The Human Activity and Vision Summer School will address the broad domains of human activity modeling and human behavior recognition, with an emphasis on vision sensors as capturing modality. Courses will comprise both tutorials and presentations of state-of-the-art methods by active researchers in the field.

The goal of the courses will be to cover most of the whole human activity analysis chain, starting from the low level processing of videos and audio for detection and feature extraction, to medium level (tracking and behavior cue extraction) and higher level modeling and recognition using both supervised and unsupervised techniques. Applications of the different methods to action and activity recognition in different domains ranging from Activities of Daily Living to surveillance (individual behavior recognition, crowd monitoring) will be considered.

List of considered topics and methodologies:

• low-level feature extraction (background subtraction, space-time interest points, tracklets)
• object detection (human, body)
• tracking (multi-object, multi-camera, audio-visual)
• behavior cue extraction (body or head pose)
• crowd monitoring
• supervised behavior recognition (statistical and symbolic approaches)
• (temporal data mining, probabilistic topic models -Latent Dirichlet Allocation, Dirichlet Processes,…)
• active learning

Presentation of real uses cases, market needs, and current bottlenecks in the surveillance domain will also be addressed, with one half day devoted to presentations and panel discussions with professional and industrial presenters.

Human Activity and Vision Summer School

Human Activity and Vision Summer School

Human Activity and Vision Summer School

he course consists of five days (Mon-Friday) of lectures and exercises on key topics in machine learning. This years summer school will focus on several different advanced topics within machine learning. The course (2.5 ects point) is passed by handing in a small report on one of the topics covered in the course on deep learning. The exercises cover both theoretical, technical programming and application aspects. It will be up to the students to decide on what aspects to focus on in the report. Specific machine learning application examples are used throughout the entire week.

The school will address the following topics: Learning Theory, Kernel Methods, Bayesian Machine learning, Monte Carlo Methods , Bayesian Nonparametrics, Optimization, Graphical Models, Information theory and Dimensionality Reduction.

Machine Learning Summer School 2012

Machine Learning Summer School 2012

From securing your smartphone and automatic photo tagging to enabling automatic border control and identifying criminals in forensics, the technology has far-reaching implications in our society.

The School is a tutorial-style 4-day intensive training workshop that discusses the latest biometrics techniques with application to 2D/3D face recognition. In addition, some fundamental Machine Learning concepts will also be covered, such as metric learning, Bayesian classifier based on Gaussian Mixture Model, and deep neural network. This intensive four-day programme will cater for the diverse background of the following targeted participants: engineers, graduate and post-graduate students, academicians, and technologists as well as new-comers to the field. All topics presented will have hands-on exercises.

Biometric School (Winter Edition)

Biometric School (Winter Edition)

In addition to a broad-range of lectures on state-of-the-art Computer Vision techniques, it offers exciting sport activities, such as Floorball, Climbing, and Table Tennis.  What is most fun: the sports sessions are given by the same internationally renowned experts who deliver the lectures!

Organizers

• Vittorio Ferrari, ETH Zurich, Zurich, Switzerland
• Matthieu Guillaumin, ETH Zurich, Zurich, Switzerland
• Barbara Widmer, ETH Zurich, Zurich, Switzerland

Over 130 participants from all over the world attended. A majority of the participants were graduate students, but a number of undergraduates, post-doctoral fellows, and industry personnel also were in attendance.

The school featured a number of tutorial style lectures by international experts. The students were also exposed to various application areas of machine learning via short application overview talks. In addition to lectures, the participants got a chance to apply their knowledge during hands-on laboratory sessions. The school also featured a number of social events including a trip to Chicago and an end of school party. Women researchers got a unique opportunity to receive mentoring via a Women in MLSS dinner.

The use of observations to automatically improve the capabilities of programs has been a long standing challenge since the invention of the computer. Machine learning strives to achieve this goal using techniques from diverse areas such as computer science, engineering, mathematics, and statistics.

Rapid progress in machine learning has made it the method of choice for many applications in areas such as business intelligence, computational biology, computational finance, computer vision, information retrieval, natural language processing and other areas of science and engineering. The summer school aims to bring both the theory and practice of machine learning to research students, researchers as well as professionals who wish to understand and apply machine learning.

