We present a generative model approach to explore intrinsic semantic structures in sport videos, e.g., the camera view in American football games. We will invoke the concept of se...
Recognizing speech, gestures, and visual features are important interface capabilities for future embedded mobile systems. Unfortunately, the real-time performance requirements of...
Presence of duplicate documents in the World Wide Web adversely affects crawling, indexing and relevance, which are the core building blocks of web search. In this paper, we pres...
Hema Swetha Koppula, Krishna P. Leela, Amit Agarwa...
Increasing applications are demanding effective and efficient support to perform retrieval in large collections of digital images. The work presented here is an early stage resear...
Giovanna Castellano, Gianluca Sforza, Maria Alessa...
Mixture models form one of the most widely used classes of generative models for describing structured and clustered data. In this paper we develop a new approach for the analysis...