VISion Understanding and Machine intelligence – VISUM 2018 was the sixth edition of the Summer School organized by INESC TEC, in the scope of Nanostima project, 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.
Considering the existing gap between the most fundamental concepts of computer vision and their application in real world scenarios, the realisation of visum school seeks to bridge these two key domains. By creating an expert multicultural environment, VISUM school aims to foster junior researchers’ awareness of computer vision topics, as well as to enhance all attendees’ knowledge regarding the state of the art, provided by leading international experts on the field. Being an area of great potential in industrial applications with a strong increase in the number of researchers in these last years, visum school will be an incredible opportunity to be on the edge of knowledge.
What they say about VISUM summer school…
VISUM will comprise three main tracks: fundamental, industrial and application topics, each one with extensive practical “hands-on” sessions. A poster session will be organized especially dedicated, but not exclusive, to Ph.D. candidates. With this, researchers can discuss their current research works, possibly leading to significant breakthroughs in the development of their theses. In the industrial track, national and international renowned institutions will present their case studies and knowingness to the attendees. VISUM will have a track dedicated to applications with the aim to bridge the gap between the fundamental and industrial topics, each year with a different subject.
:: Target Audience ::
- MSc. and Ph.D. 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 .
Machine Learning and Computer Vision
Faculdade de Engenharia, Universidade do Porto/INESC TEC
Jaime dos Santos Cardoso is an Associate Professor with Habilitation/Professor Associado com Agregação at DEEC, in the Faculdade de Engenharia da Universidade do Porto (FEUP), Portugal.
Simultaneously, he is also involved in research and development activities at INESC TEC as Leader of the Information Processing and Pattern Recognition Area.
At INESC TEC, he is the co-founder and co-leader of the Breast Research Group and of the Visual Computing and Machine Intelligence Group. At VCMI they focus their research on computer vision and pattern recognition.
Björn W. Schuller
University of Augsburg
Imperial College London
Prof. Dr. Björn W. Schuller is a Full Professor and Chair of Embedded Intelligence for Health Care and Wellbeing at the University of Augsburg/Germany, Reader (Associate Professor) at Imperial College London/UK, CEO of audEERING GmbH – an Audio Intelligence company based in the Starnberg five lake site area – Germany, and permanent Visiting Professor at Harbin Institute of Technology/China.
Previously, he was Chair of Complex and Intelligent Systems and Chair of Sensor Systems at the University of Passau/Germany, Adjunct Teaching Professor and Head of the Machine Intelligence and Signal Processing Group at Technical University of Munich/Germany, besides multiple further stations of his career such as at the National Center for Scientific Research (CNRS) near Paris/France, Joanneum Research in Graz/Austria, or the University of Geneva/Switzerland.
He published five books, more than 100 journal articles and more than 500 further scientific publications leading to more than 16000 citations (h-index equals 63). He is the Editor in Chief of the IEEE Transactions on Affective Computing, General Chair of IEEE ACII 2019, and Program Chair of Interspeech 2019 besides a multitude of further commitment to the community.
The World Economic Forum honoured him as one of 40 outstanding scientists under 40 in 2015 and 2016. In 2017 his company won the Digital Marketing Innovation World Cup. He is a PI in more than 10 European Projects and consults global enterprises such as Huawei or Samsung.
Carnegie Mellon University
Ruslan Salakhutdinov is a UPMC Professor of Computer Science in the Department of Machine Learning at CMU. He received his PhD in computer science from the University of Toronto in 2009. After spending two post-doctoral years at the Massachusetts Institute of Technology Artificial Intelligence Lab, he joined the University of Toronto as an Assistant Professor in the Departments of Statistics and Computer Science. In 2016 he joined CMU.
Ruslan’s primary interests lie in deep learning, machine learning, and large-scale optimization. He is an action editor of the Journal of Machine Learning Research and served on the senior programme committee of several top-tier learning conferences including NIPS and ICML. He has authored/co-authored over 100 research papers and his work has received over 30,000 citations according to Google Scholar. He is an Alfred P. Sloan Research Fellow, Microsoft Research Faculty Fellow, Canada Research Chair in Statistical Machine Learning, a recipient of the Early Researcher Award, Google Faculty Award, Nvidia’s Pioneers of AI award, and is a Senior Fellow of the Canadian Institute for Advanced Research.