Participants will get the opportunity to interact with leading experts in the field and potentially form collaborations with other participants. It is suitable for those who wish to learn about the area as well as those who wish to broaden their expertise. For research students, the summer school provides an intensive period of study, appropriate for those doing research in machine learning or related application areas. For academics and researchers, the summer school provides an opportunity to learn about new techniques and network with others with similar interests. For professionals who use machine learning, this is an opportunity to learn the state of the art techniques from leading experts in the area.

The summer school is part of the machine learning summer school series started in 2002. It is co-organized by Institute for Infocomm Research, National Infocomm Australia (NICTA), National University of Singapore (NUS), and Pattern Analysis, Statistical Modelling and Computational Learning (PASCAL2) with generous support from the Air Force Office of Scientific Research, Asian Office of Aerospace Research and Development, Office of Naval Research Global, SAS and the Lee Foundation.

Organizers

• Wray Buntine (NICTA)
• Cuntai Guan (I²R)
• David Hardoon (SAS)
• Wee Sun Lee (National University of Singapore)
• John Shawe Taylor (PASCAL2)

The Ghana-India Kofi Annan Centre of Excellence in ICT (AITI-KACE) in collaboration with PASCAL and ACTIVE Knowledge Powered Enterprise hosted, from February 14-22, 2011 Ghana's first capacity transfer bootcamp in the areas of Machine Learning and ACTIVE (Advanced Technologies for Knowledge-Intensive Enterprises).

The bootcamp is an international event which consists of 10 days of intensive training (lectures, practical and lab sessions) designed for Masters level students, researchers and lecturers interested in upgrading their knowledge and skills in the areas of Machine Learning and ACTIVE. This workshop aims at developing participants scientific skills to enable them to collaborate on research in these areas. Similar bootcamps, sponsored by PASCAL were held in Europe with the most recent in Marseilles 2010.

Machine Learning is a foundational discipline of the Information Sciences. It combines deep theory from areas as diverse as Statistics, Mathematics, Engineering, and Information Technology with many practical and relevant real life applications. The aim of the summer school is to cover the entire spectrum from theory to practice. It is mainly targeted at research students, IT professionals, and academics from all over the world.

This school is suitable for all levels, both for people without previous knowledge in Machine Learning, and those wishing to broaden their expertise in this area. It will allow the participants to get in touch with international experts in this field. Exchange of students, joint publications and joint projects will result because of this collaboration.

For research students, the summer school provides a unique, high-quality, and intensive period of study. It is ideally suited for students currently pursuing, or intending to pursue, research in Machine Learning or related fields. Limited scholarships are available for students to cover accommodation and registration costs. If funds are available partial travel support might also be provided.

IT professionals who use Machine Learning will find that the summer school provides relevant knowledge and exposure to contemporary techniques. In addition, they will benefit by direct interaction with top-notch researchers and knowledge workers. Previous experience indicates that personnel from both the industry as well as national laboratories like CSIRO, DSTO benefit immensely from the school.

For academics, the summer school is an excellent opportunity to help getting started in research on novel topics in Machine Learning. It provides an ideal forum for networking and discussions. Academics will also benefit from interaction with IT professionals which will lead to a deeper understanding of real life problems.

Organizers

This Summer School is organized by the School of Computer Science of the Australian National University (CS@ANU) and the Statistical Machine Learning program of the National ICT Australia (SML@NICTA), jointly with support from the Max-Planck-Institute for Biological Cybernetics in Tübingen and the Pascal Netwok. Please visit www.mlss.cc for more information about the previous summer schools.

In addition to a broad-range of lectures on state-of-the-art Computer Vision techniques, it offers exciting sport activities, such as Ultimate Frisbee, Volleyball, and Table Tennis.

Organisers

Vittorio Ferrari, ETH Zurich, Zurich, Switzerland
Thomas Deselaers, ETH Zurich, Zurich, Switzerland
Barbara Widmer, ETH Zurich, Zurich, Switzerland