CIS - "Get to know your neighbors" Seminar series - Prof. Touradj Ebrahimi

Thumbnail

Event details

Date 07.02.2022 15:1516:15  
Speaker Prof. Touradj Ebrahimi
Location
Hybride TBD
Online
Category Conferences - Seminars
Event Language English
Title: JPEG AI: The text generation of learning based image compression

Abstract:
Artificial Intelligence (AI) has emerged as a key technology in a wide range of applications, including those in visual information processing. 
Computer vision based on AI has shown outstanding results in pattern recognition and content understanding and AI-based image processing has demonstrated unparalleled performance in cognitive enhancement of visual content as witnessed by advances in super-resolution and denoising operations taking advantage of deep learning techniques. More recent efforts in AI-based compression have shown superior performance when compared to the most advanced to state of the art in image coding.
Based on the above observations, the JPEG standardization committee has started a new project in AI-based image compression for next generation applications where visual content should be efficiently represented to be used for both human and machine consumption. The scope of JPEG AI is defined as a learning-based image coding standard that offers a single-stream, compact and compressed domain representation, targeting both human visualization, with significant compression efficiency improvement over current image coding standards, as well as effective performance for image processing and computer vision tasks.
In this talk we will provide an overview of JPEG AI activities, its current status and its roadmap. Doing so, we will discuss potential applications that can be enabled thanks to JPEG AI, and examine potential technologies which can become the backbone of such a standard. 

Bio:
Touradj Ebrahimi is professor of image processing at Ecole Polytechnique Fédérale de Lausanne (EPFL). He is active in teaching and research in multimedia signal processing and heads the Multimedia Signal Processing Group at EPFL. 
Since 2014, he has been the Convenor (Chairman) of the JPEG standardization Committee which has produced a family of standards that have revolutionised the world of imaging. He represents Switzerland as the head of its delegation to JTC1 (in charge of standardization of information technology in ISO and IEC), SC29 (the body overseeing MPEG and JPEG standardization) and is a member of ITU representing EPFL. He was previously the chairman of the SC29 Advisory Group on Management until 2014. Prof. Ebrahimi is involved in Ecma International as a member of its ExeCom since 2020 and serves as consultant, evaluator and expert for European Commission and other governmental funding agencies in Europe and advises a number of Venture Capital companies in Switzerland in their scientific and technical audits. He has founded several startup and spinoff companies in the past two decades, including the most recent RayShaper SA, a research company based in Switzerland involved in AI powered multimedia. Prof. Ebrahimi is author or co-author of over 300 scientific publications and hold a dozen invention patents. His areas of interest include image and video compression, media security, quality of experience in multimedia and AI based image and video processing and analysis. Prof. Ebrahimi is a Fellow of the IEEE and SPIE and has been recipient of several awards and distinctions, including an IEEE Star Innovator Award in Multimedia.


The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/63510408613

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, February 7th, 2022 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages

Practical information

  • General public
  • Free

Organizer

  • CIS

Contact

Tags

CISSBSTIICENACApprentissage automatique Intelligence artificielle Robotique Vision par ordinateur Artificial intelligence AI Robotics Computer vision

Share