Statistical Shape Modelling
University of Sheffield
Alejandro Frangi obtained his undergraduate degree in Telecommunications Engineering from the Technical University of Catalonia (Barcelona) in 1996. Then he carried out research on electrical impedance tomography for image reconstruction and noise characterization at the same institution under a CIRIT grant. In 1997, he obtained a grant from the Dutch Ministry of Economic Affairs to pursue his PhD in Medicine at the Image Sciences Institute of the University Medical Center Utrecht on model-based cardiovascular image analysis. During this period, he was visiting researcher at the Imperial College in London, UK, and in Philips Medical Systems BV, The Netherlands. Currently, he is Professor of Biomedical Image Computing at the University of Sheffield (USFD), Sheffield, UK. He leads the CISTIB (Center for Computational Imaging and Simulation Technologies in Biomedicine) and is the Academic Coordinator of the MSc Bioengineering: Imaging and Sensing programme in Sheffield.
Professor Frangi has main research interests lay at the crossroad of medical image analysis and modeling with emphasis on machine learning (phenomenological models) and computational physiology (mechanistic models). He has particular interest in statistical methods applied to population imaging and in silico clinical trials. His highly interdisciplinary work has been translated to the areas of cardiovascular, musculoskeletal and neuro sciences. Prof Frangi has edited several books, published 7 editorial articles and over 190 journal papers in key international journals of his research field and more than over 200 book chapters and international conference papers with an h-index 51 and ca. 18,200+ citations according to Google-Scholar. He has been three times Guest Editor of special issues of IEEE Trans Med Imaging, one on IEEE Trans Biomed Eng, and one of Medical Image Analysis journal. He was chair of the 3rd International Conference on Functional Imaging and Modelling of the Heart (FIMH05) held in Barcelona in June 2005, Publications Chair of the IEEE International Symposium in Biomedical Imaging (ISBI 2006), Programme Committee Member of various editions of the Intl Conf on Medical Image Computing and Computer Assisted Interventions (MICCAI) (Brisbane, AU, 2007; Beijing CN, 2010; Toronto CA 2011; Nice FR 2012; Nagoya JP 2013), International Liaison of ISBI 2009, Tutorials Co-Chair of MICCAI 2010, and Program Co-chair of MICCAI 2015. He was also General Chair for ISBI 2012 held in Barcelona. He is the General Chair of MICCAI 2018 to be held in Granada, Spain.
Under his leadership, CISTIB develops GIMIAS (Graphical Interface for Medical Image Analysis and Simulation), an open-source platform for rapidly developing pre-commercial software prototypes in the areas of image computing and image-based computational physiology modelling. The research and development conducted in his research group led to two spin-off companies: Clintelis SA in 2009 and GalgoMedical in 2013.
Human Behaviour Analysis
University of Nottingham
Michel Valstar is an associate professor at the University of Nottingham and member of both the Computer Vision and Mixed Reality Labs. He received his masters’ degree in Electrical Engineering at Delft University of Technology in 2005 and his PhD in computer science at Imperial College London in 2008, and he was a Visiting Researcher at MIT’s Media Lab. He works in the fields of computer vision and pattern recognition, where his main interest is in automatic recognition of human behaviour, specialising in the analysis of facial expressions.
He is the founder of the facial expression recognition challenges (FERA 2011/2015/2017), and the Audio-Visual Emotion recognition Challenge series (AVEC 2011-2017). He is the coordinator of the EU Horizon2020 project ARIA-VALUSPA , which will build the next generation virtual humans, deputy director of the 6M£ Biomedical Research Centre’s Mental Health and Technology theme, and recipient of Melinda & Bill Gates Foundation funding to help premature babies survive in the developing world, which won the FG 2017 best paper award.
