Many difficult visual perception problems, like 3D human motion estimation, can be formulated in terms of inference using complex generative models, defined over high-dimensional ...
Abstract. Achieving real-time response to complex, ambiguous, highbandwidth data is impractical with conventional programming. Only the narrow class of compressible input-output ma...
Abstract. While real-time garbage collection is now available in production virtual machines, the lack of generational capability means applications with high allocation rates are ...
Daniel Frampton, David F. Bacon, Perry Cheng, Davi...
SPFDs are a mechanism to express flexibility in Boolean networks. Introduced by Yamashita et al. in the context of FPGA synthesis [4], they were extended later to general combina...
Subarnarekha Sinha, Andreas Kuehlmann, Robert K. B...
This paper presents a paradigm for automatically generating complete camera specifications for capturing events in virtual 3D environments in real-time. We describe a fully implem...