P
Patricia Correia Saraiva
Researcher at Federal University of Amazonas
Publications - 5
Citations - 188
Patricia Correia Saraiva is an academic researcher from Federal University of Amazonas. The author has contributed to research in topics: Image retrieval & Ranking (information retrieval). The author has an hindex of 5, co-authored 5 publications receiving 184 citations. Previous affiliations of Patricia Correia Saraiva include Universidade Federal de Minas Gerais.
Papers
More filters
Proceedings ArticleDOI
Rank-preserving two-level caching for scalable search engines
Patricia Correia Saraiva,Edleno Silva de Moura,Nivio Ziviani,Wagner Meira,Rodrigo Fonseca,Berthier Ribeiro-Neto +5 more
TL;DR: Experimental results show that the two-level cache is superior, and that it allows increasing the maximum number of queries processed per second by a factor of three, while preserving the response time.
Journal ArticleDOI
A multimodal query expansion based on genetic programming for visually-oriented e-commerce applications
Patricia Correia Saraiva,João M. B. Cavalcanti,Edleno Silva de Moura,Marcos André Gonçalves,Ricardo da Silva Torres +4 more
TL;DR: Experimental results indicate that the novel multimodal query expansion strategy, based on genetic programming (GP), for image search in visually-oriented e-commerce applications is an effective alternative for improving the quality of image search results when compared to a genetic programming system based only on visual information.
Journal Article
Evaluating Retrieval Effectiveness of Descriptors for Searching in Large Image Databases
Petrina A. S. Kimura,João M. B. Cavalcanti,Patricia Correia Saraiva,Ricardo da Silva Torres,Marcos André Gonçalves +4 more
TL;DR: An evaluation of image descriptors for searching in large image databases shows that in general the retrieval effectiveness of the different descriptors varies little in small image collections whereas in large image collections they differ significantly.
Book ChapterDOI
Multimodal re-ranking of product image search results
Joyce Miranda dos Santos,João M. B. Cavalcanti,Patricia Correia Saraiva,Edleno Silva de Moura +3 more
TL;DR: This article proposes an image re-ranking strategy based on multimedia information available on product databases, which relies on category and textual information associated to the top-k images of an initial ranking computed purely with CBIR techniques.
Journal ArticleDOI
Evaluation of parameters for combining multiple textual sources of evidence for Web image retrieval using genetic programming
Patricia Correia Saraiva,João M. B. Cavalcanti,Marcos André Gonçalves,Katia C. Lage dos Santos,Edleno Silva de Moura,Ricardo da Silva Torres +5 more
TL;DR: Experiments performed using a collection with more than 195,000 images extracted from the Web showed that the evolutionary approach outperforms the best baseline the authors used with gains of 22.36 % in terms of mean average precision.