Traditionally, depictions and descriptions have been seen as complementary; depictions have been preferred to convey iconic or metaphorically iconic information whereas description...
We merge the Pictorial Computing Laboratory (PCL) approach to WIMP interaction with the Interaction Locus approach to structuring visual spaces as a step toward the definition of ...
Augusto Celentano, Daniela Fogli, Piero Mussio, Fa...
Abstract. We address the problem of articulated human pose estimation by learning a coarse-to-fine cascade of pictorial structure models. While the fine-level state-space of pose...
We investigate the task of 2D articulated human pose estimation in unconstrained still images. This is extremely challenging because of variation in pose, anatomy, clothing, and i...
We describe a general method for building cascade classifiers from part-based deformable models such as pictorial structures. We focus primarily on the case of star-structured mod...
Pedro Felzenszwalb, Ross Girshick, David McAlleste...