CAREER: Enabling Perception-Driven Optimization for Online Videos
职业:为在线视频实现感知驱动的优化
基本信息
- 批准号:2146496
- 负责人:
- 金额:$ 55万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2022
- 资助国家:美国
- 起止时间:2022-04-01 至 2027-03-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).Today, video streaming is no longer just about entertainment but essential to our daily life. For example, high-resolution live videos are used for daily (remote) learning, and videos streamed from road-side sensors are constantly analyzed to make our cities and roads safer. These changes lead to a higher need for network bandwidth to reach desired Quality of Experience (QoE). This is challenging, because to serve all these demands, today’s video delivery systems must either lower video quality or upgrade the network infrastructure (which can be slow and expensive). This project develops Perception-Driven Optimization (PDO), a new paradigm that improves user experience for today’s online videos without using more bandwidth. The key insight is that in terms of how video quality impacts QoE, significant heterogeneities exist across videos, human users, and video analytic models, which are hard to capture by today’s offline QoE models. PDO takes a data-driven approach to automate online QoE modeling, by leveraging the large number of video sessions available to today’s video delivery systems. This research entails three thrusts: (a) for live video services, how to automate QoE modeling in live content with a minimal number of online sessions; (b) for on-demand videos, how to build per-user QoE models without impacting user experience; and (c) for video-analytics services, how to profile video quality’s impact on video-analytics mode. PDO also integrates online QoE modeling with today’s video-delivery systems to better adapt to changes in network conditions.This project works with industry partners in online video services and edge video analytics, and local initiatives to deploy PDO and improve online video QoE, especially for users who suffer quality issues, and scale edge analytics to more sensor videos. It also creates new ways to tie system/networking education with everyday use of the Internet, such as new educational tools that visualize how network performance affects user-perceived video quality and video-based intelligent applications. The project also engages with students through Leadership Alliance which targets underrepresented populations, and the developed educational tools will be used for compileHer, a program that targets high school female students.The software and research artifacts implemented as part of this project are released on a public website: https://people.cs.uchicago.edu/~junchenj/perception_driven_optimization. The site is regularly maintained and includes released data, source code, and reproduction instructions.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
该奖项全部或部分由2021年美国救援计划法案(公法117-2)资助。今天,视频流不再只是娱乐,而是我们日常生活中必不可少的。例如,高分辨率实时视频用于日常(远程)学习,并不断分析来自路边传感器的视频流,以使我们的城市和道路更安全。这些变化导致对网络带宽的更高需求,以达到期望的体验质量(QoE)。这是一个挑战,因为要满足所有这些需求,今天的视频传输系统必须降低视频质量或升级网络基础设施(这可能是缓慢和昂贵的)。该项目开发了感知驱动优化(PDO),这是一种新的范例,可以在不使用更多带宽的情况下改善当今在线视频的用户体验。关键的见解是,就视频质量如何影响QoE而言,视频、人类用户和视频分析模型之间存在显著的异质性,这是当今离线QoE模型难以捕捉的。PDO采用数据驱动的方法,通过利用当今视频交付系统可用的大量视频会话来自动化在线QoE建模。这项研究需要三个方面的努力:(a)对于直播视频服务,如何以最少数量的在线会话自动化直播内容中的QoE建模;(B)对于点播视频,如何在不影响用户体验的情况下构建每个用户的QoE模型;以及(c)对于视频分析服务,如何分析视频质量对视频分析模式的影响。PDO还将在线QoE建模与当今的视频交付系统集成,以更好地适应网络条件的变化。该项目与在线视频服务和边缘视频分析的行业合作伙伴以及本地计划合作,以部署PDO并改善在线视频QoE,特别是针对质量问题的用户,并将边缘分析扩展到更多传感器视频。它还创造了将系统/网络教育与日常使用互联网联系起来的新方法,例如新的教育工具,这些工具可以可视化网络性能如何影响用户感知的视频质量和基于视频的智能应用程序。该项目还通过领导力联盟(Leadership Alliance)与学生互动,该联盟针对的是代表性不足的人群,开发的教育工具将用于针对高中女生的compileHer项目。作为该项目一部分实施的软件和研究成果将在公共网站上发布:https://people.cs.uchicago.edu/~junchenj/perception_driven_optimization。该网站定期维护,包括发布的数据,源代码和复制说明。该奖项反映了NSF的法定使命,并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。
项目成果
期刊论文数量(3)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
AccMPEG: Optimizing Video Encoding for Video Analytics
- DOI:10.48550/arxiv.2204.12534
- 发表时间:2022-04
- 期刊:
- 影响因子:0
- 作者:Kuntai Du;Qizheng Zhang;Anton Arapin;Haodong Wang;Zhengxu Xia;Junchen Jiang
- 通讯作者:Kuntai Du;Qizheng Zhang;Anton Arapin;Haodong Wang;Zhengxu Xia;Junchen Jiang
OneAdapt: Fast Adaptation for Deep Learning Applications via Backpropagation
