This paper presents a new approach for the binarization of seriously degraded manuscript. We introduce a new technique based on a Markov Random Field (MRF) model of the document. ...
This paper describes a language-independent, scalable system for both challenges of crossdocument co-reference: name variation and entity disambiguation. We provide system results...
This paper describes a complete system for reading typewritten lexicon words in noisy images - in this case museum index cards. The system is conceptually simple, and straightforw...
This paper introduces a web image dataset created by NUS’s Lab for Media Search. The dataset includes: (1) 269,648 images and the associated tags from Flickr, with a total of 5,...
In this paper we investigate how a small number of high-level concepts derived for video shots, such as Sports, Face, Indoor, etc., can be used effectively for ad hoc search in vi...