Tutorials
The role of the tutorials is to provide a platform for a more intensive scientific exchange amongst researchers interested in a particular topic and as a meeting point for the community. Tutorials complement the depth-oriented technical sessions by providing participants with broad overviews of emerging fields. A tutorial can be scheduled for 1.5 or 3 hours.
TUTORIALS LIST
Visual Intelligence in Egocentric (First-Person) Vision Systems (VISIGRAPP)
Instructor : Giovanni Maria Farinella
Understanding Human Motion Primitives (VISIGRAPP)
Instructor : Nicoletta Noceti and Francesco Rea
Visual Intelligence in Egocentric (First-Person) Vision Systems
Instructor
|
Giovanni Maria Farinella
Università di Catania
Italy
|
|
|
|
Brief Bio
Giovanni Maria Farinella obtained the degree in Computer Science (egregia cum laude) from the University of Catania, Italy, in 2004. He is Founder Member of the IPLAB Research Group at University of Catania since 2005. He was awarded a Doctor of Philosophy (Computer Vision) from the University of Catania in 2008. He is currently a Full Professor at the Department of Mathematics and Computer Science, University of Catania, Italy. His research interests lie in the fields of Computer Vision, Pattern Recognition and Machine Learning, with focus on First Person (Egocentric) Vision. He is Associate Editor of the international journals IEEE Transactions on Pattern Analysis and Machine Intelligence, Pattern Recognition - Elsevier and IET Computer Vision. He has been serving as Area Chair for CVPR 2020/21/22, ICCV 2017/19/21, ECCV 2020, BMVC 2020, WACV 2019, ICPR 2018, and as Program Chair of ECCV 2022, ICIAP 2021 and VISAPP 2019/20/21/22/23. Giovanni Maria Farinella founded (in 2006) and currently directs the International Computer Vision Summer School. He also founded (in 2014) and currently directs the Medical Imaging Summer School. He is member of the European Laboratory for Learning and Intelligent Systems (ELLIS), Senior Member of the IEEE Computer Society, Scientific Advisor of the NVIDIA AI Technology Centre (NVAITC), and board member of the CINI Laboratory of Artificial Intelligence and Intelligent Systems (lead of the area AI for Industry - since 2021). He was awarded the PAMI Mark Everingham Prize 2017. In addition to academic work, Giovanni's industrial experience includes scientific advisorship to different national and international companies and startups, as well as the leadership as Founder and Chief Scientific Officer of Next Vision - Spinoff of the University of Catania.
|
Abstract
Egocentric (First-Person) Vision paradigm allows to seamlessly acquire images of the world from the perspective of the agent (person, robot, etc) moving in an environment. Given their intrinsic mobility and the ability to acquire agent-related information, those systems have to deal with a continuously evolving environment. The challenge is to provide these systems an effective and robust Visual Intelligence. This tutorial will give an overview of the advances in the field. Challenges, applications and algorithms will be discussed by considering the past and recent literature.
Keywords
Visual Intelligence, Egocentric Vision, First Person Vision, Wearable Vision
Aims and Learning Objectives
The objective of this tutorial to provide an overview of the latest advances of Computer Vision also considering challenges and applications in the context of Egocentric (First-Person) Vision. The attendees will become familiar with current and future devices and computer vision technologies, as well as with the current state-of-the-art algorithms.
Target Audience
This course is intended for those with a general computing background, and with interest in the topic of image processing, computer vision and machine learning. Ph. D. students, post-docs, young researchers (both academic and industrial), senior researchers (both academic and industrial) or academic/industrial professionals will benefit from the general overview and the introduction of the most recent advances of the field.
