RSVP: A real-time surveillance video parsing system with single frame supervision

Han Yu; Guanghui Ren; Ruihe Qian; Yao Sun; Changhu Wang; Hanqing Lu; Si Liu

doi:10.1145/3123266.3127928

RSVP: A real-time surveillance video parsing system with single frame supervision

Han Yu
, Guanghui Ren
, Ruihe Qian
, Yao Sun
, Changhu Wang
, Hanqing Lu
, Si Liu^*

^*Corresponding author for this work

CAS - Institute of Information Engineering
Toutiao AI Lab.
Chinese Academy of Sciences

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

4 Scopus citations

Abstract

In this demo, we present a real-time surveillance video parsing (RSVP) system to parse surveillance videos. Surveillance video parsing, which aims to segment the video frames into several labels, e.g., face, pants, left-legs, has wide applications, especially in security filed. However, it is very tedious and time-consuming to annotate all the frames in a video. We design a RSVP system to parse the surveillance videos in real-time. The RSVP system requires only one labeled frame in training stage. The RSVP system jointly considers the segmentation of preceding frames when parsing one particular frame within the video. The RSVP system is proved to be effective and efficient in real applications.

Original language	English
Title of host publication	MM 2017 - Proceedings of the 2017 ACM Multimedia Conference
Publisher	Association for Computing Machinery, Inc
Pages	1257-1258
Number of pages	2
ISBN (Electronic)	9781450349062
DOIs	https://doi.org/10.1145/3123266.3127928
State	Published - 23 Oct 2017
Externally published	Yes
Event	25th ACM International Conference on Multimedia, MM 2017 - Mountain View, United States Duration: 23 Oct 2017 → 27 Oct 2017

Publication series

Name	MM 2017 - Proceedings of the 2017 ACM Multimedia Conference

Conference

Conference	25th ACM International Conference on Multimedia, MM 2017
Country/Territory	United States
City	Mountain View
Period	23/10/17 → 27/10/17

Keywords

Deep learning
Human parsing
Surveillance video parsing system

Access to Document

10.1145/3123266.3127928

Cite this

Yu, H., Ren, G., Qian, R., Sun, Y., Wang, C., Lu, H., & Liu, S. (2017). RSVP: A real-time surveillance video parsing system with single frame supervision. In MM 2017 - Proceedings of the 2017 ACM Multimedia Conference (pp. 1257-1258). (MM 2017 - Proceedings of the 2017 ACM Multimedia Conference). Association for Computing Machinery, Inc. https://doi.org/10.1145/3123266.3127928

@inproceedings{1eaeb86987ba46ebaf543acf0c78ddf7,

title = "RSVP: A real-time surveillance video parsing system with single frame supervision",

abstract = "In this demo, we present a real-time surveillance video parsing (RSVP) system to parse surveillance videos. Surveillance video parsing, which aims to segment the video frames into several labels, e.g., face, pants, left-legs, has wide applications, especially in security filed. However, it is very tedious and time-consuming to annotate all the frames in a video. We design a RSVP system to parse the surveillance videos in real-time. The RSVP system requires only one labeled frame in training stage. The RSVP system jointly considers the segmentation of preceding frames when parsing one particular frame within the video. The RSVP system is proved to be effective and efficient in real applications.",

keywords = "Deep learning, Human parsing, Surveillance video parsing system",

author = "Han Yu and Guanghui Ren and Ruihe Qian and Yao Sun and Changhu Wang and Hanqing Lu and Si Liu",

note = "Publisher Copyright: {\textcopyright} 2017 Copyright held by the owner/author(s).; 25th ACM International Conference on Multimedia, MM 2017 ; Conference date: 23-10-2017 Through 27-10-2017",

year = "2017",

month = oct,

day = "23",

doi = "10.1145/3123266.3127928",

language = "英语",

series = "MM 2017 - Proceedings of the 2017 ACM Multimedia Conference",

publisher = "Association for Computing Machinery, Inc",

pages = "1257--1258",

booktitle = "MM 2017 - Proceedings of the 2017 ACM Multimedia Conference",

}

Yu, H, Ren, G, Qian, R, Sun, Y, Wang, C, Lu, H & Liu, S 2017, RSVP: A real-time surveillance video parsing system with single frame supervision. in MM 2017 - Proceedings of the 2017 ACM Multimedia Conference. MM 2017 - Proceedings of the 2017 ACM Multimedia Conference, Association for Computing Machinery, Inc, pp. 1257-1258, 25th ACM International Conference on Multimedia, MM 2017, Mountain View, United States, 23/10/17. https://doi.org/10.1145/3123266.3127928

RSVP: A real-time surveillance video parsing system with single frame supervision. / Yu, Han; Ren, Guanghui; Qian, Ruihe et al.
MM 2017 - Proceedings of the 2017 ACM Multimedia Conference. Association for Computing Machinery, Inc, 2017. p. 1257-1258 (MM 2017 - Proceedings of the 2017 ACM Multimedia Conference).

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

TY - GEN

T1 - RSVP

T2 - 25th ACM International Conference on Multimedia, MM 2017

AU - Yu, Han

AU - Ren, Guanghui

AU - Qian, Ruihe

AU - Sun, Yao

AU - Wang, Changhu

AU - Lu, Hanqing

AU - Liu, Si

PY - 2017/10/23

Y1 - 2017/10/23

N2 - In this demo, we present a real-time surveillance video parsing (RSVP) system to parse surveillance videos. Surveillance video parsing, which aims to segment the video frames into several labels, e.g., face, pants, left-legs, has wide applications, especially in security filed. However, it is very tedious and time-consuming to annotate all the frames in a video. We design a RSVP system to parse the surveillance videos in real-time. The RSVP system requires only one labeled frame in training stage. The RSVP system jointly considers the segmentation of preceding frames when parsing one particular frame within the video. The RSVP system is proved to be effective and efficient in real applications.

AB - In this demo, we present a real-time surveillance video parsing (RSVP) system to parse surveillance videos. Surveillance video parsing, which aims to segment the video frames into several labels, e.g., face, pants, left-legs, has wide applications, especially in security filed. However, it is very tedious and time-consuming to annotate all the frames in a video. We design a RSVP system to parse the surveillance videos in real-time. The RSVP system requires only one labeled frame in training stage. The RSVP system jointly considers the segmentation of preceding frames when parsing one particular frame within the video. The RSVP system is proved to be effective and efficient in real applications.

KW - Deep learning

KW - Human parsing

KW - Surveillance video parsing system

UR - https://www.scopus.com/pages/publications/85035240273

U2 - 10.1145/3123266.3127928

DO - 10.1145/3123266.3127928

M3 - 会议稿件

AN - SCOPUS:85035240273

T3 - MM 2017 - Proceedings of the 2017 ACM Multimedia Conference

SP - 1257

EP - 1258

BT - MM 2017 - Proceedings of the 2017 ACM Multimedia Conference

PB - Association for Computing Machinery, Inc

Y2 - 23 October 2017 through 27 October 2017

ER -

RSVP: A real-time surveillance video parsing system with single frame supervision

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this