Sciweavers

274 search results - page 38 / 55
» Activity Recognition from Sparsely Labeled Data Using Multi-...
Sort
View
PERVASIVE
2006
Springer
13 years 7 months ago
Building Reliable Activity Models Using Hierarchical Shrinkage and Mined Ontology
Abstract. Activity inference based on object use has received considerable recent attention. Such inference requires statistical models that map activities to the objects used in p...
Emmanuel Munguia Tapia, Tanzeem Choudhury, Matthai...
CVPR
2008
IEEE
14 years 9 months ago
Action snippets: How many frames does human action recognition require?
Visual recognition of human actions in video clips has been an active field of research in recent years. However, most published methods either analyse an entire video and assign ...
Konrad Schindler, Luc J. Van Gool
AMDO
2010
Springer
13 years 5 months ago
Multiple-Activity Human Body Tracking in Unconstrained Environments
We propose a method for human full-body pose tracking from measurements of wearable inertial sensors. Since the data provided by such sensors is sparse, noisy and often ambiguous, ...
Loren Arthur Schwarz, Diana Mateus, Nassir Navab
ICCV
2009
IEEE
1019views Computer Vision» more  ICCV 2009»
15 years 11 days ago
Similarity Functions for Categorization: from Monolithic to Category Specific
Similarity metrics that are learned from labeled training data can be advantageous in terms of performance and/or efficiency. These learned metrics can then be used in conjuncti...
Boris Babenko, Steve Branson, Serge Belongie
CVPR
2006
IEEE
14 years 9 months ago
Graph Laplacian Kernels for Object Classification from a Single Example
Classification with only one labeled example per class is a challenging problem in machine learning and pattern recognition. While there have been some attempts to address this pr...
Hong Chang, Dit-Yan Yeung