Prerequisite Knowledge of Audience
Basic knowledge in the fields of Image Processing, Computer Vision, Machine Learning
Detailed Outline
- Introduction and Motivation
- Open Challenges
- State-of-the-Art Algorithms
- Applications and Opportunities
Understanding Human Motion Primitives
Instructors
|
Nicoletta Noceti
Università di Genova
Italy
|
|
|
|
Brief Bio
Nicoletta Noceti received the Laurea cum laude (2006) and the PhD in Computer Science (2010) from the University of Genova. In 2008, she visited the IDIAP Institute (Switzerland). Since 01/2010 she is a research associate at DIBRIS, University of Genova. Her research activity is mainly focused on the design and development of visual computational models that combine Computer Vision and Machine Learning for the general goal of scene understanding from images or videos. The reference fields of her work include artificial vision modelling and image processing, within the application areas of Human-Machine Interaction and Natural User Interfaces, video-surveillance and activity monitoring. Both theoretical and practical aspects are key elements of her research. She authored more than 50 publications, and she participated to various national and international research projects (e.g. EU projects SAFEPOST and Healh-e-Child), and technology transfer and development projects with SMEs and large companies. She collaborates with universities, research institutes and hospitals. She recently organised the workshop “Vision and the development of social cognition” held in conjunction with the Sixth Joint IEEE International Conference on Developmental Learning and Epigenetic Robotics (ICDL-EPIROB 2016, Cergy-Pontoise, September 19th) and the One-Day BMVA Meeting “Vision for interaction: from humans to robots” (London, October 19th). She is currently guest editor of the special issue “A sense of interaction in humans and robots: from visual perception to social cognition” for the IEEE Transactions on Cognitive and Developmental Systems.
|
|
Francesco Rea
Istituto Italiano di Tecnologia
Italy
|
|
|
|
Brief Bio
Francesco Rea graduated in B.SC. Information Engineering at the Universita di Bergamo in 2004 and specialized in Computer Engineering at the Universita di Bergamo in 2007. He got a M.Sc. degree in Robotics and Automation at the University of Salford, Greater Manchester University UK in 2008 and a Ph.D degree in Robotics at the University of Genoa in 2012 contributing to different EU project (POETICON, eMorph) . He joined the Istituto Italiano di Tecnologia (IIT) in 2013 as fellow to support research on the perception and cognitive modeling and human-robot interaction in the EU project DARWIN. He is Post Doctoral fellow at the Istituto Italiano di Tecnologia (IIT) involved on a research program of study and dynamic simulation of human body under loads in collaboration with US Department of Defense (Natick, USA). His main areas of interest are modeling and replication of human and humanoid perception and cognitive skills, human-robot interaction and dynamic simulation of multibody systems.
|
Abstract
The segmentation of motion primitives is a key perceptual skill in humans. We use this information to identify atomic motion units and then to compose them for more complex understanding tasks, as recognising gestures, actions, and activities. The autonomous learning of such primitives is an important building block for artificial systems, that leverage low-level description to build higher-level motion representations, often used to feed a machine learning machinery to achieve the final recognition task. The aim of this tutorial is to provide a comprehensive account on this topic. We will start with the introduction of concepts proper of cognitive and neuro sciences, that may provide a guide in the design of motion segmentation strategies, reminiscent of the biological model. In the second part we will provide an overview of computational methods proposed in the literature to address motion segmentation, comparing strategies and discussing benefits and drawbacks. In the last part of the tutorial, we will discuss how to endow a robotic platform with such ability, thus enhancing the potential positive impact on the perceptual skills of the agent. We will show how this ability can be proficiently exploited to improve HRI tasks.
Keywords
Motion primitives; action recognition; robotics
Aims and Learning Objectives
The goal of this tutorial is to provide a comprehensive overview of advances in the fields of human motion understanding, with particular emphasis on the study of action units and how they can be exploited in robotics, both from a perception (action recognition) and action (action planning) point of view.
Target Audience
Phd students and researchers with some level of interest on motion understanding problems.
Prerequisite Knowledge of Audience
A (even coarse) background on robotics may be of benefit.
Detailed Outline
- Motivation and contexts
- Motion segmentation: guidelines
- Motion segmentation strategies: an overview
- Application to robotics problems