Human Action Recognition based on Convolutional Neural Networks with a Convolutional Auto-Encoder

DOI

10.2991/iccsae-15.2016.173How to use a DOI?

Keywords

human action recognition; Convolutional Neural Networks; deep learning; pre-training.

Abstract

Human action recognition (HAR) research is hot in computer vision, but high precision recognition of human action in the complex background is still an open question. Most current methods build classifiers based on complex handcrafted features computed from the raw inputs, which are driven by tasks and uncertain. In this paper, type of deep model convolutional neural network (CNN) is proposed for HAR that can act directly on the raw inputs. In addition, an efficient pre-training strategy has been introduced to reduce the high computational cost of kernel training to enable improved real-world applications. The proposed approach has been tested on the KTH database and the achieved results compares favorably against state-of-the-art algorithms using hand-designed features.

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  - Chi Geng
AU  - JianXin Song
PY  - 2016/02
DA  - 2016/02
TI  - Human Action Recognition based on Convolutional Neural Networks with a Convolutional Auto-Encoder
BT  - Proceedings of the 2015 5th International Conference on Computer Sciences and Automation Engineering
PB  - Atlantis Press
SP  - 933
EP  - 938
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccsae-15.2016.173
DO  - 10.2991/iccsae-15.2016.173
ID  - Geng2016/02
ER  -