Title:  A study on the evaluation of relevance feedback in multi-tagged image datasets
Internal authors: 
Issue Date:  2011
Authors:  Tronci R; Falqui L; Piras L; Giacinto G
Book title:  2011 IEEE International Symposium on Multimedia, ISM 2011. Proceedings
ISBN:  978-1-4577-2015-4
Publisher name:  IEEE
Conference section:  contributo
First page:  452
Last page:  457
Number of pages:  6
Digital Object Identifier (DOI):  http://dx.doi.org/10.1109/ISM.2011.80
Scopus identifier:  2-s2.0-84856344599
Peer review:  Esperti anonimi
Conference name:  IEEE International Workshop on Multimedia Information Processing and Retrieval, MIPR 2011
Conference date:  5-7 December 2011
Conference place:  Diana Point, CA, USA
Abstract:  This paper proposes a study on the evaluation of relevance feedback approaches when a multi-tagged dataset is available. The aim of this study is to verify how the relevance feedback works in a real-word scenario, i.e. by taking into account the multiple concepts represented by the query image. To this end, we first assessed how relevance feedback mechanisms adapt the search when the same image is used for retrieving different concepts. Then, we investigated the scenarios in which the same image is used for retrieving multiple concepts. The experimental results shows that relevance feedback can effectively focus the search according to the user's feedback even if the query image provides a rough example of the target concept. We also propose two performance measures aimed at comparing the accuracy of retrieval results when the same image is used as a prototype for a number of different concepts.
Type: 4.1 Contributo in Atti di convegno

Files in This Item:
There are no files associated with this item.

Questionnaire and social

Share on: