First-person activity recognition based on three-stream deep features

Ye Ji Kim, Dong Gyu Lee, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we present a novel three-stream deep feature fusion technique to recognize interaction-level human activities from a first-person viewpoint. Specifically, the proposed approach distinguishes human motion and camera ego-motion to focus on human’s movement. The features of human and camera ego-motion information are extracted from the three-stream architecture. These features are fused by considering a relationship of human action and camera ego-motion. To validate the effectiveness of our approach, we perform experiments on UTKinect-FirstPerson dataset, and achieve state-of-the-art performance.

Original languageEnglish
Title of host publicationInternational Conference on Control, Automation and Systems
PublisherIEEE Computer Society
Pages297-299
Number of pages3
Volume2018-October
ISBN (Electronic)9788993215151
Publication statusPublished - 2018 Dec 10
Event18th International Conference on Control, Automation and Systems, ICCAS 2018 - PyeongChang, Korea, Republic of
Duration: 2018 Oct 172018 Oct 20

Other

Other18th International Conference on Control, Automation and Systems, ICCAS 2018
CountryKorea, Republic of
CityPyeongChang
Period18/10/1718/10/20

Fingerprint

Cameras
Fusion reactions
Experiments

Keywords

  • First-person activity recognition
  • Human-robot interaction
  • Robot surveillance.
  • Three-stream deep features

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Kim, Y. J., Lee, D. G., & Lee, S. W. (2018). First-person activity recognition based on three-stream deep features. In International Conference on Control, Automation and Systems (Vol. 2018-October, pp. 297-299). [8571982] IEEE Computer Society.

First-person activity recognition based on three-stream deep features. / Kim, Ye Ji; Lee, Dong Gyu; Lee, Seong Whan.

International Conference on Control, Automation and Systems. Vol. 2018-October IEEE Computer Society, 2018. p. 297-299 8571982.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, YJ, Lee, DG & Lee, SW 2018, First-person activity recognition based on three-stream deep features. in International Conference on Control, Automation and Systems. vol. 2018-October, 8571982, IEEE Computer Society, pp. 297-299, 18th International Conference on Control, Automation and Systems, ICCAS 2018, PyeongChang, Korea, Republic of, 18/10/17.
Kim YJ, Lee DG, Lee SW. First-person activity recognition based on three-stream deep features. In International Conference on Control, Automation and Systems. Vol. 2018-October. IEEE Computer Society. 2018. p. 297-299. 8571982
Kim, Ye Ji ; Lee, Dong Gyu ; Lee, Seong Whan. / First-person activity recognition based on three-stream deep features. International Conference on Control, Automation and Systems. Vol. 2018-October IEEE Computer Society, 2018. pp. 297-299
@inproceedings{ddcda9e93b3d473b99e1e3b86e30b036,
title = "First-person activity recognition based on three-stream deep features",
abstract = "In this paper, we present a novel three-stream deep feature fusion technique to recognize interaction-level human activities from a first-person viewpoint. Specifically, the proposed approach distinguishes human motion and camera ego-motion to focus on human’s movement. The features of human and camera ego-motion information are extracted from the three-stream architecture. These features are fused by considering a relationship of human action and camera ego-motion. To validate the effectiveness of our approach, we perform experiments on UTKinect-FirstPerson dataset, and achieve state-of-the-art performance.",
keywords = "First-person activity recognition, Human-robot interaction, Robot surveillance., Three-stream deep features",
author = "Kim, {Ye Ji} and Lee, {Dong Gyu} and Lee, {Seong Whan}",
year = "2018",
month = "12",
day = "10",
language = "English",
volume = "2018-October",
pages = "297--299",
booktitle = "International Conference on Control, Automation and Systems",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - First-person activity recognition based on three-stream deep features

AU - Kim, Ye Ji

AU - Lee, Dong Gyu

AU - Lee, Seong Whan

PY - 2018/12/10

Y1 - 2018/12/10

N2 - In this paper, we present a novel three-stream deep feature fusion technique to recognize interaction-level human activities from a first-person viewpoint. Specifically, the proposed approach distinguishes human motion and camera ego-motion to focus on human’s movement. The features of human and camera ego-motion information are extracted from the three-stream architecture. These features are fused by considering a relationship of human action and camera ego-motion. To validate the effectiveness of our approach, we perform experiments on UTKinect-FirstPerson dataset, and achieve state-of-the-art performance.

AB - In this paper, we present a novel three-stream deep feature fusion technique to recognize interaction-level human activities from a first-person viewpoint. Specifically, the proposed approach distinguishes human motion and camera ego-motion to focus on human’s movement. The features of human and camera ego-motion information are extracted from the three-stream architecture. These features are fused by considering a relationship of human action and camera ego-motion. To validate the effectiveness of our approach, we perform experiments on UTKinect-FirstPerson dataset, and achieve state-of-the-art performance.

KW - First-person activity recognition

KW - Human-robot interaction

KW - Robot surveillance.

KW - Three-stream deep features

UR - http://www.scopus.com/inward/record.url?scp=85060468167&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060468167&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85060468167

VL - 2018-October

SP - 297

EP - 299

BT - International Conference on Control, Automation and Systems

PB - IEEE Computer Society

ER -