you are welcome to attend FOR FREE the “e-Workshop on GANs for Media Content Generation”, on October 1st, 2020, in the framework of EU-funded H2020 R&D project AI4Media: https://ai4media.eu.

Generative Adversarial Networks (GANs) are part of the cutting edge in recent machine learning research. Trained by exploiting the interplay between a generative and a discriminative deep neural network, GANs are able to implicitly model the data distribution, thus allowing us to generate realistic data samples after model training is complete. 
The Digital Media sector is perhaps the greatest beneficiary of GAN-based algorithms, with industry-relevant research already taking advantage of their potential. They are useful for a wide range of media-related applications, such as image-to-image translation, optical recognition enhancement, text-to-speech systems, music/image/video generation, video summarization, image anonymization and many others, frequently giving rise to state-of-the-art results. 
On the negative side, the rise of so-called “deep fakes” poses significant new challanges, both ethical and technical, thus making the development of methods to robustly detect them a top priority. Overall, GANs hold the key to revolutionizing the way we produce media and arts content.

The AI4Media project focuses on building a network of research excellence that will deliver the next generation of core AI advances to serve the key sector of Media. In this context, this Workshop is meant to disseminate knowledge regarding GAN-based state-of-the-art for media content generation and for fake media detection. The workshop lectures are at CS/ECE/EE graduate level. MSc/PhD/Postodoc researchers are particularly welcomed from Europe and around the world.

The lectures will be presented live by senior or Postdoc researchers from several AI4Media consortium members and collaborators across Europe.
You can attend using Webex, accessed nthrough the Workshop website:   https://ai4media.eu/events/gan-media-generation-workshop-oct-2020/

E-workshop program (CEST time-zone):

-10:00 – 10:15 Welcome
-10:15 – 10:30 Yiannis Kompatsiaris Centre for Research and Technology Centre Hellas (CERTH-ITI) “Introduction to AI4Media Project”
-10:30 – 11:10 Marta Mrak, BBC R&D, “Learning to Predict Pixels Using AI for Content Enhancement and Delivery”
-11:10 – 11:30 Ioannis Mademlis, Aristotle University of Thessaloniki (AUTH) “An Overview of GANs for Media Production”
-11:30 – 11:50 Vasileios Mezaris, Centre for Research and Technology Hellas (CERTH-ITI) “GAN-based Video Summarization”
-11:50 – 12:10 Break
-12:10 – 12:30 Nicu Sebe, University of Trento (UNITN) “Human Image and Video Generation/Animation”
-12:30 – 12:50 Symeon Papadopoulos Centre for Research and Technology Hellas (CERTH-ITI) “Deepfake and Synthetic Media Detection”
-12:50 – 13:10 Vasileios Mygdalis Aristotle University of Thessaloniki (AUTH) “Adversarial Face De-identification for Privacy Protection”
-13:10 – 13:50 Luisa Verdoliva, University of Naples Federico II (UNINA), “Major Challenges in the Detection of Synthetic Media and Deepfakes”
-13:50 – 14:10 Closing remarks

This event is the first activity of the upcoming International AI Doctoral Academy (IAIDA) put forward by AI4Media.
Stay tuned at: https://ai4media.eu  and https://twitter.com/AI4Media_EU

Till IAIDA creates its own communication channels (very soon), you may want to register to the CVML email list, where certainly all related messages will be posted, following instructions in https://lists.auth.gr/sympa/info/cvml

Sincerely yours,
Dr. I. Kompatsiaris, CERTH-ITI, AI4Media Coordinator, Prof. I. Pitas, AUTH,  AI4Media Doctoral Studies coordinator