5 search results - page 1 / 1 » Fast realistic multi-action recognition using mined dense sp... |
ICCV
2009
IEEE
13 years 2 months ago
2009
IEEE
Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
In this paper, we present a systematic framework for re-cognizing realistic actions from videos “in the wild.” Such unconstrained videos are abundant in personal collections as...
CVPR
2009
IEEE
13 years 11 months ago
2009
IEEE
In this paper, we present a systematic framework for recognizing realistic actions from videos “in the wild.” Such unconstrained videos are abundant in personal collections as...
CVPR
2011
IEEE
13 years 8 hour ago
2011
IEEE
Feature trajectories have shown to be efficient for representing videos. Typically, they are extracted using the KLT tracker or matching SIFT descriptors between frames. However,...
KDD
2010
ACM
13 years 8 months ago
2010
ACM
Feature selection is an important task in order to achieve better generalizability in high dimensional learning, and structure learning of Markov random fields (MRFs) can automat...