Rank diffusion for context-based image retrieval

• Autor(a) principal: Pedronette, Daniel Carlos Guimarães [UNESP]
• Data de Publicação: 2016
• Outros Autores: Torres, Ricardo Da S.
• Tipo de documento: Artigo de conferência
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1145/2911996.2912060; http://hdl.handle.net/11449/168817
• topic: Content-based image retrieval; Rank diffusion process; Unsupervised distance learning

This paper presents an efficient diffusion-based re-ranking approach. The proposed method propagates contextual information defined in terms of top-ranked objects of ranked lists in a diffusion process. That makes the method suitable for large scale real-world collections. Experiments were conducted considering public image collections, several descriptors, and comparisons with state-of-the-art methods. Experimental results demonstrate that the proposed method provides high effectiveness gains with low computational costs.