, the query is only expressed in terms of the visual content, which brings several challenges for this type of application. In order to evaluate the effectiveness of our method, we have collected two datasets containing images of clothing products taken from different online shops. Experimental results indicate that our method is an effective alternative for improving the quality of image search results when compared to a genetic programming system based only on visual information. Our method can achieve gains varying from 10.8% against the strongest learning-to-rank baseline to 54% against an adhoc specialized solution for the particular domain at hand. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