His work has received popular press coverage in, among others, Science Magazine, The Guardian, New Scientist and on BBC Radio. He has published over 50 peer-reviewed papers at venues including PAMI, CVPR, ICCV, SMC-Cybernetics, and Transactions on Affective Computing (h-index 33, >6000 citations).
Currently the CEO/CTO of Mint Labs (co-founder), Paulo Rodrigues graduated from Software Engineering Department of the University of Minho, Portugal in 2004 and obtained his PhD in Medical Visualization and Image Processing from the Eindhoven University of Technology, Netherlands, in 2011. During his PhD, Paulo researched new technologies for the cross sectional imaging of the brain. He worked in several international IT companies, first, at an innovative mobile development company called MobiComp, in Portugal; then, in The Netherlands, at Quintiq, a company specialized in advanced planning and scheduling solutions. Afterwards, he became an associate researcher in the Faculty of Psychology at the University of Barcelona’s Individual Differences Lab specializing in neuroimaging techniques, executing social psychology experiments and neuroimaging. At the same time, he was working for Event-Lab, a laboratory that creates virtual environments for neuroscience and technology for social psychology and neuroscience experiments. Together with Vesna Prchkovska, Paulo co-founded QMENTA (formerly called Mint Labs) in 2013.
“Our aim is to help to make brain diseases a thing of the past, by bringing together neuroimaging, AI, and cloud computing into the hands of the experts.”
by Dr. John R. Smith, USA
ABOUT IBM Research AI
IBM Research has been exploring artificial intelligence and machine learning technologies and techniques for decades. They believe AI will transform the world in dramatic ways in the coming years – and they’re advancing the field through our portfolio of research focused on three areas: AI Science, AI Engineering, and AI Tech. They’re also working to accelerate AI research through collaboration with like-minded institutions and individuals to push the boundaries of AI faster – for the benefit of industry and society.
ABOUT Dr. John R. Smith
Dr. John R. Smith is IBM Fellow and Head of AI Tech for IBM Research AI at IBM T. J. Watson Research Center. He leads IBM’s Research & Development on vision, speech, language, knowledge and interaction in Yorktown Heights, NY USA. Recent work includes IBM Watson Visual Recognition, Automatic Sports Video Highlights Detection, Augmented Creativity for Filmmaking, and Skin Cancer Image Analysis and Detection. Dr. Smith served as co-General Chair of ACM International Conference on Multimedia Retrieval (ICMR-2016). He was Editor-in-Chief of IEEE Multimedia from 2010 – 2014. Dr. Smith is a Fellow of IEEE.
by Jochen Wingbermühle, PT
ABOUT Bosch Car Multimedia
Bosch Car Multimedia develops smart integration solutions for entertainment, navigation, telematics and driver assistance functions used in the original equipment business. The needs of the driver are always at the focus of all research and development activities to create technologies that enhance safety and driving convenience and at the same time reduce energy consumption.
Information, communication and entertainment in the vehicle environment play an integral role in automotive development. How the vehicle and driver interact with one another and by what means are decisive factors. Bosch Car Multimedia develops cutting-edge features tailored to modern mobility requirements, providing optimum driving convenience, safety, and access to entertainment and information via smart networked architectures. Solutions from Bosch are specifically designed to reduce driver distraction through their implementation of user-centric interface concepts.
In the near future, vehicles will also be connected to the cloud. Connected Horizon, a Car Multimedia solution, will aggregate data from all connected vehicles to provide enhanced navigation with real-time traffic and weather data as well as anticipatory powertrain control to reduce energy consumption.
by Thierry Keller, ES
Key challenges for society and the economy can turn into business opportunities for your company. Based on those needs, at TECNALIA, we work to generate differential margins and success for your business which are translated into higher quality of life for people, progress and well-being for society at large. These challenges and opportunities are related to Advanced Manufacturing, Low-carbon Energy, Health and Ageing, Digital and Hyperconnected World, Urban Habitat, Climate Change and Lack of Resources and, in short, anything related to the economical and social development.
ABOUT Thierry Keller
Thierry Keller received his Dipl. Ing. degree in Electrical Engineering (M.Sc.E.E.) and his Doctorate (Dr. sc. Techn.) from the ETH Zurich, Switzerland in 1995 and 2001, respectively.
