Content-aware personalised rate adaptation for adaptive streaming via deep video analysis

Adaptive bitrate (ABR) streaming is the de facto solution for achieving smooth viewing experiences under unstable network conditions. However, most of the existing rate adaptation approaches for ABR are content-agnostic, without considering the semantic information of the video content. Nevertheless...

Full description

Saved in:
Bibliographic Details
Main Authors: Gao, Guanyu, Dong, Linsen, Zhang, Huaizheng, Wen, Yonggang, Zeng, Wenjun
Other Authors: School of Computer Science and Engineering
Format: Conference or Workshop Item
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/152992
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-152992
record_format dspace
spelling sg-ntu-dr.10356-1529922021-10-27T08:16:06Z Content-aware personalised rate adaptation for adaptive streaming via deep video analysis Gao, Guanyu Dong, Linsen Zhang, Huaizheng Wen, Yonggang Zeng, Wenjun School of Computer Science and Engineering ICC 2019 - 2019 IEEE International Conference on Communications (ICC) Engineering::Computer science and engineering Streaming Media Bit Rate Adaptive bitrate (ABR) streaming is the de facto solution for achieving smooth viewing experiences under unstable network conditions. However, most of the existing rate adaptation approaches for ABR are content-agnostic, without considering the semantic information of the video content. Nevertheless, semantic information largely determines the informativeness and interestingness of the video content, and consequently affects the QoE for video streaming. One common case is that the user may expect higher quality for the parts of video content that are more interesting or informative so as to reduce overall subjective quality loss. This creates two main challenges for such a problem: First, how to determine which parts of the video content are more interesting? Second, how to allocate bitrate budgets for different parts of the video content with different significances? To address these challenges, we propose a Content-of-Interest (CoI) based rate adaptation scheme for ABR. We first design a deep learning approach for recognizing the interestingness of the video content, and then design a Deep Q-Network (DQN) approach for rate adaptation by incorporating video interestingness information. The experimental results show that our method can recognize video interestingness precisely, and the bitrate allocation for ABR can be aligned with the interestingness of video content while not compromising the performances on objective QoE metrics. This project is partially funded by Microsoft Research Asia. 2021-10-27T08:16:06Z 2021-10-27T08:16:06Z 2019 Conference Paper Gao, G., Dong, L., Zhang, H., Wen, Y. & Zeng, W. (2019). Content-aware personalised rate adaptation for adaptive streaming via deep video analysis. ICC 2019 - 2019 IEEE International Conference on Communications (ICC). https://dx.doi.org/10.1109/ICC.2019.8761156 9781538680889 https://hdl.handle.net/10356/152992 10.1109/ICC.2019.8761156 2-s2.0-85070191067 en © 2019 IEEE. All righs reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Streaming Media
Bit Rate
spellingShingle Engineering::Computer science and engineering
Streaming Media
Bit Rate
Gao, Guanyu
Dong, Linsen
Zhang, Huaizheng
Wen, Yonggang
Zeng, Wenjun
Content-aware personalised rate adaptation for adaptive streaming via deep video analysis
description Adaptive bitrate (ABR) streaming is the de facto solution for achieving smooth viewing experiences under unstable network conditions. However, most of the existing rate adaptation approaches for ABR are content-agnostic, without considering the semantic information of the video content. Nevertheless, semantic information largely determines the informativeness and interestingness of the video content, and consequently affects the QoE for video streaming. One common case is that the user may expect higher quality for the parts of video content that are more interesting or informative so as to reduce overall subjective quality loss. This creates two main challenges for such a problem: First, how to determine which parts of the video content are more interesting? Second, how to allocate bitrate budgets for different parts of the video content with different significances? To address these challenges, we propose a Content-of-Interest (CoI) based rate adaptation scheme for ABR. We first design a deep learning approach for recognizing the interestingness of the video content, and then design a Deep Q-Network (DQN) approach for rate adaptation by incorporating video interestingness information. The experimental results show that our method can recognize video interestingness precisely, and the bitrate allocation for ABR can be aligned with the interestingness of video content while not compromising the performances on objective QoE metrics.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Gao, Guanyu
Dong, Linsen
Zhang, Huaizheng
Wen, Yonggang
Zeng, Wenjun
format Conference or Workshop Item
author Gao, Guanyu
Dong, Linsen
Zhang, Huaizheng
Wen, Yonggang
Zeng, Wenjun
author_sort Gao, Guanyu
title Content-aware personalised rate adaptation for adaptive streaming via deep video analysis
title_short Content-aware personalised rate adaptation for adaptive streaming via deep video analysis
title_full Content-aware personalised rate adaptation for adaptive streaming via deep video analysis
title_fullStr Content-aware personalised rate adaptation for adaptive streaming via deep video analysis
title_full_unstemmed Content-aware personalised rate adaptation for adaptive streaming via deep video analysis
title_sort content-aware personalised rate adaptation for adaptive streaming via deep video analysis
publishDate 2021
url https://hdl.handle.net/10356/152992
_version_ 1715201524272988160