I am interested in efficient inference methods for computer vision. What makes models stand out to allow fast inference and how push the computational burden towards training time? In particular, I am working on human pose estimation from single images, a challenging structured prediction problem.
P. Gehler, C. Rother, M. Kiefel, L. Zhang, B. Schölkopf
(2011). Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance In: Advances in Neural Information Processing Systems 24, (Ed) J Shawe-Taylor and RS Zemel and PL Bartlett and FCN Pereira and KQ Weinberger, Curran Associates, Inc., Red Hook, NY, USA, 765-773, Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS 2011)