Deep Learning Methods for Human Posture Estimation
Ioannis Pitas, Aristotle University of Thessaloniki, Greece
“Deep Internal Learning”: Deep Learning and Visual Inference without Prior Examples
Michal Irani, Weizmann Institute of Science, Israel
Ethical Creation of Ethical Data
João Freitas, PagerDuty, Portugal
Deep Learning Methods for Human Posture Estimation
Ioannis Pitas
Aristotle University of Thessaloniki
Greece
http://poseidon.csd.auth.gr
![]()
Brief Bio
Prof. Ioannis Pitas (IEEE fellow, IEEE Distinguished Lecturer, EURASIP fellow) received the Diploma and PhD degree in Electrical Engineering, both from the Aristotle University of Thessaloniki (AUTH), Greece. Since 1994, he has been a Professor at the Department of Informatics of AUTH and Director of the Artificial Intelligence and Information Analysis (AIIA) lab. He served as a Visiting Professor at several Universities.His current interests are in the areas of computer vision, machine learning, autonomous systems, intelligent digital media, image/video processing, human-centred computing, affective computing, 3D imaging and biomedical imaging. He has published over 920 papers, contributed in 45 books in his areas of interest and edited or (co-)authored another 11 books. He has also been member of the program committee of many scientific conferences and workshops. In the past he served as Associate Editor or co-Editor of 13 international journals and General or Technical Chair of 5 international conferences. He delivered 98 keynote/invited speeches worldwide. He co-organized 33 conferences and participated in technical committees of 291 conferences. He participated in 71 R&D projects, primarily funded by the European Union and is/was principal investigator in 43 such projects. Prof. Pitas lead the big European H2020 R&D project MULTIDRONE: https://multidrone.eu/. He is AUTH principal investigator in H2020 R&D projects Aerial Core and AI4Media. He was chair and initiator of the Autonomous Systems Initiative https://ieeeasi.signalprocessingsociety.org/. He is chair of the International AI Doctoral Academy (AIDA) https://www.i-aida.org/ and is PI in Horizon2020 EU funded R&D projects AI4Media (1 of the 4 AI flagship projects in Europe) and AerialCore. He has 34400+ citations to his work and h-index 87+.
Abstract
Human posture estimation, also referred as human pose estimation, is a well-researched computer vision topic due to its importance in a large number of application areas, such as monitoring, surveillance, human-robot interaction, etc.. 2D/3D human posture estimation typically entails estimating the 2D pixel/3D world coordinates of a predefined set of human body joints given an input image, while other body posture representations (body parts, 3D angles, etc.) have also been used in the literature. Deep Convolutional Neural Networks (CNNs) are an effective algorithmic approach to this end that has achieved remarkable results. A great application area is human-robot collaboration, e.g, for ensuring safety, by enabling robots to autonomously maintain a safe distance from humans.
“Deep Internal Learning”: Deep Learning and Visual Inference without Prior Examples
Michal Irani
Weizmann Institute of Science
Israel
Brief Bio
Michal Irani is a Professor at the Weizmann Institute of Science, Israel, in the Department of Computer Science and Applied Mathematics. She received a B.Sc. degree in Mathematics and Computer Science from the Hebrew University of Jerusalem, and M.Sc. and Ph.D. degrees in Computer Science from the same institution. During 1993-1996 she was a member of the Vision Technologies Laboratory at the Sarnoff Research Center (Princeton). She joined the Weizmann Institute in 1997. Michal's research interests center around Computer-Vision, Image-Processing, Artificial-Intelligence and Video information analysis. Michal's prizes and honors include the David Sarnoff Research Center Technical Achievement Award (1994), the Yigal Alon three-year Fellowship for Outstanding Young Scientists (1998), the Morris L. Levinson Prize in Mathematics (2003), the Maria Petrou Prize (awarded by the IAPR) for outstanding contributions to the fields of Computer Vision and Pattern Recognition (2016), the Landau Prize in Artificial Intelligence (2019), and the Rothschild Prize in Mathematics and Computer Science (2020). She received the ECCV Best Paper Award in 2000 and in 2002, and was awarded the Honorable Mention for the Marr Prize in 2001 and in 2005. In 2017 Michal received the Helmholtz Prize – the “Test of Time Award” (for the paper “Actions as space-time shapes”).
Abstract
In this talk I will show how Deep-Learning can be performed without any prior examples, by training on a single image – the test image alone. The strong recurrence of information inside a single natural image provides powerful internal examples which suffice for self-supervision of Deep-Networks, thus giving rise to true “Zero-Shot Learning”. I will show the power of this approach to a variety of problems, including: super-resolution (in space and in time), image-segmentation, transparent layer separation, image-dehazing, and more.
I will further show how self-supervision can be used also for “Mind-Reading” (recovering observed visual information from fMRI brain recordings), when only few fMRI training examples are available.
Ethical Creation of Ethical Data
João Freitas
PagerDuty
Portugal
Brief Bio
João Freitas is General Manager and Engineering Site Lead at Pager Duty. João is the main representative of the Lisbon office and is responsible for its growth, expansion, and culture. With more than 16 years of experience in Software Development, Machine Learning, and as a People Manager, he was previously CTO at a startup in the area of Artificial Intelligence and has taken several roles at Microsoft in the areas of Speech Technologies and Big Data. João also holds a PhD in the areas of speech technology and human-computer interaction and filed several patents and published over 40 articles in peer-reviewed international conferences and journals. He is also the author and co-author of book chapters and one book.
Abstract
Artificial Intelligence (AI) has become ubiquitous and we, as a society, have become AI consumers. Today the debate around AI in terms of its definition, risks, economic impact, and safety is more lively than ever. As technology and products become more mature, companies are starting to realize the need for investing in more responsible and transparent AI systems. We've also observed in the last years a change from a mode-centric approach, to a data-centric view, where the emphasis is placed on the quality of the data. However, ethical, fair, unbiased data comes at a cost. And, on our road to data democratization, we cannot forget about these sustainability pillars for AI systems. In this keynote, we will talk about the challenges in the creation of ethical, fair, and unbiased datasets and the importance of having an ethical data stamp that guarantees that we leave no one out.