In this paper, we tackle the problem of learning a user's interest from his photo collections and suggesting relevant ads. We address two key challenges in this work: 1) unde...
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
User feedback has proven very successful to query large multimedia databases. Due to the nature of the data representation and the mismatch between mathematical models and human p...
Renaissance artists discovered methods for imaging realistic depth on a two dimensional surface by re-inventing linear perspective. In solving the problem of depth depiction, they...
Well tuned Large-Vocabulary Continuous Speech Recognition (LVCSR) has been shown to generally be more effective than vocabulary-independent techniques for ranked retrieval of spo...