International Journal of Computer Vision vol:106 issue:3 pages:237-251
In this paper we propose a generic frame-
work to incorporate unobserved auxiliary information
for classifying objects and actions. This framework al-
lows us to automatically select a bounding box and its
quadrants from which best to extract features. These
spatial subdivisions are learnt as latent variables. The
paper is an extended version of our earlier work ,
complemented with additional ideas, experiments and
We approach the classification problem in a discrim-
inative setting, as learning a max-margin classifier that
infers the class label along with the latent variables.
Through this paper we make the following contribu-
tions: a) we provide a method for incorporating latent
variables into object and action classification; b) these
variables determine the relative focus on foreground vs.
background information that is taken account of; c) we
design an objective function to more effectively learn in
unbalanced data sets; d) we learn a better classifier by
iterative expansion of the latent parameter space. We
demonstrate the performance of our approach through experimental evaluation on a number of standard object and action recognition data sets.
Bilen H., Namboodiri V.P., Van Gool L., ''Object and action classification with latent window parameters'', International journal of computer vision, vol. 106, no. 3, pp. 237-251, February 2014.