Blind Natural Video Quality Prediction via Statistical Temporal Features and Deep Spatial Features

Jari Korhonen; Yicheng Su; Junyong You

doi:10.1145/3394171.3413845

Blind Natural Video Quality Prediction via Statistical Temporal Features and Deep Spatial Features

Jari Korhonen, Yicheng Su, Junyong You

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

71 Citations (Scopus)

Abstract

Due to the wide range of different natural temporal and spatial distortions appearing in user generated video content, blind assessment of natural video quality is a challenging research problem. In this study, we combine the hand-crafted statistical temporal features used in a state-of-the-art video quality model and spatial features obtained from convolutional neural network trained for image quality assessment via transfer learning. Experimental results on two recently published natural video quality databases show that the proposed model can predict subjective video quality more accurately than the publicly available video quality models representing the state-of-the-art. The proposed model is also competitive in terms of computational complexity.

Original language	English
Title of host publication	MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia
Publisher	Association for Computing Machinery, Inc
Pages	3311-3319
Number of pages	9
ISBN (Electronic)	9781450379885
DOIs	https://doi.org/10.1145/3394171.3413845
Publication status	Published - 12 Oct 2020
Event	28th ACM International Conference on Multimedia, MM 2020 - Virtual, Online, United States Duration: 12 Oct 2020 → 16 Oct 2020

Conference

Conference	28th ACM International Conference on Multimedia, MM 2020
Country/Territory	United States
City	Virtual, Online
Period	12/10/20 → 16/10/20

Bibliographical note

Funding Information:
This work was supported in part by Natural Science Foundation of China under grant 61772348.

Publisher Copyright:
© 2020 ACM.

Keywords

convolutional neural network
human visual system
machine learning
video quality assessment

Access to Document

10.1145/3394171.3413845

Cite this

Blind Natural Video Quality Prediction via Statistical Temporal Features and Deep Spatial Features. / Korhonen, Jari; Su, Yicheng; You, Junyong.
MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia. Association for Computing Machinery, Inc, 2020. p. 3311-3319.

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

Korhonen, J, Su, Y & You, J 2020, Blind Natural Video Quality Prediction via Statistical Temporal Features and Deep Spatial Features. in MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia. Association for Computing Machinery, Inc, pp. 3311-3319, 28th ACM International Conference on Multimedia, MM 2020, Virtual, Online, United States, 12/10/20. https://doi.org/10.1145/3394171.3413845

@inproceedings{93edaaf60fc1483394ec18b8ab6f06c4,

title = "Blind Natural Video Quality Prediction via Statistical Temporal Features and Deep Spatial Features",

abstract = "Due to the wide range of different natural temporal and spatial distortions appearing in user generated video content, blind assessment of natural video quality is a challenging research problem. In this study, we combine the hand-crafted statistical temporal features used in a state-of-the-art video quality model and spatial features obtained from convolutional neural network trained for image quality assessment via transfer learning. Experimental results on two recently published natural video quality databases show that the proposed model can predict subjective video quality more accurately than the publicly available video quality models representing the state-of-the-art. The proposed model is also competitive in terms of computational complexity.",

keywords = "convolutional neural network, human visual system, machine learning, video quality assessment",

author = "Jari Korhonen and Yicheng Su and Junyong You",

note = "Funding Information: This work was supported in part by Natural Science Foundation of China under grant 61772348. Publisher Copyright: {\textcopyright} 2020 ACM.; 28th ACM International Conference on Multimedia, MM 2020 ; Conference date: 12-10-2020 Through 16-10-2020",

year = "2020",

month = oct,

day = "12",

doi = "10.1145/3394171.3413845",

language = "English",

pages = "3311--3319",

booktitle = "MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia",

publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Blind Natural Video Quality Prediction via Statistical Temporal Features and Deep Spatial Features

AU - Korhonen, Jari

AU - Su, Yicheng

AU - You, Junyong

PY - 2020/10/12

Y1 - 2020/10/12

N2 - Due to the wide range of different natural temporal and spatial distortions appearing in user generated video content, blind assessment of natural video quality is a challenging research problem. In this study, we combine the hand-crafted statistical temporal features used in a state-of-the-art video quality model and spatial features obtained from convolutional neural network trained for image quality assessment via transfer learning. Experimental results on two recently published natural video quality databases show that the proposed model can predict subjective video quality more accurately than the publicly available video quality models representing the state-of-the-art. The proposed model is also competitive in terms of computational complexity.

AB - Due to the wide range of different natural temporal and spatial distortions appearing in user generated video content, blind assessment of natural video quality is a challenging research problem. In this study, we combine the hand-crafted statistical temporal features used in a state-of-the-art video quality model and spatial features obtained from convolutional neural network trained for image quality assessment via transfer learning. Experimental results on two recently published natural video quality databases show that the proposed model can predict subjective video quality more accurately than the publicly available video quality models representing the state-of-the-art. The proposed model is also competitive in terms of computational complexity.

KW - convolutional neural network

KW - human visual system

KW - machine learning

KW - video quality assessment

UR - http://www.scopus.com/inward/record.url?scp=85106684280&partnerID=8YFLogxK

U2 - 10.1145/3394171.3413845

DO - 10.1145/3394171.3413845

M3 - Published conference contribution

AN - SCOPUS:85106684280

SP - 3311

EP - 3319

BT - MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia

PB - Association for Computing Machinery, Inc

T2 - 28th ACM International Conference on Multimedia, MM 2020

Y2 - 12 October 2020 through 16 October 2020

ER -

Blind Natural Video Quality Prediction via Statistical Temporal Features and Deep Spatial Features

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this