Currently, Dr. Keller is the head of the Neurorehabilitation Department at Tecnalia, the largest private research center in Spain. Main activities of the Neurorehabilitation Department are research & innovation of novel enabling technologies for rehabilitation robotics, tele-rehabilitation, technologies for physical and cognitive prevention, and FES technologies including neuroprostheses.
Dr. Keller is principal investigator in national and international projects and chaired the EU COST action TD1006: European Network on Robotics for Neurorehabilitation. He developed various neuroprostheses that help improve walking and grasp functions in spinal cord injured and stroke subjects. His research interests are in the fields of rehabilitation engineering and robotics, neural prostheses, signal processing and human-machine interaction.
Dr. Keller is the President of the International Functional Electrical Stimulation Society (IFESS), and steering committee member of the International Industry Society in Advanced Rehabilitation Technologies (IISART). Since 2015 he chairs the umbrella society ‘International Consortium for Rehabilitation Technologies (ICRT)’, which associates IISART, IFESS, ICORR and ICVR with the aim to organize joint conferences under the label Rehabweek.
by Manuel João Ferreira, PT
NEADVANCE is a technological based company working in the development of innovative solutions on artificial vision and machine vision. Started in 2001, based in Braga, grows in a consistent way due to a forward-thinking and innovation oriented attitude and high level of dedication to clients. It offers a highly trained professional with large experience team, aiming to answer to any challenge. The company is ISO 9001:2008 certified, thus fostering high level of quality control in order to assure the more economic and innovative solutions.
ABOUT Manuel João Ferreira
Manuel J. Ferreira received the B.Sc. degree in electronics and telecommunications from the University of Aveiro, Aveiro, Portugal, in 1992, and the M.Sc. degree in industrial informatics and the Ph.D. degree in industrial electronics from the University of Minho, Guimarães, Portugal, in 1996 and 2004, respectively. Between 1992 and 1999 he was a researcher at INESC Porto and Professor at the Universidade Lusíada. In this period he developed his Master thesis resulting in a system installed in four different countries (Portugal, Spain, Brazil and Australia) in several companies. From 1999 and 2001 was the technical coordinator of the computer vision area at IDITE-Minho research Institute. Since 2001 until 2012 he was Professor in the Industrial Electronics Department, University of Minho, mainly teaching in the fields of image and signal processing, and working with several companies helping them to specify and develop a large number of computer vision solutions for different industrial sectors, such as: plastic, textile, leather, automotive, beverage, agro-food, robotics and multimedia. From 2008 to 2012 was the coordinator of the computer vision group of CCG research institute. From 2012 to 2017 was the R&D coordinator at ENERMETER for the computer vision issues. Currently he is the head of Research, Development & Innovation department at NEADVANCE. His main research interests include image processing, image analysis and artificial intelligence. Since 1992 he has been working mainly on the development of computer vision and machine learning technologies based on advanced algorithms, applied to industrial applications and medical imaging.
by André Lourenço, PT
CardioID Technologies is a spin-off company of Instituto Superior Técnico and Instituto de Telecomunicações (IT) that started in 2014, after several years of research at IT, within a research group under the supervision of Prof. Ana Fred. The main focus of this group was the area of Physiological Computing, especially regarding the development of signal processing and pattern recognition methods for the automatic analysis of biosignals such as the electrocardiogram (ECG), electrodermal activity (EDA), electromyogram (EMG), and electroencephalogram (EEG).
CardioID Technologies was launched with the goal of exploiting the use of the ECG for identity recognition, as well as other innovative applications built around this signal. The automotive vertical was the first focus, and CardioWheel the first product – a steering wheel cover that acquires in an non-intrusive way the ECG of the driver, and triggers alerts of driver-change and drowsiness. The integration with other advanced driver assisting systems (ADAS), as Mobileye and Geotab is allowing to monitor the driver, and the driving behaviour in an innovative way.
