One of the main challenges faced by the current face recognition techniques lies in the difficulties of collecting samples. Fewer samples per person mean less laborious effort for...
Video temporal segmentation is normally the first and important step for content-based video applications. Many features including the pixel difference, colour histogram, motion, ...
The performance of many supervised and unsupervised learning algorithms is very sensitive to the choice of an appropriate distance metric. Previous work in metric learning and ada...
Most traditional text clustering methods are based on "bag of words" (BOW) representation based on frequency statistics in a set of documents. BOW, however, ignores the ...
Jian Hu, Lujun Fang, Yang Cao, Hua-Jun Zeng, Hua L...
We have designed and built a mobile emotional messaging system named eMoto. With it, users can compose messages through using emotion-related gestures as input, rendering a backgr...