Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
We develop a variant of the Nelder-Mead (NM) simplex search procedure for stochastic simulation optimization that is designed to avoid many of the weaknesses encumbering such dire...
Traditional classification methods assume that the training and the test data arise from the same underlying distribution. However, in several adversarial settings, the test set is...
This paper describes a new method to recover the sign of the local Gaussian curvature at each point on the visible surface of a 3-D object. Multiple (p > 3) shaded images are a...
Shinji Fukui, Yuji Iwahori, Akira Iwata, Robert J....
We propose to detect abnormal events via a sparse reconstruction over the normal bases. Given an over-complete normal basis set (e.g., an image sequence or a collection of local s...