In this paper, we present a Deformable Action Template
(DAT) model that is learnable from cluttered real-world
videos with weak supervisions. In our generative model,
an action ...
We present an algorithm that learns invariant features from real data in an entirely unsupervised fashion. The principal benefit of our method is that it can be applied without hu...
A dynamic classification using the support vector machine (SVM) technique is presented in this paper as a new `incremental' framework for multiple-classifying video stream da...
The major problem in building a good lipreading system is to extract effective visual features from enormous quantity of video sequences data. For appearance-based feature analysi...
Yun Fu, Xi Zhou, Ming Liu, Mark Hasegawa-Johnson, ...
This paper shows (i) improvements over state-of-the-art local feature recognition systems, (ii) how to formulate principled models for automatic local feature selection in object c...