Although human action recognition has been the subject of much research in the past, the issue of viewpoint invariance has received scarce attention. In this paper, we present an ...
We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natur...
In this paper, we propose a novel and general approach for time-series data mining. As an alternative to traditional ways of designing specific algorithm to mine certain kind of ...
Yi Wang, Lizhu Zhou, Jianhua Feng, Jianyong Wang, ...
The objective of this work is automatic detection and identification of individuals in unconstrained consumer video, given a minimal number of labelled faces as training data. Whi...
Realistic audio-visual mapping remains a very challenging problem. Having short time delay between inputs and outputs is also of great importance. In this paper, we present a new ...