We present SpeedBoost, a natural extension of functional gradient descent, for learning anytime predictors, which automatically trade computation time for predictive accuracy by s...
The problem of characterizing and detecting recurrent sequence patterns such as substrings or motifs and related associations or rules is variously pursued in order to compress da...
Alberto Apostolico, Mary Ellen Bock, Stefano Lonar...
Background: Most non-coding RNA families exert their function by means of a conserved, common secondary structure. The Rfam data base contains more than five hundred structurally ...
We present a scalable approach to recognizing and describing complex activities in video sequences. We are interested in long-term, sequential activities that may have several par...
We introduce an iterative algorithm for shape reconstruction from multiple images of a moving (Lambertian) object illuminated by distant (and possibly time varying) lighting. Star...
Jongwoo Lim, Jeffrey Ho, Ming-Hsuan Yang, David J....