Register for Pattern Recognition School Sept 2010

6th International Summer School and Workshop on Pattern Recognition (5-10 September, 2010)

Registration is now Open – take advantage of early registration fee

The International Summer School on Pattern Recognition is the premier event on research training in the area of pattern recognition and machine learning. The school is fully residential and its registration includes all attendance, and living costs. The vision of the summer school is to empower its participants with the state-of-the-art techniques in pattern recognition and machine learning – to provide a deep understanding of how techniques work, their strengths and limitations, and the future of things to come in this field.

If you have used or will use pattern recognition technology, this is a must attend event. You can:

– Learn from leading experts in pattern recognition and machine learning on a range of topics including statistical pattern recognition, Bayesian approaches, structural approaches, neural networks and support vector machines, data mining, classification, evolutionary computation, markov models, feature selection and reduction, and many more.

– Demonstrate your research till date and win best research prizes sponsored by Microsoft. The event is supported by Microsoft Research, Springer, and Mathworks.

– Meet some of the leading exponents in pattern recognition and machine learning area, network with your peers from around the world using similar tools to solve complex problems

– Enjoy a unique learning experience within a fully residential summer school, admired by previous participants as one of the best summer schools available

www.patternrecognitionschool.com

Email for enquiries: m.singh(at)lboro.ac.uk, or enquiries(at)patternrecognitionschool.com

Postdoc position in the Human Sensing Laboratory at Carnegie Mellon University

Human-observer based methods for measuring human motion are labor intensive qualitative, and difficult to standardize across laboratories, clinical settings, and over time. Moreover, many conditions that affect normal human movements are currently diagnosed during short visits to the clinician. Advances in wearable and wireless sensor networks have opened up new opportunities in health care systems. We are looking for a postdoc to develop novel machine learning algorithms able to perform medical diagnosis, temporal segmentation and activity recognition from accelerometer data. To qualify for the position, it is mandatory to have research experience in time series analysis. A proven record of publications in top machine learning conferences and journals is required. This will initially be a one year position with the possibility of an extension pending funding.

To apply: Applications should be sent by email to jkh(at)cs.cmu.edu and ftorre(at)cs.cmu.edu . It should include a CV, a brief statement of research interests, the expected date of availability and the names for 3 references. Applications should be sent as soon as possible and preferably before July 20th, 2010, but later applications may be considered until the position is filled.

ICPCA10 Call for Paper

The 5th International Conference on Pervasive Computing and Applications
(ICPCA 2010)
CALL FOR PAPERS
http://icpca.lzu.edu.cn/
Maribor, Slovenia December 1-3, 2010

The ICPCA steering committee cordially invites you to submit a paper to the 5th International Conference on Pervasive Computing and Applications, held in Maribor, Slovenia, between 1 and 3 December, 2010.

Sponsors:

* Microsoft

* HP

* SRA

* IEEE

Topics:

* Mobile and Wireless Networks and Communications

* Semantic technologies in Pervasive Computing

* Context-awareness

* Data Grid and Data Cloud

* Distributed data and knowledge management

* Distributed intelligence

* Innovative HCI Technologies

* Socio-technical Issues in Pervasive Computing

* Applications and case studies

ICPCA2010 extends its interests in pervasive computer with special tracks on collaborative work, health care, e-learning, emergency management, security, etc. In addition to technical papers, ICPCA2010 will include keynote speeches, penal discussions, late breaking results, and demonstrations.

Submission of Papers:

All papers must be unpublished and should not be under simultaneous review for any other conferences and workshops. Papers must be written in English and formatted according to the IEEE conference proceedings. Research papers should be no more than 6 pages including references and illustrations. Position papers and system demos are also welcome. Electronic submissions in PDF or PS format are recommended.

Important Dates:

* Technical paper

Deadline for submission 30/07/2010 (extended)

Notification of acceptance 15/09/2010

Camera-ready deadline 15/10/2010

* System demo/position paper/etc.

Deadline for submission 01/09/2010

Notification of acceptance 15/09/2010

Camera-ready deadline 15/10/2010

This conference is sponsored by IEEE Slovenia Section and Lanzhou University. All papers accepted will be indexed by EI. For more information, please contact us:

ICPCA Organising Committee

icpca10(AT)easychair.org

Gaussian Processes for Machine Learning Toolbox 3.0

We are delighted to announce an updated release of the GPML Toolbox.

