We hope you can join us on Thursday, May 4th at 12:30pm CET for our next 1-hour webinar with Leonardo Chiariglione, Roberto Iacoviello, and Chuanmin Jia on “MPAI: AI-based End-to-End and AI-Enhanced Video Coding.”
[6:30 a.m. New-York] – [12:30 p.m. Paris] – [6:30 p.m. Beijing]
To join the webinar, please register to receive more details on how to connect. The registration form can be found at: https://forms.gle/9JCc6NBgM1x2kZK6A
*If you wish to promote a EURASIP journal special issue, conference, event, or new image/video database at an upcoming webinar, please reply to this email with additional details. Contact: esinu.abadjivor@springernature.com

Title: MPAI: AI-based End-to-End and AI-Enhanced Video Coding
Speakers: L. Chiariglione, R. Lacoviello and C. Jia

Abstract:
MPAI-General (L. Chiariglione): Moving Picture, Audio, and Data Coding by Artificial Intelligence is the Standards Developing Organisation whose mission is Data Coding by Artificial Intelligence. Founded in September 2020, it has developed and published 12 technical documents on audio enhancement, human-machine conversation, execution of AI applications, company performance prediction, neural network watermarking, and metaverse model. The talk on MPAI will briefly describe the mission, the organisation, and the scope of activities.
MPAI  (http://mpai.community/)
MPAI-EVC talk (R. Lacoviello): Video internet traffic has grown rapidly, leading to increased strain on infrastructure, slower speeds, and higher costs. Video compression can alleviate this problem; deep learning-based coding tools have shown great potential to reduce bitrate and improve quality. MPAI is working to standardize these tools. In particular, MPAI-EVC is working to improve an existing video codec by 25% in terms of encoding gain by exploiting deep learning.
MPAI-EEV talk (C. Jia): Recently, neural network for video coding has been an active research topic, receiving attention from both academic society and industry entity. The end-to-end video coding (EEV) of MPAI exploits AI-based data coding technologies in an end-to-end fashion, namely fully neural network based video codec. MPAI-EEV is at the level of Functional Requirements. The essential use cases and related reference model are under construction. This talk elaborates recent advances in EEV and reports the model design, which outperforms the latest H.266/VVC standard in terms of MS-SSIM.

Bios:
Leonardo Chiariglione, MSc at the Polytechnic of Torino and PhD at the University of Tokyo, is the initiator and leader of international groups such as MPEG which have shaped media technology and business. He currently leads MPAI, the standards body for artificial intelligence-based data coding.
Roberto Iacoviello is a Lead Research Engineer who graduated from the Politecnico di Torino and has been employed at Rai R&D since 2007. His research is currently concentrated on developing artificial intelligence applications in video compression and point clouds, next-generation television services such as virtual production for broadcast television.He leads two groups at the European Broadcasting Union (EBU) , namely the Video Evaluation group and the Computer Graphics Animation group.  Additionally, he is involved in two EC-funded projects, namely AI4MEDIA and XRECO.
Chuanmin Jia is currently an Assistant Professor with the Wangxuan Institute of Computer Technology, Peking University, Beijing, China. His research interests include video compression and processing. He has published over 20 journal/conference papers in related venue, received 3 best paper awards.


Webinar videos are available online at https://vimeo.com/showcase/8005816.