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 ...
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...
Jingen Liu (University of Central Florida), Jiebo ...
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...
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,...
Heng Wang, Alexander Kläser, Cordelia Schmid, Che...
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...