PUMA
Istituto di Scienza e Tecnologie dell'Informazione     
Amato G., Falchi F., Rabitti F., Vadicamo L. Combining fisher vector and convolutional neural networks for image retrieval. In: IIR 2016 - Italian Information Retrieval Workshop (Venezia, Italy, 30-31 May 2016). Atti, article n. 19. Giorgio Maria Di Nunzio, Franco Maria Nardini, Salvatore Orlando (eds.). (CEUR Workshop Proceedings, vol. 1653). CEUR-WS.org, 2016.
 
 
Abstract
(English)
Fisher Vector (FV) and deep Convolutional Neural Network (CNN) are two popular approaches for extracting effective image representations. FV aggregates local information (e.g., SIFT) and have been state-of-the-art before the recent success of deep learning approaches. Recently, combination of FV and CNN has been investigated. However, only the aggregation of SIFT has been tested. In this work, we propose combining CNN and FV built upon binary local features, called BMM-FV. The results show that BMM-FV and CNN improve the latter retrieval performance with less computational effort with respect to the use of the traditional FV which relies on non-binary features.
URL: http://ceur-ws.org/Vol-1653/paper_19.pdf
Subject Fisher Vector
Convolutional Neural Network
Content based image retrieval
H.3.3 INFORMATION STORAGE AND RETRIEVAL. Information Search and Retrieval


Icona documento 1) Download Document PDF


Icona documento Open access Icona documento Restricted Icona documento Private

 


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional