Application of related data automatic semantic annotation technology in Internet of things

DOI

10.2991/wartia-16.2016.265How to use a DOI?

Keywords

semi-supervised learning, video correlation, video annotation, semantic relevance, linear neighborhood propagation

Abstract

specific to semi-supervised learning method based on graph ignoring the problem of video correlation in research and application of multimedia, a kind of video annotation algorithm based on related kernel mapping linear neighborhood propagation is put forward. Firstly, the propagation coefficient of the iteration annotation is calculated in the algorithm with the kernel function according to the adjusted distance of semi-supervised learning; secondly, the sample of the low-lever feature space is obtained by using the propagation coefficient; thirdly, the correlation table between the semantic concepts is constructed according to video correlation modeling; finally, the structure of the nearest neighborhood graph is constructed; use the labeled video information to carry out iterative propagation to unlabeled video so as to complete video annotation. Experimental results show that: this algorithm can not only improve the accuracy of video annotation but also can make up for the lack of the number of video data labeled.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lianwang Zhao
AU  - Hai Huang
PY  - 2016/05
DA  - 2016/05
TI  - Application of related data automatic semantic annotation technology in Internet of things
BT  - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications
PB  - Atlantis Press
SP  - 1260
EP  - 1264
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-16.2016.265
DO  - 10.2991/wartia-16.2016.265
ID  - Zhao2016/05
ER  -