Browse wiki

Jump to: navigation, search
Image interpretation using large corpus: Wikipedia
Abstract Image is a powerful medium for expressing Image is a powerful medium for expressing one's ideas and rightly confirms the adage, One picture is worth a thousand words. In this work, we explore the application of world knowledge in the form of Wikipedia to achieve this objectiveliterally. In the first part, we disambiguate and rank semantic concepts associated with ambiguous keywords by exploiting link structure of articles in Wikipedia. In the second part, we explore an image representation in terms of keywords which reflect the semantic content of an image. Our approach is inspired by the desire to augment low-level image representation with massive amounts of world knowledge, to facilitate computer vision tasks like image retrieval based on this information. We represent an image as a weighted mixture of a predetermined set of concrete concepts whose definition has been agreed upon by a wide variety of audience. To achieve this objective, we use concepts defined by Wikipedia articles, e.g., sky, building, or automobile. An important advantage of our approach is availability of vast amounts of highly organized human knowledge in Wikipedia. Wikipedia evolves rapidly steadily increasing its breadth and depth over time.ncreasing its breadth and depth over time.
Abstractsub Image is a powerful medium for expressing Image is a powerful medium for expressing one's ideas and rightly confirms the adage, One picture is worth a thousand words. In this work, we explore the application of world knowledge in the form of Wikipedia to achieve this objectiveliterally. In the first part, we disambiguate and rank semantic concepts associated with ambiguous keywords by exploiting link structure of articles in Wikipedia. In the second part, we explore an image representation in terms of keywords which reflect the semantic content of an image. Our approach is inspired by the desire to augment low-level image representation with massive amounts of world knowledge, to facilitate computer vision tasks like image retrieval based on this information. We represent an image as a weighted mixture of a predetermined set of concrete concepts whose definition has been agreed upon by a wide variety of audience. To achieve this objective, we use concepts defined by Wikipedia articles, e.g., sky, building, or automobile. An important advantage of our approach is availability of vast amounts of highly organized human knowledge in Wikipedia. Wikipedia evolves rapidly steadily increasing its breadth and depth over time.ncreasing its breadth and depth over time.
Bibtextype inproceedings  +
Doi 10.1109/JPROC.2010.2050410  +
Has author Rahurkar M. + , Tsai S.-F. + , Dagli C. + , Huang T.S. +
Has extra keyword Human knowledge + , Image interpretation + , Image representations + , Link structure + , Semantic concept + , Semantic content + , Use concept + , Wikipedia + , World knowledge + , Computer vision + , Image analysis + , Image understanding + , Semantics + , Knowledge representation +
Has keyword Concepts + , Image understanding + , Wikipedia +
Issn 189219  +
Issue 8  +
Language English +
Number of citations by publication 0  +
Number of references by publication 0  +
Pages 1509–1525  +
Published in Proceedings of the IEEE +
Title Image interpretation using large corpus: Wikipedia +
Type conference paper  +
Volume 98  +
Year 2010 +
Creation dateThis property is a special property in this wiki. 7 November 2014 19:16:42  +
Categories Publications without license parameter  + , Publications without remote mirror parameter  + , Publications without archive mirror parameter  + , Publications without paywall mirror parameter  + , Conference papers  + , Publications without references parameter  + , Publications  +
Modification dateThis property is a special property in this wiki. 7 November 2014 19:16:42  +
DateThis property is a special property in this wiki. 2010  +
hide properties that link here 
Image interpretation using large corpus: Wikipedia + Title
 

 

Enter the name of the page to start browsing from.