Scope and topics of the workshop
Nowadays people spend a significant amount of time on consuming various types of streaming videos such as video on demand (VoD) for movies, dramas or variety shows through Netflix, User Generated Content (UGC) through Facebook or Tiktok, or live streaming videos for social, gaming, or shopping, benefiting from the popularity of high-speed networks and intelligent terminals. Users thus have increasing demands on the Quality of Experience (QoE) of this visual multimedia, which reflects the user’s fulfillment of enjoyment or expectation to a service or an application. Enhancing the QoE of end-users is thus the ultimate goal nowadays for the multimedia service providers. The scope of this workshop focuses on the QoE assessment of any visual multimedia applications both subjectively and objectively.
The topics include:
· QoE assessment on different visual multimedia applications, including VoD for movies, dramas, variety shows, UGC on social networks, live streaming videos for gaming/shopping/social, etc.
· QoE assessment for different video formats in multimedia services, including 2D, stereoscopic 3D, High Dynamic Range (HDR), Augmented Reality (AR), Virtual Reality (VR), 360, Free-Viewpoint Video(FVV), etc.
· Key performance indicators (KPI) analysis for QoE.
Organizers
Xinbo Gao
Xidian University, China
Patrick Le Callet
University of Nantes, France
Jing Li
Alibaba Group, China
Zhi Li
Netflix Inc., U.S.
Wen Lu
Xidian University, China
Jiachen Yang
Tianjin University, China
Program Committee
Leida Li,
Xidian University, China
Hantao Liu,
Cardiff University, U.K.
Giuseppe Valenzise,
CNRS - CentraleSupelec, France
Mai Xu,
Beihang University, China
Lu Zhang,
INSA de Rennes, France
Call for Papers
The workshop QoEVMA2020 focuses on the QoE assessment of any visual multimedia applications, including possible key performance indicators (KPI) analysis on different video formats. The topics of interests of this workshop include but not limited to:
  • QoE for traditional image/video and stereo image/video: the new research for evaluation of traditional visual multimedia.
  • QoE methods for underwater images/videos or QoE-driven underwater image/video processing: assessment for underwater visual multimedia.
  • QoE methods for image/video retargeting or QoE-driven image/video retargeting processing: the new researches on image retargeting quality assessment (IRQA).
  • QoE methods for other application situations: any application situation which can import the QoE, such as screen content image/video.
  • QoE methods for visual multimedia based on machine learning: researches on QoE methods for any kind of visual information based on new technologies, and deep learning is encouraged.
  • QoE-driven mobile visual multimedia processing: the QoE applications on mobile situations and the new research on mobile visual multimedia processing based on QoE.
    • Submission
    Submission Due: Monday, June 29, 2020 July 30, 2020 （PST）
    Acceptance Notification: Friday, July 31 2020 August 26, 2020 （PST）
    Camera Ready Submission: Friday, August 7 2020 September 2, 2020 （PST）
    Workshop Date: 12 or 16 October 2020 (to be decided)

    Please refer to the submission site (https://2020.acmmm.org/call-for-paper.html) for submission policies.

    Please submit your paper via https://cmt3.research.microsoft.com/MMW2020 . You will have to choose "1st Workshop On Quality of Experience (QoE) in Visual Multimedia Applications" as your track. Submissions can be of varying length from 4 to 8 pages, plus additional pages for the reference pages; i.e., the reference page(s) are not counted to the page limit of 4 to 8 pages. There is no distinction between long and short papers, but the authors may themselves decide on the appropriate length of the paper. All papers will undergo the same review process and review period.

    Have questions?

    Please feel free to send an email to Dr. Jing LI (lj225205@alibaba-inc.com) if you have any questions relating to the workshop.

    Program

    Due to the current worldwide COVID-19 pandemic, QoEVMA'20 will be an all-online workshop, which will be held on 16 October. Please note that the workshop schedule follows the Eastern Standard Time (EST).

    The keynote sessions will be a single track session, and all will be running as live meetings (Zoom webinar). Each accepted paper will have a pre-recorded video presentation (around 15 min), which will be accessed on demand during the conference period. The time slots allocated to accepted papers are only for live Q&A, not traditional paper presentations.

