


Clusters all cuboids in DATASETS (based on their descriptions).
INPUTS
DATASETS - array of structs, should have the fields:
.cuboids - [optional] length N cell vector of sets of cuboids
.desc - length N cell vector of cuboid descriptors
k - number of clusters to use
par_kmeans - parameters for kmeans2
OUTPUTS
clusters - cluster centers
M - cluster movie, slow to calculate
See also RECOG_TEST