Supervised Learning Methods for Diversification of Image Search Results

We adopt a supervised learning framework, namely R-LTR [17], to diversify image search results, and extend it in various ways. Our experiments show that the adopted and proposed variants are superior to two well-known baselines, with relative gains up to 11.4%.

Detalles Bibliográficos
Autores principales: Goynuk, Burak, Altingovde, Ismail Sengor
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7148049/
http://dx.doi.org/10.1007/978-3-030-45442-5_20
Descripción
Sumario:We adopt a supervised learning framework, namely R-LTR [17], to diversify image search results, and extend it in various ways. Our experiments show that the adopted and proposed variants are superior to two well-known baselines, with relative gains up to 11.4%.

Ejemplares similares