VISion Understanding and Machine intelligence – VISUM 2019 – was the seventh edition of a non-profit summer school that aimed to gather Ph.D. candidates, Post-Doctoral scholars and researchers from academia and industry with research interests in computer vision and machine intelligence.
VISUM 2019 as organized by INESC TEC, supported by Portucalense University Infante D. Henrique, ScaleUp Porto, Google Cloud Platform, Bosch, and Porto University, in partnership with Data Science Portugal and Future of Computing UPTEC summer school.
VISUM’19 Main Topics:
- Computer Vision & Machine Learning Basics
- Computer Vision with Deep Learning
- Deep Generative Models
- Visual Approaches for Robotic Control
- Optimization and Constraint Programming
Our arget Audience:
- MSc and PhD candidates
- Post-Doctoral scholars and researchers
- Academic and industrial professionals with (research) interests in computer vision
- And everyone who wants to have knowledge of avant-garde topics
Computer Vision & Machine Learning Basics
José Costa Pereira
Huawei Technologies Co., Ltd, London, United Kingdom
José Costa Pereira is a Research Scientist in the computer vision group at Huawei – Noah’s Ark Lab, after two years as a Research Scientist with INESC TEC. He is also an invited professor at the Computer Science Department in the School of Engineering, University of Porto (FEUP), Portugal.
He received his PhD degree, in 2015, from University of California, San Diego (USA), in Electrical and Computer Engineering. His research focus lies on Computer Vision, specifically on Statistical Signal Processing, Optimization, Machine Learning and Multimedia.
Computer Vision with Deep Learning
UVA, Amsterdam, Netherlands
Pascal Mettes is an Assistant Professor at the University of Amsterdam. He received his PhD in 2017 and was subsequently a postdoctoral researcher at the University of Amsterdam. In 2016, he was a visiting scientist at Columbia University, New York.
His research interests are in computer vision, with a focus on video understanding and learning from limited supervision.
Deep Generative Models
Dr. Mohamed Elhoseiny is an Assistant Professor of Computer Science at KAUST and a visiting faculty at Baidu Silicon Valley AI Lab. Dr. Elhoseiny has productively collaborated with several researchers at Facebook AI Research including Marcus Rohrbach, Yann LeCun, Devi Parikh, Dhruv Batra, Manohar Paluri, Marc’Aurelio Ranzato, Antoine Bordes, and Camille Couprie. He has also fruitfully teamed up with academic institutions including KULeuven (with Rahaf Aljundi and Tinne Tuytelaars), UC Berkeley (with Sayna Ebrahimi and Trevor Darrell), the University of Oxford (with Arslan Chaudry and Philip Torr), and the Technical University of Munich (with Shadi AlBarqouni and Nassir Navab). His primary research interests are in computer vision, the intersection between natural language and vision, computational creativity, and deep generative models.
Dr. Elhoseiny received his Ph.D. degree from Rutgers University, New Brunswick, in October 2016 under Prof. Ahmed Elgammal. His work has been widely recognized. In 2018, he received the best paper award for his work on creative fashion generation at ECCV workshop from Tamara Berg of UNC chapel hill and sponsored by IBM Research and JD AI Research. The work got also featured at the New Scientist Magazine and he co-presented it the Facebook F8 annual conference with Camille Couprie. His earlier work on creative art generation was featured by the New Scientist magazine and MIT technology review in 2017, HBO Silicon Valley TV Series ( season 5 episode 3) in 2018. His Creative AI art generation demo was featured/presented at the best of AI meeting 2017 at Disney (6000+ audience), Facebook’s booth at NeurIPS 2017, and the official FAIR video in June 2018. His work on life-long learning was covered at the MIT technology review in 2018. In Nov 2018 and based on his 5-year work on zero-shot learning, Dr. Elhoseiny made significant participation in the United Nations Biodiversity conference (~10,000 audience from >192 countries and tens of important organization) on how AI may benefit biodiversity which reflects in both disease management and climate change. Dr. Elhoseiny received the Doctoral Consortium award at CVPR 2016 and an NSF Fellowship for his Write-a-Classifier project in 2014.
Optimization and Constraint Programming
United Technologies Research Centre, Cork, Ireland
Deepak Mehta works in the United Technologies Research Centre (UTRC), Ireland. His work is focused on researching and developing solutions methods for combinatorial decision and optimisation problems arising in the domain of aerospace. Prior to joining UTRC, he was a senior research scientist in Insight Centre for Data Analytics (Cork Constraint Computation Centre). He received his PhD from University College of Cork in 2009 for his work on constraint programming.
Visual Approaches for Robotic Control
Berkeley Artificial Intelligence Research Lab, California, United States
Dinesh Jayaraman is a postdoc at the Berkeley Artificial Intelligence Research Lab, UC Berkeley, advised by Alyosha Efros and Sergey Levine. His work is focused on problems at the intersection of vision and robotics. In August 2017, he got his PhD at UT Austin, where he had been working with Kristen Grauman since Spring of 2013.
Before joining UT in Fall of 2011, he obtained a bachelor’s degree at Indian Institute of Technology Madras (IITM), Chennai, India, where he majored in electrical engineering and minored in literature.
Healthcare Imaging A.I., Medical Faculty of University of Bern, Bern, Switzerland
Prof. Dr. Mauricio Reyes is the head of Healthcare Imaging A.I. at the Medical Faculty of University of Bern, Switzerland. He has a bachelor degree from the University of Santiago de Chile, Chile in 2001 and his thesis, “Three-dimensional Reconstruction of a Human Embryo Hand Using Artificial Vision Techniques”, was awarded best Electrical Engineering bachelor thesis work. Later on, during 2002-2004, he conducted studies to obtain a Ph.D. degree in computer sciences from the University of Nice, France, on the topic of lung cancer imaging and breathing compensation in emission tomography, under the supervision of Prof. Dr. Grégoire Malandain, Asclepios research project (formerly known as Epidaure).
In 2006 he joined the Medical Image Analysis group at the MEM Research Center as a postdoctoral fellow focusing on topics related to medical image analysis and statistical shape models for orthopaedic research. In 2008, he took over the lead of the Medical Image Analysis group at the Institute for Surgical Technology and Biomechanics, Switzerland.
During the hands-on sessions of this VISUM 2019 edition, the students were gathered in groups to develop a project covering the subjects of VISUM, putting what they have learned in the theoretical classes into practice. The topic of this edition was the detection of objects inside a vehicle. The organization provided a baseline solution to the students, as well as acess to google cloud to all teams in order to run the developed algorithms.
The groups that achieved the best performances on the final submission were invited to present their ideas, evaluated by a panel formed by industry invitees and the project staff.
The winner group (awarded with 3 NVIDIA RTX 2080 DL training kits, given by Bosch Portugal) was team “Foobar”, formed by:
- Claúdio Sá, Twente University, The Netherlands
- Kemilly Dearo, Twente University, The Netherlands
- Lise Stork, Leiden University, The Netherlands
|Ana Rebelo||UPT | INESC TEC|
|Bruno Veloso||UPT | INESC TEC|
|Inês Domingues||CISUC | IPO PORTO|
|Hélder Oliveira||INESC TEC | FCUP|
|Sara Oliveira||INESC TEC | FCUP|
|Diogo Pernes||INESC TEC | FCUP|
|Eduardo Castro||INESC TEC|
|Jaime Cardoso||FEUP | INESC TEC|
|João Pinto||INESC TEC | FEUP|
|Ricardo Araújo||INESC TEC | FCUP|
|Wilson Silva||INESC TEC | FEUP|
|Renata Rodrigues||INESC TEC|
Industry Day Committe