Practical Video Quality Assessment of User Generated Content

Jari Korhonen; Xuanzheng Wen; Jun Cheng; Xu Wang

doi:10.1109/ICMEW53276.2021.9455974

Practical Video Quality Assessment of User Generated Content

Jari Korhonen, Xuanzheng Wen, Jun Cheng, Xu Wang^*

^*Corresponding author for this work

Shenzhen University

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Abstract

During the past few years, video quality assessment (VQA) of user generated content (UGC) has attracted considerable attention in the research community. In this paper, we propose a practical architecture for a versatile video quality model, designed for assessing user generated videos in particular. The proposed architecture is based on our earlier design of two-level video quality model with a convolutional neural network (CNN-TLVQM), with various improvements and re-designed elements. We have built a fast implementation of the proposed model in C++, demonstrating that the model is practical for real-life applications. The implementation of the model has been submitted for evaluation in ICME UGCVQA Challenge in 2021.

Original language	English
Title of host publication	2021 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	6
ISBN (Electronic)	9781665449892
DOIs	https://doi.org/10.1109/ICMEW53276.2021.9455974
Publication status	Published - 2021
Event	2021 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2021 - Shenzhen, China Duration: 5 Jul 2021 → 9 Jul 2021

Publication series

Name	IEEE International Conference on Multimedia and Expo Workshops
Publisher	IEEE
ISSN (Print)	2330-7927

Conference

Conference	2021 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2021
Country/Territory	China
City	Shenzhen
Period	5/07/21 → 9/07/21

Bibliographical note

Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grants 61772348 and 61871270, Guangdong ”Pearl River Talent Recruitment Program” under Grant 2019ZT08X603, and Shenzhen Fundamental Research Program under Grant JCYJ20200109110410133.

Publisher Copyright:
© 2021 IEEE.

Keywords

Convolutional neural network
Recurrent neural network
User generated content
Video quality assessment

Access to Document

10.1109/ICMEW53276.2021.9455974

Cite this

Practical Video Quality Assessment of User Generated Content. / Korhonen, Jari; Wen, Xuanzheng; Cheng, Jun et al.
2021 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW). Institute of Electrical and Electronics Engineers Inc., 2021. (IEEE International Conference on Multimedia and Expo Workshops).

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Korhonen, J, Wen, X, Cheng, J & Wang, X 2021, Practical Video Quality Assessment of User Generated Content. in 2021 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW). IEEE International Conference on Multimedia and Expo Workshops, Institute of Electrical and Electronics Engineers Inc., 2021 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2021, Shenzhen, China, 5/07/21. https://doi.org/10.1109/ICMEW53276.2021.9455974

@inproceedings{2e45cbc10376437690c0d999e30cc473,

title = "Practical Video Quality Assessment of User Generated Content",

abstract = "During the past few years, video quality assessment (VQA) of user generated content (UGC) has attracted considerable attention in the research community. In this paper, we propose a practical architecture for a versatile video quality model, designed for assessing user generated videos in particular. The proposed architecture is based on our earlier design of two-level video quality model with a convolutional neural network (CNN-TLVQM), with various improvements and re-designed elements. We have built a fast implementation of the proposed model in C++, demonstrating that the model is practical for real-life applications. The implementation of the model has been submitted for evaluation in ICME UGCVQA Challenge in 2021. ",

keywords = "Convolutional neural network, Recurrent neural network, User generated content, Video quality assessment",

author = "Jari Korhonen and Xuanzheng Wen and Jun Cheng and Xu Wang",

note = "Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grants 61772348 and 61871270, Guangdong ”Pearl River Talent Recruitment Program” under Grant 2019ZT08X603, and Shenzhen Fundamental Research Program under Grant JCYJ20200109110410133. Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2021 ; Conference date: 05-07-2021 Through 09-07-2021",

year = "2021",

doi = "10.1109/ICMEW53276.2021.9455974",

language = "English",

series = "IEEE International Conference on Multimedia and Expo Workshops",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2021 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW)",

address = "United States",

}

TY - GEN

T1 - Practical Video Quality Assessment of User Generated Content

AU - Korhonen, Jari

AU - Wen, Xuanzheng

AU - Cheng, Jun

AU - Wang, Xu

N1 - Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grants 61772348 and 61871270, Guangdong ”Pearl River Talent Recruitment Program” under Grant 2019ZT08X603, and Shenzhen Fundamental Research Program under Grant JCYJ20200109110410133. Publisher Copyright: © 2021 IEEE.

PY - 2021

Y1 - 2021

N2 - During the past few years, video quality assessment (VQA) of user generated content (UGC) has attracted considerable attention in the research community. In this paper, we propose a practical architecture for a versatile video quality model, designed for assessing user generated videos in particular. The proposed architecture is based on our earlier design of two-level video quality model with a convolutional neural network (CNN-TLVQM), with various improvements and re-designed elements. We have built a fast implementation of the proposed model in C++, demonstrating that the model is practical for real-life applications. The implementation of the model has been submitted for evaluation in ICME UGCVQA Challenge in 2021.

AB - During the past few years, video quality assessment (VQA) of user generated content (UGC) has attracted considerable attention in the research community. In this paper, we propose a practical architecture for a versatile video quality model, designed for assessing user generated videos in particular. The proposed architecture is based on our earlier design of two-level video quality model with a convolutional neural network (CNN-TLVQM), with various improvements and re-designed elements. We have built a fast implementation of the proposed model in C++, demonstrating that the model is practical for real-life applications. The implementation of the model has been submitted for evaluation in ICME UGCVQA Challenge in 2021.

KW - Convolutional neural network

KW - Recurrent neural network

KW - User generated content

KW - Video quality assessment

UR - http://www.scopus.com/inward/record.url?scp=85130732327&partnerID=8YFLogxK

U2 - 10.1109/ICMEW53276.2021.9455974

DO - 10.1109/ICMEW53276.2021.9455974

M3 - Published conference contribution

AN - SCOPUS:85130732327

T3 - IEEE International Conference on Multimedia and Expo Workshops

BT - 2021 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2021

Y2 - 5 July 2021 through 9 July 2021

ER -

Practical Video Quality Assessment of User Generated Content

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this