The code as well as the documentation and a tutorial can be obtained from
http://www.gaussianprocess.org/gpml/code

The GPML toolbox implements approximate inference algorithms for
Gaussian processes such as Expectation Propagation, the Laplace
Approximation and Variational Bayes for a wide variety of likelihood
functions for both regression and classification. It comes with a large
algebra of covariance and mean functions allowing for flexible
modeling.

Requirements: octave 3.2.x or matlab 7.x
Platform: any, tested on: mac, linux and windows
License: FreeBSD

Carl Edward Rasmussen & Hannes Nickisch

Two Postdoc Positions in Statistical Machine Learning and Algorithmic Mechanism design at Xerox Research Centre Europe

The Machine Learning for Optimisation and Services group (MLS) at Xerox Research Centre Europe is expanding. We conduct fundamental research in statistical machine learning and algorithmic mechanism design, with applications to abstract knowledge representation, content creation, recommendation systems and dynamic pricing. Our research is the result of combining state-of-the-art expertise in computational linguistics, large-scale data mining, computational statistics and game theory.

We are currently looking for two very strong researchers in the following areas:

1. Statistical Machine Learning for Text Understanding and Multi-document Summarisation:

www.xrce.xerox.com/About-XRCE/Career-opportunities/Research-Scientist-in-Statistical-Machine-Learning-for-Text-Understanding-and-Multi-document-Summarisation

2. Statistical Machine Learning and Algorithmic Mechanism design:

www.xrce.xerox.com/About-XRCE/Career-opportunities/Research-Scientist-in-Machine-learning-and-Algorithmic-Mechanism-Design

Applicants will have to demonstrate their capacity to define and/or implement research plans, to carry out leading research through collaboration with Xerox researchers and also the wider academic community. As a researcher you will be expected to formalize challenging problems, develop new solutions, and work with business and development teams to ensure that these solutions have a significant impact. We work together with top academic partners and expect our researchers to publish results in top-tier conferences and journals.

Requirements:

– PhD in Statistics, Mathematics, Economics or Computer Science

– Strong publication record in top tier conferences and journals

– Evidence of implementing systems

– Strong English-language written and oral communications skills

The application deadline is August 15, 2010. Applications will be considered after this date until the positions are filled.

Informal inquiries can be made to Cedric.Archambeau(AT)xerox.com, Guillaume.Bouchard(ATxerox.com or Onno.Zoeter(AT)xerox.com. To submit an application, please send your CV and cover letter to both xrce-candidates(AT)xrce.xerox.com and the aforementioned email addresses. You should also include in your CV at least three referees we can contact for letters of recommendation.

PhD Position in Biomedical Data Analysis at the University of Basel, Switzerland

PhD Position in Biomedical Data Analysis at the University of Basel, Switzerland

Applications are invited for a PhD position in the Biomedical Data Analysis Group at
the Department of Computer Science of the University of Basel.
The open position is part of the research project “Emotional Memory in Health and
Disease” funded by the Swiss National Science Foundation.
This interdisciplinary research effort aims at identifying the molecular genetic basis of
emotional memory by combining experimental, clinical, and computational approaches.
The position involves development of computational methods for genome-wide
association studies, statistical analysis of gene interactions, computational modeling of
disease-related gene regulatory pathways, as well as data integration and human-mouse
comparative data analysis.

Successful applicants have a profound knowledge in mathematical modeling and in
algorithmics. Furthermore, the project requires substantial programming skills and a
genuine interest in computational biology. Candidates are expected to engage in
interdisciplinary research groups and to foster collaborations with clinicians and
biologists.
A prerequisite is a Masters degree in Computer Science, Bioinformatics, Mathematics or
Physics.

