We address document image classification by visual appearance. An image is represented by a variable-length list of visually salient features. A hierarchical Bayesian network is ...
We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the e...
Erik B. Sudderth, Antonio B. Torralba, William T. ...
This paper presents the XML-based formats ALTO, TEI, METS used for Digital Libraries and their interest for data representation in a Document Image Analysis and Recognition (DIAR)...
—We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden condi...
Recognition and retrieval of historical handwritten material is an unsolved problem. We propose a novel approach to recognizing and retrieving handwritten manuscripts, based upon ...