IEEE ICIP 2024 proudly presents an extensive and varied industry program, including workshops organized by top experts on timely and relevant topics to ICIP 2024 themes, industry panels and keynotes by prominent experts from industry and academia as well as a Generative AI art competition. A summary of the program follows with links to more details for each.

Workshop: AOMedia Industry Workshop Sponsored by Google and Meta

Overview:

In this joint workshop, we will first present the recent progress in enabling AV1 deployment, developing the next generation Alliance for Open Media (AOM) video coding standard and software implementation of the AOM encoders and other related activities. The second part of the workshop will focus on various topics from real production use cases at Google and Meta, including image compression, AV1 enabling for RTC use case, quality metrics, and Machine Learning for video compression, etc.

Schedule and location:

Wednesday, 30 October 2024, 8:15AM – 12PM, in Capital Suite – 20

Organizers:

• Ioannis Katsavounidis, Research Scientist, Video Infrastructure, Meta
• Ryan Lei, Video Codec Specialist, Video Infrastructure, Meta
• Debargha Mukherjee, Principal Engineer, Google
• In Suk Chong, Video Codec Lead, Google
• Balu Adsumilli, Media Algorithms, Google
• Shan Liu, Distinguished Scientist, Tencent

Next, ICIP 2024 will host two important industry/academia panels: “GENAI-To GPT or Not to GPT: This is NOT the question” and “Video Coding for Machines.”

Panel 1: GENAI- To GPT or Not to GPT: This is NOT the question

Overview:

The AI Field took a transformational turn with the creation of powerful Generative Artificial Intelligence (AI) models. This disruptive technology has captured the attention all over the world at a very fast rate. For instance, ChatGPT reached 100 million users in two months. It is the fastest growing app. ever, with an impact of $7.9 trillion.

Generative AI is relatively new, it has stimulated and generated many questions among regular citizens and experts/developers as well. This is just the beginning, what is coming may be beyond imagination. Generative AI will impact all our life. In some cases, the applications may be clearly visible, but most of the times, they will be working in the background.

Our distinguished panelist will address some of these questions. Audience is strongly
encouraged to interact with the panel through questions and comments.

Schedule and location:

Monday, 28 October 2024, 2:30PM – 3:30PM, in ICC Hall 1

Organizer:

Professor Magdy Bayoumi

Panelists: TBA

Panel 2: Video Coding for Machines

Overview:

Video is occupying about 80% of today’s Internet traffic. Out of this, more and more video contents are consumed by machines, in broad applications such as video surveillance, healthcare monitoring, transportation, smart cities, etc. Machine vision is different from human vision in many aspects. Great interests and demands have risen in recent years to develop video coding technologies and solutions for machine vision requirements and use cases. This panel will discuss and envision technology and standard development, applications, challenges, as well as trends that are related to video coding for machines (VCM).

Schedule and location:

Tuesday, 29 October 2024, 2:30PM – 3:30PM, in ICC Hall 1

Organizer:

• Shan Liu, Distinguished Scientist, Tencent

Panelists:

• Marek Domanski, Full professor, Director of the institute, Poznan University of Technology, Poland
• Jin Lee, Principal Researcher, Electronics and Telecommunications Research Institute (ETRI), Korea
• Dong Tian, Principal Researcher, InterDigital Inc., USA
• Giuseppe Valenzise, CNRS researcher and head of the Multimedia and Networking team, Université Paris-Saclay, CentraleSupélec, France
• Honglei Zhang, Principal Researcher, UNokia Technologies, Finland

IEEE ICIP 2024 Industry track is proud to present two keynotes by highly reputed scholars: “Generative AI in the open-source world: Challenges and opportunities” and “Language as an ‘API’ for vision.”

Keynote by Professor Merouane Debbah

Title: Generative AI in the open-source world: Challenges and opportunities

Abstract: This talk will review the evolving landscape of generative AI within the open-source world, we will explore the unique opportunities that open-source AI offers, such as customization, and community-driven innovation. We will also address critical challenges, including the sustainability of open-source models, data limitations and the complexity of scaling within the energy wall. By examining both the hurdles and potential pathways forward, we aim to shed light on how open-source AI can drive transformative progress while navigating its inherent obstacles.

Bio: Mérouane Debbah is Professor at Khalifa University of Science and Technology in Abu Dhabi and founding Director of the KU 6G Research Center. He is a frequent keynote speaker at international events in the field of telecommunication and AI. His research has been lying at the interface of fundamental mathematics, algorithms, statistics, information and communication sciences with a special focus on random matrix theory and learning algorithms. In the Communication field, he has been at the heart of the development of small cells (4G), Massive MIMO (5G) and Large Intelligent Surfaces (6G) technologies. In the AI field, he is known for his work on Large Language Models, distributed AI systems for networks and semantic communications. He received multiple prestigious distinctions, prizes and best paper awards (more than 40 IEEE best paper awards) for his contributions to both fields. He is an IEEE Fellow, a WWRF Fellow, a Eurasip Fellow, an AAIA Fellow, an Institut Louis Bachelier Fellow, an AIIA Fellow and a Membre émérite SEE

Schedule and location:

Tuesday, 29 October 2024, 4:30 – 5:15 PM, in ICC Hall 1

Spotlight by Dr Yasser Djilali Technology Innovation Institute, Falcon Vision Language Model Team

Title: Language as an ‘API’ for vision

Abstract: Dr Yasser Djilali (TII) will introduce the recently developed Falcon VLM on behalf of the AI center team in the Technology Innovation Institute, UAE. He will talk about how vision has evolved with the integration of language, focusing on the of Falcon VLM. He will then highlight some recent work from his group, spending time on Falcon VLM key features and training recipe.

Bio: Yasser Djilali did his PhD at Dublin City University in Ireland on human perception and self-supervised learning from images. Now, he is a researcher at the Technology Innovation Institute in Abu Dhabi, working on multimodal vision-language research and development.

Schedule and location:

Tuesday, 29 October 2024, 5:30 – 5:45 PM in ICC Hall 1

Generative AI art competition to fight climate change

Overview:

The contest welcomes all individuals interested in creating art inspired by climate change issues. The aim is to utilize the latest AI-powered generative image modeling tools to produce artworks that raise awareness about the impact of climate change. Voting for the best artwork is allowed to ICIP2024 registered participants. The top 3 artworks, among finalists, will be determined by the majority of votes from ICIP 2024 registered participants

Evaluation standards:

The selection of the 10 finalists will consider factors such as creativity, technical proficiency, aesthetic appeal, originality of the concept, the novelty of prompt engineering techniques, and relevance to climate change.

Schedule:

October 22, 2024: Application Submission Deadline

October 27 to 30, 2024: voting during the conference

October 30: winner disclosure

Application procedure:

Participants are invited to submit their work in electronic form (image file) using the CMT link

For inquiries, please reach out to haithem.boussaid@tii.ae and shanl@global.tencent.com