Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant with good resistance to local occlusions and to geomet...
Non-blind deconvolution is a key component in image deblurring systems. Previous deconvolution methods assume a linear blur model where the blurred image is generated by a linear ...
The appearance of non-rigid objects detected and tracked in video streams is highly variable and therefore makes the identification of similar objects very complex. Furthermore, i...
This paper describes the Arabic broadcast transcription system fielded by IBM in the GALE Phase 3.5 machine translation evaluation. Key advances compared to our Phase 2.5 system ...
George Saon, Hagen Soltau, Upendra Chaudhari, Step...
We consider the problem of multi-task reinforcement learning where the learner is provided with a set of tasks, for which only a small number of samples can be generated for any g...