Crossing textual and visual content in different application scenarios

From Brede Wiki
Jump to: navigation, search
Paper (help)
Crossing textual and visual content in different application scenarios
Authors: Julien Ah-Pine, Marco Bressan, Stephane Clinchant, Gabriela Csurka, Yves Hoppenot, Jean-Michel Renders
Citation: Multimedia Tools and Applications 42 (1): 31-56. 2009
Database(s): Google Scholar cites
DOI: 10.1007/s11042-008-0246-8.
Link(s): http://dx.doi.org/10.1007/s11042-008-0246-8
Search
Web: Bing Google Yahoo!Google PDF
Article: BASE Google Scholar PubMed
Restricted: DTU Digital Library
Other: NIF
Services
Format: BibTeX
Extract: Talairach coordinates from linked PDF: CSV-formated wiki-formated

Crossing textual and visual content in different application scenarios describes a system which displays multimedia content in a visualization where the content is clustered. They work with text and images and describe the mathematics behind the image similarity, text similarity and "trans-media" similiary.

Contents

[edit] Data

Their system is evaluted on ImageCLEFphoto data and demonstrated on Wikipedia data.

[edit] Wikipedia

[edit] Text

Wikipedia pages: "This corpus concerns around 8,500 pages taken from the french Wikipedia corpus. We extracted these pages from the xml dump done in September 2007 and provided by the Wikipedia Foundation" (page 48).

They selected pages under the category "Geography" and "Tourism".

They do not use the whole part of the document only title, free-text image description and the paragraph where it is used.

Data was taken from the XML September 2007 dump.

[edit] Images

19,000 images

[edit] Results

They report performance on the ImageCLEFphoto 2008 data set with "MAP (Mean Average Precision) and P@20 (precision at 20)".

Personal tools