2 search results - page 1 / 1 » View-invariant action recognition using cross ratios across ... |
81
Voted
ICIP
2009
IEEE
14 years 7 months ago
2009
IEEE
We present a new method of computing invariants in videos captured from different views to achieve view-invariant action recognition. To avoid the constraints of collinearity or c...
CVPR
2010
IEEE
15 years 3 months ago
2010
IEEE
Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amount...