loading
Documents

Research.Publish.Connect.

Paper

Authors: Mohammad Al-Naser 1 ; Hiroki Ohashi 2 ; Sheraz Ahmed 3 ; Katsuyuki Nakamura 4 ; Takayuki Akiyama 4 ; Takuto Sato 4 ; Phong Nguyen 4 and Andreas Dengel 5

Affiliations: 1 German Research Center for Artificial Intelligence(DFKI) and University of Kaiserslautern, Germany ; 2 Hitachi Europe GmbH, Germany ; 3 German Research Center for Artificial Intelligence(DFKI), Germany ; 4 Hitachi Ltd, Japan ; 5 German Research Center for Artificial Intelligence (DFKI) and University of Kaiserslautern, Germany

ISBN: 978-989-758-275-2

Keyword(s): Zero-shot Learning, Activity Recognition, And Hierarchical Model.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Industrial Applications of AI ; Soft Computing ; Vision and Perception

Abstract: We present a hierarchical framework for zero-shot human-activity recognition that recognizes unseen activities by the combinations of preliminarily learned basic actions and involved objects. The presented framework consists of gaze-guided object recognition module, myo-armband based action recognition module, and the activity recognition module, which combines results from both action and object module to detect complex activities. Both object and action recognition modules are based on deep neural network. Unlike conventional models, the proposed framework does not need retraining for recognition of an unseen activity, if the activity can be represented by a combination of the predefined basic actions and objects. This framework brings competitive advantage to industry in terms of the service-deployment cost. The experimental results showed that the proposed model could recognize three types of activities with precision of 77% and recall rate of 82%, which is comparable to a baselin e method based on supervised learning. (More)

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.163.22.209

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Al-Naser M., Ohashi H., Ahmed S., Nakamura K., Akiyama T., Sato T., Nguyen P. and Dengel A. (2018). Hierarchical Model for Zero-shot Activity Recognition using Wearable Sensors.In Proceedings of the 10th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-275-2, pages 478-485. DOI: 10.5220/0006595204780485

@conference{icaart18,
author={Mohammad Al-Naser and Hiroki Ohashi and Sheraz Ahmed and Katsuyuki Nakamura and Takayuki Akiyama and Takuto Sato and Phong Nguyen and Andreas Dengel},
title={Hierarchical Model for Zero-shot Activity Recognition using Wearable Sensors},
booktitle={Proceedings of the 10th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2018},
pages={478-485},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006595204780485},
isbn={978-989-758-275-2},
}

TY - CONF

JO - Proceedings of the 10th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Hierarchical Model for Zero-shot Activity Recognition using Wearable Sensors
SN - 978-989-758-275-2
AU - Al-Naser M.
AU - Ohashi H.
AU - Ahmed S.
AU - Nakamura K.
AU - Akiyama T.
AU - Sato T.
AU - Nguyen P.
AU - Dengel A.
PY - 2018
SP - 478
EP - 485
DO - 10.5220/0006595204780485

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.