In this paper, we explore the more practical aspects of building and rendering concentric mosaics. First, we use images captured with only approximately circular camera trajectorie...
We address the problem of effective reuse of subproblem solutions in dynamic programming. In dynamic programming, a memoed solution of a subproblem can be reused for another if th...
Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature conv...
The task of selecting and ordering information appears in multiple contexts in text generation and summarization. For instance, methods for title generation construct a headline b...
Understanding the source, data, and documentation files associated with legacy systems in preparation for maintenance or reengineering is an increasingly important problem for man...