Sciweavers

92 search results - page 9 / 19
» Active Learning for Large Multi-class Problems
Sort
View
CVPR
2003
IEEE
14 years 9 months ago
Activity Recognition Using the Dynamics of the Configuration of Interacting Objects
Monitoring activities using video data is an important surveillance problem. A special scenario is to learn the pattern of normal activities and detect abnormal events from a very...
Namrata Vaswani, Amit K. Roy Chowdhury, Rama Chell...
ECTEL
2007
Springer
14 years 1 months ago
Mobile Social Software with Context Awareness and Data Uncertainty for Technology-Enhanced Learning
Mobile computing technologies and social software have given new challenges to technology-enhanced learning. Simple e-learning system personalization, adaptation and authoring beco...
Yiwei Cao
CVPR
2010
IEEE
14 years 3 months ago
Learning Shift-Invariant Sparse Representation of Actions
A central problem in the analysis of motion capture (Mo- Cap) data is how to decompose motion sequences into primitives. Ideally, a description in terms of primitives should fac...
Yi Li
DPC
1996
192views more  DPC 1996»
13 years 8 months ago
Finding Pictures of Objects in Large Collections of Images
Retrieving images from very large collections, using image content as a key, is becoming an important problem. Users prefer to ask for pictures using notions of content that are st...
David A. Forsyth, Jitendra Malik, Thomas K. Leung,...
PAMI
2006
206views more  PAMI 2006»
13 years 7 months ago
MILES: Multiple-Instance Learning via Embedded Instance Selection
Multiple-instance problems arise from the situations where training class labels are attached to sets of samples (named bags), instead of individual samples within each bag (called...
Yixin Chen, Jinbo Bi, James Ze Wang