Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
We introduce a new feature size for bounded domains in the plane endowed with an intrinsic metric. Given a point x in a domain X, the homotopy feature size of X at x measures half...
Jie Gao, Leonidas J. Guibas, Steve Oudot, Yue Wang
In the square linear blind source separation problem, one must nd a linear unmixing operator which can detangle the result xi(t) of mixing n unknown independent sources si(t) thro...
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
The support of peer-to-peer (P2P) resource sharing in dynamic scenarios is one of the most challenging research fields for both its expected commercial and technological impact o...
Laura Galluccio, Alessandro Leonardi, Antonio Mate...