Vector data represents one major category of data managed by GIS. This paper presents a new technique for vector-data display that is able to precisely and efficiently map vector ...
Tracking human lips in video is an important but notoriously dicult task. To accurately recover their motions in 3D from any head pose is an even more challenging task, though s...
Large vocabulary continuous speech recognition (LVCSR) systems traditionally represent words in terms of smaller subword units. Both during training and during recognition, they re...
The new video-coding standard MPEG-4 enables content-based functionality, as well as high coding efficiency, by taking into account shape information of moving objects. A novel alg...
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...