Argus: Efficient Activity Detection System for Extended Video Analysis

Wenhe Liu; Guoliang Kang; Po Yao Huang; Xiaojun Chang; Lijun Yu; Yijun Qian; Junwei Liang; Liangke Gui; Jing Wen; Peng Chen; Alexander G. Hauptmann

doi:10.1109/WACVW50321.2020.9096929

Argus: Efficient Activity Detection System for Extended Video Analysis

Wenhe Liu, Guoliang Kang, Po Yao Huang, Xiaojun Chang, Lijun Yu, Yijun Qian, Junwei Liang, Liangke Gui, Jing Wen, Peng Chen, Alexander G. Hauptmann

Department of Data Science & AI

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

35 Citations (Scopus)

Abstract

We propose an Efficient Activity Detection System, Argus, for Extended Video Analysis in the surveillance scenario. For the spatial-temporal event detection in the surveillance video, we first generate video proposals by applying object detection and tracking algorithm which shared the detection features. After that, we extract several different features and apply sequential activity classification with them. Finally, we eliminate inaccurate events and fuse all the predictions from different features. The proposed system wins Trecvid Activities in Extended Video (ActEV¹) challenge 2019. It achieves the first place with 60.5 mean weighted P_miss, outperforming the second place system by 14.5 and the baseline R-C3D by 29.0. In TRECVID 2019 Challenge², the proposed system wins the first place with [email protected] 0.48407.

Original language	English
Title of host publication	Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)
Editors	Gang Hua, Ming-Yu Liu, Vishal Patel, Walter Scheirer, Ryan Farrell
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	126-133
Number of pages	8
ISBN (Electronic)	9781728171623
ISBN (Print)	9781728171630
DOIs	https://doi.org/10.1109/WACVW50321.2020.9096929
Publication status	Published - 2020
Event	IEEE Winter Conference on Applications of Computer Vision Workshops 2020 - Snowmass Village, United States of America Duration: 1 Mar 2020 → 5 Mar 2020

Conference

Conference	IEEE Winter Conference on Applications of Computer Vision Workshops 2020
Abbreviated title	WACVW 2020
Country/Territory	United States of America
City	Snowmass Village
Period	1/03/20 → 5/03/20

Access to Document

10.1109/WACVW50321.2020.9096929

Cite this

Liu, W., Kang, G., Huang, P. Y., Chang, X., Yu, L., Qian, Y., Liang, J., Gui, L., Wen, J., Chen, P., & Hauptmann, A. G. (2020). Argus: Efficient Activity Detection System for Extended Video Analysis. In G. Hua, M.-Y. Liu, V. Patel, W. Scheirer, & R. Farrell (Eds.), Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW) (pp. 126-133). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/WACVW50321.2020.9096929

Liu, Wenhe ; Kang, Guoliang ; Huang, Po Yao et al. / Argus : Efficient Activity Detection System for Extended Video Analysis. Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW). editor / Gang Hua ; Ming-Yu Liu ; Vishal Patel ; Walter Scheirer ; Ryan Farrell. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2020. pp. 126-133

@inproceedings{1331fd38eb98407697ee6d47b294cd03,

title = "Argus: Efficient Activity Detection System for Extended Video Analysis",

abstract = "We propose an Efficient Activity Detection System, Argus, for Extended Video Analysis in the surveillance scenario. For the spatial-temporal event detection in the surveillance video, we first generate video proposals by applying object detection and tracking algorithm which shared the detection features. After that, we extract several different features and apply sequential activity classification with them. Finally, we eliminate inaccurate events and fuse all the predictions from different features. The proposed system wins Trecvid Activities in Extended Video (ActEV1) challenge 2019. It achieves the first place with 60.5 mean weighted Pmiss, outperforming the second place system by 14.5 and the baseline R-C3D by 29.0. In TRECVID 2019 Challenge2, the proposed system wins the first place with [email protected] 0.48407.",

author = "Wenhe Liu and Guoliang Kang and Huang, {Po Yao} and Xiaojun Chang and Lijun Yu and Yijun Qian and Junwei Liang and Liangke Gui and Jing Wen and Peng Chen and Hauptmann, {Alexander G.}",

year = "2020",

doi = "10.1109/WACVW50321.2020.9096929",

language = "English",

isbn = "9781728171630",

pages = "126--133",

editor = "Hua, {Gang } and Liu, {Ming-Yu } and Patel, {Vishal } and Scheirer, {Walter } and Farrell, {Ryan }",

booktitle = "Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE Winter Conference on Applications of Computer Vision Workshops 2020, WACVW 2020 ; Conference date: 01-03-2020 Through 05-03-2020",

