This work proposes a learning method for deep architectures that takes advantage of sequential data, in particular from the temporal coherence that naturally exists in unlabeled v...
The paper describes an incremental advance in search engine from Internet information searching to information summarizing service. This incremental innovation requires only exist...
In this paper, we propose a method to detect raindrops from in-vehicle camera images and recognize rainfall using time-series information. We aim to improve the accuracy of raindr...
A scheme for pose-independent face recognition is presented. An "unwrapped" texture map is constructed from a video sequence using a texture-from-motion approach, which ...
We consider the problem of obtaining the 3D trajectory of a ball from a sequence of images taken with a camera which is possibly rotating and zooming (but not translating). Techni...