BibTeX
CSL-JSON
MLA
Harvard
Learning zeroth class dictionary for human action recognition
release_plbeyfhgjrdmhiowvokgafw6du
by
Jia-xin Cai, Xin Tang, Lifang Zhang, Guocan Feng
Released
as a article
.
2016
Abstract
In this paper, a discriminative two-phase dictionary learning framework is
proposed for classifying human action by sparse shape representations, in which
the first-phase dictionary is learned on the selected discriminative frames and
the second-phase dictionary is built for recognition using reconstruction
errors of the first-phase dictionary as input features. We propose a "zeroth
class" trick for detecting undiscriminating frames of the test video and
eliminating them before voting on the action categories. Experimental results
on benchmarks demonstrate the effectiveness of our method.
In text/plain
format
Archived Files and Locations
application/pdf 125.5 kB
file_7g3glb4eofcd7ldvzfdhubewgq
|
arxiv.org (repository) web.archive.org (webarchive) |
Read Archived PDF
Preserved and Accessible
arXiv
1603.04015v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
access all versions, variants, and formats of this works (eg, pre-prints)
Cite This
Lookup Links