Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Within the world of multimedia, the new MPEG-21 standard is currently under development. The purpose of this new standard is to create an open framework for multimedia delivery an...
Frederik De Keukelaere, Thomas DeMartini, Jeroen B...
This paper develops a general, formal framework for modeling term dependencies via Markov random fields. The model allows for arbitrary text features to be incorporated as eviden...
Abstract. This paper proposes a lexicon-constrained character model that combines both word and character features to solve complicated issues in Chinese morphological analysis. A ...
We present a non-traditional retrieval problem we call subtopic retrieval. The subtopic retrieval problem is concerned with finding documents that cover many different subtopics ...
ChengXiang Zhai, William W. Cohen, John D. Laffert...