29 search results - page 2 / 6 » Correlating Text and Images: Concept and Evaluation |
SIGIR
2006
ACM
13 years 11 months ago
2006
ACM
This paper employs ConceptNet, which covers a rich set of commonsense concepts, to retrieve images with text descriptions by focusing on spatial relationships. Evaluation on test ...
CIVR
2009
Springer
14 years 11 days ago
2009
Springer
Describing shots through the occurrence of semantic concepts is the first step towards modeling the content of a video semantically. An important challenge is to automatically se...
ICFHR
2010
13 years 19 days ago
2010
There are many video images where hand written text may appear. Therefore handwritten scene text detection in video is essential and useful for many applications for efficient ind...
PRICAI
2010
Springer
13 years 4 months ago
2010
Springer
Conventional methods for multimodal data retrieval use text-tag based or cross-modal approaches such as tag-image co-occurrence and canonical correlation analysis. Since there are ...
CLEF
2007
Springer
13 years 12 months ago
2007
Springer
This paper presents the LIG contribution to the CLEF 2007 medical retrieval task (i.e. ImageCLEFmed). The main idea in this paper is to incorporate medical knowledge in the langua...