Sciweavers

881 search results - page 128 / 177
» Training Deformable Models for Localization
Sort
View
CVPR
2012
IEEE
13 years 5 months ago
Discovering discriminative action parts from mid-level video representations
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...
Michalis Raptis, Iasonas Kokkinos, Stefano Soatto
CVPR
2012
IEEE
13 years 5 months ago
Occlusion reasoning for object detection under arbitrary viewpoint
We present a unified occlusion model for object instance detection under arbitrary viewpoint. Whereas previous approaches primarily modeled local coherency of occlusions or attem...
Edward Hsiao, Martial Hebert
CVPR
2004
IEEE
16 years 4 months ago
Shape Correspondence through Landmark Sliding
Motivated by improving statistical shape analysis, this paper presents a novel landmark-based method for accurate shape correspondence, where the general goal is to align multiple...
Song Wang, Toshiro Kubota, Theodor Richardson
ICCV
2001
IEEE
16 years 4 months ago
Incorporating Differential Constraints in a 3D Reconstruction Process. Application to Stereo
We propose to incorporate a priori geometric constraints in a 3?D stereo reconstruction scheme to cope with the many cases where image information alone is not sufficient to accur...
Richard Lengagne, Pascal Fua
MICCAI
2009
Springer
16 years 4 months ago
Asymmetric Image-Template Registration
A natural requirement in pairwise image registration is that the resulting deformation is independent of the order of the images. This constraint is typically achieved via a symmet...
Mert R. Sabuncu, B. T. Thomas Yeo, Koen Van Leem...