Sciweavers

593 search results - page 32 / 119
» Unsupervised Learning of Invariant Features Using Video
Sort
View
JMLR
2010
206views more  JMLR 2010»
13 years 2 months ago
Learning Translation Invariant Kernels for Classification
Appropriate selection of the kernel function, which implicitly defines the feature space of an algorithm, has a crucial role in the success of kernel methods. In this paper, we co...
Sayed Kamaledin Ghiasi Shirazi, Reza Safabakhsh, M...
ICCV
2009
IEEE
15 years 19 days ago
Learning Actions From the Web
This paper proposes a generic method for action recognition in uncontrolled videos. The idea is to use images collected from the Web to learn representations of actions and use ...
Nazli Ikizler-Cinbis, R. Gokberk Cinbis, Stan Scla...
3DIM
2005
IEEE
14 years 1 months ago
Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets
This paper presents a system for fully automatic recognition and reconstruction of 3D objects in image databases. We pose the object recognition problem as one of finding consist...
Matthew Brown, David G. Lowe
MVA
2007
160views Computer Vision» more  MVA 2007»
13 years 9 months ago
Probabilistic Motion Segmentation of Videos for Temporal Super Resolution
A novel scheme is proposed for achieving motion segmentation in low-frame rate videos, with application to temporal super resolution. Probabilistic generative models are commonly ...
Arasanathan Thayananthan, Masahiro Iwasaki, Robert...
CVPR
2009
IEEE
15 years 2 months ago
Locally Time-Invariant models of Human Activities using Trajectories on the Grassmanian
Human activity analysis is an important problem in computer vision with applications in surveillance and summarization and indexing of consumer content. Complex human activities...
Pavan Turaga, Rama Chellappa