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
Type  article
Stage   submitted
Date   2016-05-24
Version   v2
Language   en ?
arXiv  1603.04015v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 7f9890a3-a2c3-49ad-84eb-ab87b6c9b81c
API URL: JSON