102 search results - page 3 / 21 » A discriminatively trained, multiscale, deformable part mode... |
124
click to vote
ECCV
2006
Springer
16 years 2 months ago
2006
Springer
Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstra...
101
Voted
EMNLP
2008
15 years 1 months ago
2008
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...
97
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
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...
117
Voted
CVPR
2012
IEEE
13 years 2 months ago
2012
IEEE
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...
103
Voted
ECCV
2006
Springer
16 years 2 months ago
2006
Springer
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...