Recent approaches to action classification in videos have used sparse spatio-temporal words encoding local appearance around interesting movements. Most of these approaches use a ...
Biometric fusion consolidates the output of multiple biometric classifiers to render a decision about the identity of an individual. We consider the problem of designing a fusion s...
Background: Integrating data from multiple global assays and curated databases is essential to understand the spatiotemporal interactions within cells. Different experiments measu...
Yuji Zhang, Jianhua Xuan, Benildo de los Reyes, Ro...
In this paper, we develop the continuous time dynamic topic model (cDTM). The cDTM is a dynamic topic model that uses Brownian motion to model the latent topics through a sequenti...
We consider the problem of improving named entity recognition (NER) systems by using external dictionaries--more specifically, the problem of extending state-of-the-art NER system...