In this paper a method for extraction of mid-level semantics from sign language videos is proposed, by employing high level domain knowledge. The semantics concern labeling of the ...
Blind separation of sources from nonlinear mixtures is a challenging and often ill-posed problem. We present three methods for solving this problem: an improved nonlinear factor a...
Antti Honkela, Harri Valpola, Alexander Ilin, Juha...
Abstract--In this paper, we develop an adaptive waveform design method for target tracking under a framework of sequential Bayesian inference. We employ polarization diversity to i...
Successful secondary structure predictions provide a starting point for direct tertiary structure modelling, and also can significantly improve sequence analysis and sequence-stru...
Previous research suggests that children can infer causal relations from patterns of events. However, what appear to be cases of causal inference may simply reduce to children rec...
David M. Sobel, Joshua B. Tenenbaum, Alison Gopnik