DSPT#60 - AI, Can you Recommend me a World of Pure Imagination (Porto)

This is a past event

71 people went

Location image of event venue


"Come with me and you'll be in a world of pure imagination" is what DSPT recommends for the evening of the 8th of July, in our meetup integrated with Porto VISUM School. We'll hear João Vinagre talk about the intricate details of recommender systems and Mohamed Elhoseiny talk about how Machines can access characteristics of our imagination to improve computer vision systems.

Will you join us in this beautiful world of "pure imagination"?

=== SCHEDULE ===

The preliminary agenda for the meetup is the following:
• 18:30-19:00: Welcome and get together
• 19:00-19:30: "I know what you like”: The magic, the science, and the future of recommender systems by João Vinagre, INESC TEC
• 19:40-19:45: Group photo
• 19:45-20:15: Networking / Coffee Break
• 20:15-20:45: Imagination Inspired Vision by Mohamed Elhoseiny, Baidu
• 20:50: Closing
• 21:00: Dinner is optional but it might be an excellent opportunity for networking. You can register here: https://doodle.com/poll/6iihuzgaiv5xgsq4

This Meetup is sponsored by Deloitte Digital: https://eu.deloittedigital.com/en/home

Talk 1
Title: "I know what you like”: The magic, the science, and the future of recommender systems

Abstract: Recommender systems are pervasive in online commerce and services. They account for a huge - if not the largest - share of online traffic, from streaming services (audio and video) to social networks and online commerce. This talk will go through the origins, the state-of-the-art and the future of recommendation algorithms.

Bio: João Vinagre is a researcher at the Laboratory of Artificial Intelligence and Decision Support (LIAAD) of INESC TEC and an invited professor at the Department of Computer Science, in the Faculty of Sciences of the University of Porto (FCUP). He obtained his PhD in 2016 from the joint doctoral programme of the Universities of Minho, Aveiro and Porto. His research focuses on recommender systems and user modeling, with special emphasis on stream-based algorithms, evaluation issues and incremental ensemble models. He has published several journal and conference papers on these subjects, and has worked on multiple technology transfer projects with industry partners. He is currently a member of the Data Science Hub of INESC TEC, an initiative to promote the collaboration between the industry and the academia in Data Science projects.

Talk 2:
Title: Imagination Inspired Vision

Abstract: Imagination is one of the key properties of human intelligence that enables us not only to learn new concepts quickly and efficiently but also to generate creative products like art and music. My research has focused on developing imagination-inspired techniques that empower AI machines to see the world (computer vision) or to create novel products (e.g., fashion and art); “Imagine to See” and “Imagine to Create”. In this talk, I will cover some of my works on these two directions and I will show how they are connected by the developed techniques and that they circle back to benefit each other. Imagine to See: Many people might not know what “Parakeet Auklet” is but can imagine it when described in language by saying that “Parakeet Auklet is a bird that has an orange bill, dark above and white below.”. If we give this description to an average person, he will be able to select the relevant bird among other different birds, due to our capability to imagine the “Parakeet Auklet” class from the language description. I will cover in the presentation how to develop this capability powered by generative models. Imagine to Create: Creative AI has a high potential to speed up our rate of generating creative products like paintings, music, animations, etc. as a source of inspiration. I have worked on modeling Creative AI to produce art (ICCC17) and fashion. Our work on both art and fashion grabbed attention from the scientific community, media, and industry. One of the exciting results we achieved recently is that our AI fashion model was able to create new pants with additional arm sleeves (non-existing in the dataset). The surprising aspect of this design is that professional fashion designers found it inspirational for designing new pants, showing how creativity may impact the fashion industry. Our work has been featured by the new scientist magazine, the Facebook F8 conference. Our work also received the best paper award at ECCV18 workshop on fashion and art. At the end, I will show that these Creative AI techniques for creating a likable unseen circle back to benefit understanding an unseen (zero-shot learning) in our very recent work .

Short bio: Dr. Mohamed Elhoseiny is Assistant Professor of Computer Science at the Visual Computing Center at KAUST (King Abdullah University of Science and Technology) and an AI Research consultant at Baidu Research, Silicon Valley AI Lab. He received his PhD from Rutgers university under Prof. Ahmed Elgammal in October 2016 then spent more than two years at Facebook AI Research(FAIR) until January 2019 as a Postdoc Researcher. His primary research interests are in computer vision and especially about learning about the unseen or the least unseen by recognition (e.g., zero-shot learning) or by generation (creative art and fashion generation). Under the umbrella of how AI may benefit biodiversity, Dr. Elhoseiny's 6-years long development of the zero-shot task on major vision conferences was featured in the United Nations biodiversity conference in November 2018 (~10,000 audience from >192 countries). His creative AI research projects were recognized at the ECCV18 workshop on Fashion and Art with the best paper award, media coverage at the New Scientist Magazine and MIT Tech review (2017, 2018), 20 min speech at the Facebook F8 conference (2018), and coverage at HBO Silicon Valley TV Series (2018), and the official FAIR video (2018).​"