Improving Human Action Recognition by Non-action Classification

Yang Wang; Minh Hoai

doi:10.1109/CVPR.2016.295

Improving Human Action Recognition by Non-action Classification

Yang Wang
, Minh Hoai

Computer Science

Stony Brook University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

16 Scopus citations

Abstract

In this paper we consider the task of recognizing human actions in realistic video where human actions are dominated by irrelevant factors. We first study the benefits of removing non-action video segments, which are the ones that do not portray any human action. We then learn a nonaction classifier and use it to down-weight irrelevant video segments. The non-action classifier is trained using Action-Thread, a dataset with shot-level annotation for the occurrence or absence of a human action. The non-action classifier can be used to identify non-action shots with high precision and subsequently used to improve the performance of action recognition systems.

Original language	English
Title of host publication	Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Publisher	IEEE Computer Society
Pages	2698-2707
Number of pages	10
ISBN (Electronic)	9781467388504
DOIs	https://doi.org/10.1109/CVPR.2016.295
State	Published - Dec 9 2016
Event	29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States Duration: Jun 26 2016 → Jul 1 2016

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2016-December
ISSN (Print)	1063-6919

Conference

Conference	29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Country/Territory	United States
City	Las Vegas
Period	06/26/16 → 07/1/16

Access to Document

10.1109/CVPR.2016.295

Cite this

Wang, Y., & Hoai, M. (2016). Improving Human Action Recognition by Non-action Classification. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (pp. 2698-2707). Article 7780664 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December). IEEE Computer Society. https://doi.org/10.1109/CVPR.2016.295

@inproceedings{da90606cf5214354a8022551f9e90c9c,

title = "Improving Human Action Recognition by Non-action Classification",

abstract = "In this paper we consider the task of recognizing human actions in realistic video where human actions are dominated by irrelevant factors. We first study the benefits of removing non-action video segments, which are the ones that do not portray any human action. We then learn a nonaction classifier and use it to down-weight irrelevant video segments. The non-action classifier is trained using Action-Thread, a dataset with shot-level annotation for the occurrence or absence of a human action. The non-action classifier can be used to identify non-action shots with high precision and subsequently used to improve the performance of action recognition systems.",

author = "Yang Wang and Minh Hoai",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 ; Conference date: 26-06-2016 Through 01-07-2016",

year = "2016",

month = dec,

day = "9",

doi = "10.1109/CVPR.2016.295",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "2698--2707",

booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",

}

Wang, Y & Hoai, M 2016, Improving Human Action Recognition by Non-action Classification. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016., 7780664, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, IEEE Computer Society, pp. 2698-2707, 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 06/26/16. https://doi.org/10.1109/CVPR.2016.295

Improving Human Action Recognition by Non-action Classification. / Wang, Yang; Hoai, Minh.
Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 2698-2707 7780664 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Improving Human Action Recognition by Non-action Classification

AU - Wang, Yang

AU - Hoai, Minh

PY - 2016/12/9

Y1 - 2016/12/9

N2 - In this paper we consider the task of recognizing human actions in realistic video where human actions are dominated by irrelevant factors. We first study the benefits of removing non-action video segments, which are the ones that do not portray any human action. We then learn a nonaction classifier and use it to down-weight irrelevant video segments. The non-action classifier is trained using Action-Thread, a dataset with shot-level annotation for the occurrence or absence of a human action. The non-action classifier can be used to identify non-action shots with high precision and subsequently used to improve the performance of action recognition systems.

AB - In this paper we consider the task of recognizing human actions in realistic video where human actions are dominated by irrelevant factors. We first study the benefits of removing non-action video segments, which are the ones that do not portray any human action. We then learn a nonaction classifier and use it to down-weight irrelevant video segments. The non-action classifier is trained using Action-Thread, a dataset with shot-level annotation for the occurrence or absence of a human action. The non-action classifier can be used to identify non-action shots with high precision and subsequently used to improve the performance of action recognition systems.

UR - https://www.scopus.com/pages/publications/84986308438

U2 - 10.1109/CVPR.2016.295

DO - 10.1109/CVPR.2016.295

M3 - Conference contribution

AN - SCOPUS:84986308438

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 2698

EP - 2707

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

Y2 - 26 June 2016 through 1 July 2016

ER -

Improving Human Action Recognition by Non-action Classification

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this