152 search results - page 8 / 31 » Recognizing Human Actions: A Local SVM Approach |
ICPR
2010
IEEE
14 years 1 months ago
2010
IEEE
Existing action recognition approaches mainly rely on the discriminative power of individual local descriptors extracted from spatio-temporal interest points (STIP), while the geo...
ICPR
2010
IEEE
14 years 26 days ago
2010
IEEE
—In this paper we evaluate the use of Restricted Bolzmann Machines (RBM) in the context of learning and recognizing human actions. The features used as basis are binary silhouett...
CVPR
2009
IEEE
15 years 2 months ago
2009
IEEE
We present a new method for classification with structured
latent variables. Our model is formulated using the
max-margin formalism in the discriminative learning literature.
We...
CVPR
2008
IEEE
14 years 9 months ago
2008
IEEE
In this paper we introduce a template-based method for recognizing human actions called Action MACH. Our approach is based on a Maximum Average Correlation Height (MACH) filter. A...
NIPS
2008
13 years 9 months ago
2008
We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditi...