Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstra...
We present a discriminative, latent variable approach to syntactic parsing in which rules exist at multiple scales of refinement. The model is formally a latent variable CRF gramm...
We present a new method for training deformable models. Assume that we have training images where part locations have been labeled. Typically, one fits a model by maximizing the l...
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
This paper introduces the Located Hidden Random Field (LHRF), a conditional model for simultaneous part-based detection and segmentation of objects of a given class. Given a traini...