The article entitled “A multimodal query expansion based on genetic programming for visually-oriented e-commerce applications” presents a novel multimodal query expansion strategy, based on genetic programming (GP), for image search in visually-oriented e-commerce applications. The proposed solution allows finding relevant products related to an image query even though their image representation is not (very) similar to the query.
In order to evaluate the solution, the authors adopted the scenario of searching for fashion and accessories in e-commerce Web sites. The achieved results indicate that expressive gains in the quality of the responses can be obtained in this scenario when using our proposed multimodal expansion method, in comparison to use adhoc solutions or even other learning-to-rank alternatives.
Patrícia C. Saraiva, João M.B. Cavalcanti, Edleno S. de Moura, Marcos A. Gonçalves, Ricardo da S. Torres, A multimodal query expansion based on genetic programming for visually-oriented e-commerce applications, Information Processing & Management, Volume 52, Issue 5, September 2016, Pages 783-800, ISSN 0306-4573, http://dx.doi.org/10.1016/j.ipm.2016.03.001.