Sciweavers

1144 search results - page 47 / 229
» Energy-Based Models in Document Recognition and Computer Vis...
Sort
View
CVPR
2012
IEEE
13 years 6 days ago
Social behavior recognition in continuous video
We present a novel method for analyzing social behavior. Continuous videos are segmented into action ‘bouts’ by building a temporal context model that combines features from s...
Xavier P. Burgos-Artizzu, Piotr Dollár, Day...
WACV
2012
IEEE
13 years 5 months ago
Kernel analysis over Riemannian manifolds for visual recognition of actions, pedestrians and textures
A convenient way of analysing Riemannian manifolds is to embed them in Euclidean spaces, with the embedding typically obtained by flattening the manifold via tangent spaces. This...
Mehrtash Tafazzoli Harandi, Conrad Sanderson, Arno...
CVPR
2012
IEEE
13 years 6 days ago
3D visual phrases for landmark recognition
In this paper, we study the problem of landmark recognition and propose to leverage 3D visual phrases to improve the performance. A 3D visual phrase is a triangular facet on the s...
Qiang Hao, Rui Cai, Zhiwei Li, Lei Zhang 0001, Yan...
CVPR
2007
IEEE
15 years 11 months ago
Adaptive Patch Features for Object Class Recognition with Learned Hierarchical Models
We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
Fabien Scalzo, Justus H. Piater
CVPR
2008
IEEE
15 years 11 months ago
Learning 4D action feature models for arbitrary view action recognition
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...
Pingkun Yan, Saad M. Khan, Mubarak Shah