Best Paper Award PSI at British Machine Vision Conference

H. Bilen, V. P. Namboodiri, L. Van Gool, Object and Action Classification with Latent Variables. The British Machine Vision Conference (BMVC), 2011

In this paper we propose a generic framework to incorporate unobserved auxiliary information for classifying objects and actions. This framework allows us to explicitly
account for localisation and alignment of representations for generic object and action classes as latent variables. We approach this problem in the discriminative setting as
learning a max-margin classifier that infers the class label along with the latent variables.
Through this paper we make the following contributions a) We provide a method for incorporating latent variables into object and action classification b) We specifically account
for the presence of an explicit class related subregion which can include foreground and/or background. c)We explore a way to learn a better classifier by iterative expansion
of the latent parameter space. We demonstrate the performance of our approach by rigorous experimental evaluation on a number of standard object and action recognition datasets.

http://homes.esat.kuleuven.be/~hbilen/pubs/bilen2011bmvc.pdf