The ability to normalize pose based on super-category landmarks can significantly improve models of individual categories when training data are limited. Previous methods have co...
—The success of transfer to improve learning on a target task is highly dependent on the selected source data. Instance-based transfer methods reuse data from the source tasks to...
Navigating through new voicemail messages to find messages of interest is a time-consuming task, particularly for high-volume users. When checking messages under a time constraint...
A dynamic texture is a spatio-temporal generative model for video, which represents video sequences as observations from a linear dynamical system. This work introduces the mixtur...
Shallow parsers are usually assumed to be trained on noise-free material, drawn from the same distribution as the testing material. However, when either the training set is noisy ...