We propose an approach for cross-view action recognition by way of ‘virtual views’ that connect the action descriptors extracted from one (source) view to those extracted from...
A widely used technique to recover a 3D surface from photographs is patch-based (multi-view) stereo reconstruction. Current methods are able to reproduce fine surface details, th...
Improving coding and spatial pooling for bag-of-words based feature design have gained a lot of attention in recent works addressing object recognition and scene classification. ...
In this work, we present intrinsic shape context (ISC) descriptors for 3D shapes. We generalize to surfaces the polar sampling of the image domain used in shape contexts: for this...
Iasonas Kokkinos, Michael M. Bronstein, Roee Litma...
We consider the problem of shape recovery for real world scenes, where a variety of global illumination (interreflections, subsurface scattering, etc.) and illumination defocus e...