Paper: Towards Automatic Image Region Annotation - Image Region Textual Coreference Resolution

ACL ID N09-2011
Title Towards Automatic Image Region Annotation - Image Region Textual Coreference Resolution
Venue Human Language Technologies
Session Short Paper
Year 2009
Authors

Detailed image annotation necessary for reli- able image retrieval involves not only annotat- ing the image as a single artifact, but also an- notating specific objects or regions within the image. Such detailed annotation is a costly en- deavor and the available annotated image data are quite limited. This paper explores the fea- sibility of using image captions from scientific journals for the purpose of automatically an- notating image regions. Salient image clues, such as an object location within the image or an object color, together with the associated explicit object mention, are extracted and clas- sified using rule-based and SVM learners.