We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
Content-based retrieval (CBIR) methods in medical databases have been designed to support specific tasks, such as retrieval of digital mammograms or 3D MRI images. These methods c...
Semantic peer to peer (P2P) systems are fully decentralized overlay networks of people or machines (called peers) sharing and searching varied resources (documents, videos, photos...
Gia Hien Nguyen, Philippe Chatalic, Marie-Christin...
A knowledge-intensive problem is often not solved by an individual knowledge artifact; rather the solution needs to draw upon multiple, and even heterogeneous, knowledge artifacts....
We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...