- DOI:10.1145/3620678.3624653
- 发表时间:2023-10
- 期刊:
- 影响因子:0
- 作者:Kuntai Du;Yuhan Liu;Yitian Hao;Qizheng Zhang;Haodong Wang;Yuyang Huang;Ganesh Ananthanarayanan;Junchen Jiang
- 通讯作者:Kuntai Du;Yuhan Liu;Yitian Hao;Qizheng Zhang;Haodong Wang;Yuyang Huang;Ganesh Ananthanarayanan;Junchen Jiang
Online Profiling and Adaptation of Quality Sensitivity for Internet Video
互联网视频质量灵敏度的在线分析和调整
- DOI:10.1145/3620678.3624788
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Cheng, Yihua;Zhang, Hui;Jiang, Junchen
- 通讯作者:Jiang, Junchen
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Junchen Jiang其他文献
Eloquent: A More Robust Transmission Scheme for LLM Token Streaming
Eloquent:一种更稳健的 LLM 令牌流传输方案
- DOI:
10.1145/3672198.3673797 - 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Hanchen Li;Yuhan Liu;Yihua Cheng;Siddhant Ray;Kuntai Du;Junchen Jiang - 通讯作者:
Junchen Jiang
Raising the Level of Abstraction for Time-State Analytics With the Timeline Framework
使用时间线框架提高时间状态分析的抽象级别
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:0
- 作者:
Henry Milner;Yihua Cheng;Jibin Zhan;Hui Zhang;Vyas Sekar;Junchen Jiang;I. Stoica - 通讯作者:
I. Stoica
Understanding Throughput Stability and Predictability to Enable Better Video Quality of Experience
了解吞吐量稳定性和可预测性以实现更好的视频体验质量
- DOI:
- 发表时间:
2015 - 期刊:
- 影响因子:0
- 作者:
Xiaoqi Yin;Junchen Jiang;Vyas Sekar;B. Sinopoli - 通讯作者:
B. Sinopoli
Enabling Data-Driven Optimization of Quality of Experience for Internet Applications
- DOI:
- 发表时间:
2017 - 期刊:
- 影响因子:0
- 作者:
Junchen Jiang - 通讯作者:
Junchen Jiang
Measurements on movie distribution behavior in Peer-to-Peer networks
对等网络中电影分发行为的测量
- DOI:
10.1109/inm.2011.5990585 - 发表时间:
2011 - 期刊:
- 影响因子:0
- 作者:
Xiaofei Wang;Xiaojun Wang;Chengchen Hu;Keqiang He;Junchen Jiang;B. Liu - 通讯作者:
B. Liu
Junchen Jiang的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Junchen Jiang', 18)}}的其他基金
CNS Core: Small: Closing the Reality Gap for Learning-Augmented Network Systems
CNS 核心:小型:缩小学习增强网络系统的现实差距
- 批准号:
2131826 - 财政年份:2022
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
CNS Core:Medium:Systems Challenges in Scaling Distributed Intelligent Applications
CNS 核心:中:扩展分布式智能应用程序的系统挑战
- 批准号:
1901466 - 财政年份:2019
- 资助金额:
$ 55万 - 项目类别:
Continuing Grant
相似海外基金
Collaborative Research: SHF: Small: Enabling Efficient 3D Perception: An Architecture-Algorithm Co-Design Approach
协作研究:SHF:小型:实现高效的 3D 感知:架构-算法协同设计方法
- 批准号:
2334624 - 财政年份:2023
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
Collaborative Research: CNS Core: HCC: Small: Enabling Efficient Computer Systems for Augmented and Virtual Reality: A Perception-Guided Approach
合作研究:CNS 核心:HCC:小型:为增强现实和虚拟现实启用高效计算机系统:感知引导方法
- 批准号:
2225861 - 财政年份:2022
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
RINGS: Enabling Joint Sensing, Communication, and Multi-tenant Edge AI for Cooperative Perception Systems
RINGS:为协作感知系统提供联合感知、通信和多租户边缘人工智能
- 批准号:
2148353 - 财政年份:2022
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
AISat: enabling spacecraft autonomy with smart perception
AISat:通过智能感知实现航天器自主
- 批准号:
10027357 - 财政年份:2022
- 资助金额:
$ 55万 - 项目类别:
Collaborative R&D
Collaborative Research: CNS Core: HCC: Small: Enabling Efficient Computer Systems for Augmented and Virtual Reality: A Perception-Guided Approach
合作研究:CNS 核心:HCC:小型:为增强现实和虚拟现实启用高效计算机系统:感知引导方法
- 批准号:
2225860 - 财政年份:2022
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Evaluating Bias In The Creation and Perception of GAN-Generated Faces
EAGER:DCL:SaTC:实现跨学科协作:评估 GAN 生成的面孔的创建和感知中的偏差
- 批准号:
2210142 - 财政年份:2022
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
Enabling Interactive Perception Applications on Edge Devices
在边缘设备上启用交互式感知应用
- 批准号:
RGPIN-2019-05989 - 财政年份:2022
- 资助金额:
$ 55万 - 项目类别:
Discovery Grants Program - Individual
Enabling Interactive Perception Applications on Edge Devices
在边缘设备上启用交互式感知应用
- 批准号:
RGPIN-2019-05989 - 财政年份:2021
- 资助金额:
$ 55万 - 项目类别:
Discovery Grants Program - Individual
Collaborative Research: SHF: Small: Enabling Efficient 3D Perception: An Architecture-Algorithm Co-Design Approach
协作研究:SHF:小型:实现高效的 3D 感知:架构-算法协同设计方法
- 批准号:
2126643 - 财政年份:2021
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Small: Enabling Efficient 3D Perception: An Architecture-Algorithm Co-Design Approach
协作研究:SHF:小型:实现高效的 3D 感知:架构-算法协同设计方法
- 批准号:
2126642 - 财政年份:2021
- 资助金额:
$ 55万 - 项目类别:
Standard Grant