TS-ICNN: Time Sequence-Based Interval Convolutional Neural Networks for Human Action Detection and Recognition

Zhendong ZHUANG  Yang XUE  

IEICE TRANSACTIONS on Information and Systems   Vol.E101-D   No.10   pp.2534-2538
Publication Date: 2018/10/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDL8046
Type of Manuscript: LETTER
Category: Human-computer Interaction
human action detection and recognition,  inertial sensor,  interval proposals,  interval-based classification,  convolutional neural network,  

Full Text: PDF(2.6MB)
>>Buy this Article

The research on inertial sensor based human action detection and recognition (HADR) is a new area in machine learning. We propose a novel time sequence based interval convolutional neutral networks framework for HADR by combining interesting interval proposals generator and interval-based classifier. Experiments demonstrate the good performance of our method.