}

Liu, W, Kang, G, Huang, PY, Chang, X, Yu, L, Qian, Y, Liang, J, Gui, L, Wen, J, Chen, P & Hauptmann, AG 2020, Argus: Efficient Activity Detection System for Extended Video Analysis. in G Hua, M-Y Liu, V Patel, W Scheirer & R Farrell (eds), Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW). IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 126-133, IEEE Winter Conference on Applications of Computer Vision Workshops 2020, Snowmass Village, Colorado, United States of America, 1/03/20. https://doi.org/10.1109/WACVW50321.2020.9096929

Argus: Efficient Activity Detection System for Extended Video Analysis. / Liu, Wenhe; Kang, Guoliang; Huang, Po Yao et al.
Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW). ed. / Gang Hua; Ming-Yu Liu; Vishal Patel; Walter Scheirer; Ryan Farrell. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2020. p. 126-133.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

TY - GEN

T1 - Argus

T2 - IEEE Winter Conference on Applications of Computer Vision Workshops 2020

AU - Liu, Wenhe

AU - Kang, Guoliang

AU - Huang, Po Yao

AU - Chang, Xiaojun

AU - Yu, Lijun

AU - Qian, Yijun

AU - Liang, Junwei

AU - Gui, Liangke

AU - Wen, Jing

AU - Chen, Peng

AU - Hauptmann, Alexander G.

PY - 2020

Y1 - 2020

N2 - We propose an Efficient Activity Detection System, Argus, for Extended Video Analysis in the surveillance scenario. For the spatial-temporal event detection in the surveillance video, we first generate video proposals by applying object detection and tracking algorithm which shared the detection features. After that, we extract several different features and apply sequential activity classification with them. Finally, we eliminate inaccurate events and fuse all the predictions from different features. The proposed system wins Trecvid Activities in Extended Video (ActEV1) challenge 2019. It achieves the first place with 60.5 mean weighted Pmiss, outperforming the second place system by 14.5 and the baseline R-C3D by 29.0. In TRECVID 2019 Challenge2, the proposed system wins the first place with [email protected] 0.48407.

AB - We propose an Efficient Activity Detection System, Argus, for Extended Video Analysis in the surveillance scenario. For the spatial-temporal event detection in the surveillance video, we first generate video proposals by applying object detection and tracking algorithm which shared the detection features. After that, we extract several different features and apply sequential activity classification with them. Finally, we eliminate inaccurate events and fuse all the predictions from different features. The proposed system wins Trecvid Activities in Extended Video (ActEV1) challenge 2019. It achieves the first place with 60.5 mean weighted Pmiss, outperforming the second place system by 14.5 and the baseline R-C3D by 29.0. In TRECVID 2019 Challenge2, the proposed system wins the first place with [email protected] 0.48407.

UR - http://www.scopus.com/inward/record.url?scp=85085931966&partnerID=8YFLogxK

U2 - 10.1109/WACVW50321.2020.9096929

DO - 10.1109/WACVW50321.2020.9096929

M3 - Conference Paper

AN - SCOPUS:85085931966

SN - 9781728171630

SP - 126

EP - 133

BT - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)

A2 - Hua, Gang

A2 - Liu, Ming-Yu

A2 - Patel, Vishal

A2 - Scheirer, Walter

A2 - Farrell, Ryan

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

Y2 - 1 March 2020 through 5 March 2020

ER -

Liu W, Kang G, Huang PY, Chang X, Yu L, Qian Y et al. Argus: Efficient Activity Detection System for Extended Video Analysis. In Hua G, Liu MY, Patel V, Scheirer W, Farrell R, editors, Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2020. p. 126-133 doi: 10.1109/WACVW50321.2020.9096929

Argus: Efficient Activity Detection System for Extended Video Analysis

Abstract

Conference

Access to Document

Other files and links

Cite this