scene of multiple emotions. All generated clips
from both methods are random and therefore all characters
will have a different motion signature.
two approaches for the generation of novel video textures
which portray a human expressing different emotions. Here
training data is provided by video sequences of an actress
expressing specific emotions such as angry, happy and sad.
The main challenge of modelling these video texture sequences
is the high variance in head position and facial expression.
Principal Components Analysis (PCA) is used to generate so
called motion signatures which are shown to be
complex and have non-Gaussian distributions.
The first method uses a combined appearance model to transform
the video data into a lower dimensional Gaussian space. This
can then be modelled using a standard autoregressive process.
The second technique presented extracts sub-samples from the
original data using short temporal windows, some of which
have Gaussian distributions and can be modelled by an autoregressive
process (ARP). We find that the combined appearance technique
produces more aesthetically pleasing clips but does not maintain
the motion characteristics as well as the temporal window