中文版 | English
题名

BiSR: Bidirectionally Optimized Super-Resolution for Mobile Video Streaming

作者
通讯作者Li,Qing
DOI
发表日期
2023-04-30
会议录名称
页码
3121-3131
摘要
The user experience of mobile web video streaming is often impacted by insufficient and dynamic network bandwidth. In this paper, we design Bidirectionally Optimized Super-Resolution (BiSR) to improve the quality of experience (QoE) for mobile web users under limited bandwidth. BiSR exploits a deep neural network (DNN)-based model to super-resolve key frames efficiently without changing the inter-frame spatial-temporal information. We then propose a downscaling DNN and a mobile-specific optimized lightweight super-resolution DNN to enhance the performance. Finally, a novel reinforcement learning-based adaptive bitrate (ABR) algorithm is proposed to verify the performance of BiSR on real network traces. Our evaluation, using a full system implementation, shows that BiSR saves 26% of bitrate compared to the traditional H.264 codec and improves the SSIM of video by 3.7% compared to the prior state-of-the-art. Overall, BiSR enhances the user-perceived quality of experience by up to 30.6%.
关键词
学校署名
第一
语种
英语
相关链接[Scopus记录]
收录类别
EI入藏号
20232014104388
EI主题词
Bandwidth ; Optical resolving power ; Quality of service ; Reinforcement learning ; Video streaming
EI分类号
Ergonomics and Human Factors Engineering:461.4 ; Information Theory and Signal Processing:716.1 ; Artificial Intelligence:723.4 ; Light/Optics:741.1
Scopus记录号
2-s2.0-85159325583
来源库
Scopus
引用统计
被引频次[WOS]:0
成果类型会议论文
条目标识符http://sustech.caswiz.com/handle/2SGJ60CL/536585
专题南方科技大学
作者单位
1.SUSTech,Peng Cheng Laboratory,Shenzhen,China
2.Peng Cheng Laboratory,Shenzhen,China
3.Hong Kong University of Science and Technology(GZ),Guangzhou,China
4.International Graduate School,Tsinghua University,Shenzhen,China
5.Northumbria University,Newcastle,United Kingdom
6.Tencent,Shenzhen,China
第一作者单位南方科技大学
第一作者的第一单位南方科技大学
推荐引用方式
GB/T 7714
Yu,Qian,Li,Qing,He,Rui,et al. BiSR: Bidirectionally Optimized Super-Resolution for Mobile Video Streaming[C],2023:3121-3131.
条目包含的文件
条目无相关文件。
个性服务
原文链接
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
导出为Excel格式
导出为Csv格式
Altmetrics Score
谷歌学术
谷歌学术中相似的文章
[Yu,Qian]的文章
[Li,Qing]的文章
[He,Rui]的文章
百度学术
百度学术中相似的文章
[Yu,Qian]的文章
[Li,Qing]的文章
[He,Rui]的文章
必应学术
必应学术中相似的文章
[Yu,Qian]的文章
[Li,Qing]的文章
[He,Rui]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
[发表评论/异议/意见]
暂无评论

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。