    Time slot (EST) Session
    8:00 am - 9:00 am Keynote session 1 (Live session)： QoE and Immersive Media: A New Challenge (Federica Battisti, University of Padova)
    9:00 am - 10:00 am Q & A session 1:
    Towards Better Quality Assessment of High-Quality Videos (Suiyi Ling, CAPACITÉS SAS; Yoann Baveye, CAPACITÉS SAS; Deepthi Nandakumar, Amazon Video; Sriram Sethuraman, Amazon Video; Patrick Le Callet, University of Nantes)
    VMP360: Adaptive 360° Video Streaming Based on Optical Flow Estimated QoE (Yuxuan Pan, Xikang Jiang, Wei Quan, Lin Zhang, Beijing University of Posts and Telecommunications)
    Improving the efficiency of QoE crowdtesting (Ricky K. P. Mok, CAIDA/UC San Diego; Ginga Kawaguti, NTT)
    10:00 am - 11:00 am Keynote session 2 (Live session): Do we Really Need No-reference Video Quality Metrics? （Ioannis Katsavounidis, Facebook）
    11:00 am - 12:00 am Q & A session 2:
    Perceptual Characterization of 3D Graphical Contents based on Attention Complexity Measures (Mona Abid, Matthieu Perreira Da Silva, Patrick Le Callet, University of Nantes)
    Performance Measurements on a Cloud VR Gaming Platform (Yen-Chun Li, Chia-Hsin Hsu, Yu-Chun Lin, Cheng-Hsin Hsu, National Tsing-Hua University)
    A Subjective Study of Multi-Dimensional Aesthetic Assessment for Mobile Game Image (Suiyi Ling, CAPACITÉS SAS; Junle Wang, Tencent; Wenming Huang, Tencent; Yundi Guo, Tencent; Like Zhang, Tencent; Yanqing Jing, Tencent; Patrick Le Callet, University of Nantes)

    Speakers
    Federica Battisti, Assistant Professor, University of Padova, Padua, Italy
    Federica Battisti is an Assistant Professor in the Department of Information Engineering at University of Padova, Padua, Italy. She received the Laurea (Master of Science) in Electronic Engineering from Università degli Studi Roma Tre, Rome, Italy, in July 2006 and in March 2010 she received the Ph.D. degree with a thesis titled “Multimedia data hiding based on human perception characteristics”. Her main research interests are signal and image processing with a focus on the subjective quality analysis of multimedia. She is IEEE Senior member, and she serves as Associate Editor of IEEE Transactions on Multimedia, of EURASIP Journal on Image and Video Processing, and of ELSEVIER Signal Processing: Image Communication. She is member of the IEEE Multimedia Signal Processing Technical Committee, of the EURASIP Visual Information Processing Technical Area Committee, of the VQEG Immersive Media Group, she contributes to the IEEE P3333.1 Human Factors for Visual Experiences Working Group.
    Ioannis Katsavounidis, Research Scientist – Video Infrastructure – Facebook, Menlo Park, CA, USA
    /Dr. Ioannis Katsavounidis is a member of the Video Processing group, part of the Video Infrastructure team, leading technical efforts in improving video quality across all video products at Facebook. Before joining Facebook, he spent 3.5 years at Netflix, contributing to the development and popularization of VMAF, Netflix's video quality metric, as well as inventing the Dynamic Optimizer, a shot-based video quality optimization framework that brought significant bitrate savings across the whole streaming spectrum. Before that, he was a professor for 8 years at the University of Thessaly's Electrical Engineering Department in Greece, teaching video compression, signal processing and information theory. His work experience includes a year in China as co-founder and CTO of Cidana, a mobile multimedia software company, 7 years as director of software at InterVideo and 4 years in Italy working for an underground high-energy Physics experiment. He has over 100 publications and patents in the general field of video coding, but also high energy experimental physics. His research interests lie in video coding, video quality, adaptive streaming and hardware/software partitioning of multimedia processing, with particular emphasis on energy efficiency.