Abstract. Much recent research in human activity recognition has focused on the problem of recognizing simple repetitive (walking, running, waving) and punctual actions (sitting up...
—This paper is concerned with the representation and recognition of the observed dynamics (i.e., excluding purely spatial appearance cues) of spacetime texture based on a spatiot...
Abstract. Most software tools in homology recognition on proteins answer only a few specific questions, often leaving not much room for the interpretation of the results. We devel...
We present learning and inference algorithms for a versatile class of partially observed vector autoregressive (VAR) models for multivariate time-series data. VAR models can captu...
In this paper, we tackle the problem of understanding the temporal structure of complex events in highly varying videos obtained from the Internet. Towards this goal, we utilize a...