ABOUT André Lourenço
André Lourenço holds a Licenciatura (2001), a MSc (2002), and a PhD in Electrotechnical and Computers Engineering (2014), all from Instituto Superior Técnico (IST), Universidade de Lisboa. After a brief period in the industry, working on IT projects at WeDo Consulting (2001) and on instrumentation and testing at Lusospace (2003-2005), Lourenço has developed his work on the academia, and on the scientific transfer of academic research to industry. Since 2002, he lecturers at Instituto Superior de Engenharia de Lisboa (ISEL) and collaborates as a researcher at Instituto de Telecomunicações (IT), focused on signal processing and programming. Lourenço’s speciality is pattern recognition, beginning with clustering algorithms and applications during his doctoral studies. Currently, he is CEO and one of the founders of CardioID Technologies, a Portuguese company that works with sensors, electronics, signal processing, and machine learning for biometrics and health monitoring applications, mainly using physiological signals acquired in unobtrusive and seamless ways in challenging settings, such as vehicles.
by Pedro Costa, PT
Created in 2012, Abyssal SA has been developing and implementing a set of products and solutions applied to a wide range of subsea offshore industries such as Oil and Gas, Marine Renewables, Deepsea mining, Aquaculture and Fishing, and Marine Research.
With a continuous investment in R&D, close relationships with Offshore Industry users and driven by the motivation to address the main challenges that the extreme and complex subsea environments present to the offshore operations, Abyssal has developed specific solutions focused on increasing visibility and spatial awareness.
The company commercializes subsea navigation and visualization systems for Remotely Operated Vehicles (ROVs) by combining 3D real time visualization with Augmented Reality and accurate navigation and positioning data for a more efficient and safe subsea operation.
In 2015, Abyssal has been named one of the top 10 technology startups in the Oil and Gas industry at the GE/Chevron Innovation Day, in 2016 it was selected as one of the 5 startups to present at the Energy Fest and in 2017 was invited by the European Commissioner Carlos Moedas to present at the “A New Era of Blue Enlightenment”, The Connected Atlantic Ocean: Riding the Next Wave of Ocean Technology and Innovation.
ABOUT Pedro Costa
Pedro Costa holds a MSc (2015) in Informatics and Computing Engineering at the Faculty of Engineering, University of Porto. Costa started working with INESC TEC in 2014 trying to find adverse drug reactions in biological data using Machine Learning. After a brief experience in the industry, Costa came back to INESC TEC to work on medical image processing using Deep Learning methods, having published in a top medical imaging journal. He then spent three months working on weakly supervised deep learning methods at Carnegie Mellon University (CMU). Currently, he is Head of Research at Abyssal, working on how to improve Remotely Operated Vehicles’ operational efficiency using Machine Learning and Computer Vision techniques. He is also a researcher at INESC TEC and keeps cooperating with CMU on several projects.
During the hands-on sessions of this VISUM 2018 edition, the students were gathered in groups to develop a project covering the subjects of VISUM, encouraging the students to put what they have learned in the theoretical classes into practice. The topic of this edition was the detection of keypoints on images of female breast torso. The organization provided two baseline solutions 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 two industry invitees and the project staff.
The winner group (awarded with a prize money of 1200 €) was “The Scientific Turtles”, formed by:
- Claúdio Sá, INESC TEC, Porto, Portugal
- Márcia Oliveira, Skim Technologies, London, UK
- João Portela, Abyssal, Porto, Portugal
- José Santos, Abyssal, Porto, Portugal
|Ana Rebelo||INESC TEC|
|Hélder Oliveira||FCUP | INESC TEC|
|Inês Domingues||CISUC | IPO PORTO|
|Jaime Cardoso||FEUP | INESC TEC|
|Luis F. Teixeira||FEUP | INESC TEC|
|Pedro Ferreira||INESC TEC | FEUP|
|Sara Oliveira||INESC TEC | FEUP|
|Diogo Pernes||INESC TEC | FCUP|
|Eduardo Meca||INESC TEC|
|Ricardo Cruz||INESC TEC | FCUP|
|Renata Rodrigues||INESC TEC|
|Wilson Silva||INESC TEC | FEUP|