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...
Analysis of videos of human-object interactions involves understanding human movements, locating and recognizing objects and observing the effects of human movements on those obje...
We extend the "Sparse LDA" algorithm of [7] with new sparsity bounds on 2-class separability and efficient partitioned matrix inverse techniques leading to 1000-fold spe...
Protein fold recognition is a key step towards inferring the tertiary structures from amino-acid sequences. Complex folds such as those consisting of interacting structural repeat...
Phoneme set clustering of accurate modeling is important in the task of multilingual speech recognition, especially when each of the available language training corpora is mismatc...