For further inquiries, please contact
Volker Roth, Email: volker.roth@unibas.ch, Phone: +41-61-2670549

Successful candidates will be awarded a fellowship with a competitive salary (~43000
CHF/year).
Applications with a full CV, list of publications, short statement of research interests
and names of at least one referee should be submitted (in electronic form) to
volker.roth@unibas.ch

CFP Media Retargeting Workshop at ECCV 2010

MEDIA RETARGETING WORKSHOP

in conjunction with ECCV 2010, September 10, Crete, Greece

http://www.vision.ee.ethz.ch/MRW2010

OVERVIEW

Media retargeting is the process of adapting media content such as
images or video to the characteristics of different output devices.

Media retargeting has received considerable attention in computer
vision and graphics research in the recent years due to the growing
variability in capture devices and displays (small displays in mobile
devices, large high resolution displays in home cinema systems) and
the availability of huge amounts of image and video data. Besides
converting video between different display sizes, the spectrum of
problems related to media retargeting also comprises issues such as
color adaptation between different dynamic ranges, or the automatic
conversion of 2D to 3D footage for upcoming stereoscopic consumer
display devices.

The goal of this workshop is to bring together researchers and
practitioners from all areas of computer vision, machine learning,
and computer graphics, and to stimulate the discussion about shared
concepts and recent progress on topics ranging from perceptual content
analysis over efficient optimization algorithms for retargeting to
systematic evaluation of already existing techniques.

CALL FOR PARTICIPATION

We invite high quality, original submissions for presentation during
the workshop. Contributions from the following areas are especially
welcome:

* video or image retargeting of aspect ratio and resolution
* color retargeting between low and high dynamic ranges
* visual saliency estimation
* attention estimation and perceptual metrics
* temporal retargeting and content summarization
* retargeting of stereoscopic content
* monocular video to stereo conversion
* relevant optimization techniques
* systematic evaluation and user studies of relevant methods
* perceptual studies of retargeting results
* multi-modal retargeting (e.g. video and sound)

DATES

* Full paper submission: June 16, 2010
* Notification of acceptance: July 9, 2010
* Camera ready version of accepted papers: July 13, 2010

KEYNOTE SPEAKER

* Ariel Shamir, Efi Arazi School of Computer Science, Herzliya

ORGANIZERS
* Thomas Deselaers, ETH Zurich
* Alexander Hornung, Disney Research Zurich
* Olga Sorkine, New York University

Two PhD studentships at Surrey

Two PhD Studentships
University of Surrey,
Centre for Vision, Speech and Signal Processing (CVSSP)

————————————————
Transfer learning for sports video understanding

CVSSP are offering an EPSRC funded 3 year PhD studentship in Computer
Vision within the area of Video Understanding and Transfer Learning. The
studentship covers UK/EU tuition fees plus a maintenance grant for three
years.

This PhD shall use video analysis techniques in order build an adaptable
system to provide high level description of game events. Most
importantly, the research will focus on transferring knowledge from one
game modality to another. Multiple cues shall be used. The student will
join a team of people who are already working on different aspects of
this problem, such as player action classification, ball event detection
and audio pattern recognition. This is part of the
ACASVA project (http://kahlan.eps.surrey.ac.uk/acasva/).

————————————————
Pose invariant face recognition

Face recognition is a challenging application for computer vision for a
number of reasons. First of all, faces in a general pose cannot be
easily registered in a consistent manner. Second, illumination tends to
play a dominating influence in assessing the similarity of two face
images. Third, uncontrolled pose often implies poor resolution, which
further complicates the face recognition problem. This PhD project will
tackle these problems with the help of a morphable 3D face model. By
fitting such a model to 2D face image, it should be possible to correct
the pose of the input image and perform the matching in a standard
frontal pose. More over, it should be possible to use the 3D model to
relight the query image to achieve photometric normalisation.

————————————————
Application procedure

Please send the completed Postgraduate Research Programmes application
form, available from www2.surrey.ac.uk/postgraduate/apply, to Prof J
Kittler by email to J.Kittler@surrey.ac.uk. Please address any enquiries
to Dr Teo de Campos at T.Decampos(at)surrey.ac.uk

The successful candidates will have strong mathematical background and
programming skills in C++. Research experience in Vision and Machine
Learning will be a plus.

CVSSP is part of the Faculty of Engineering and Physical Sciences, which
received the highest rating of 5**A in the 2001 Research Assessment
Exercise (RAE), and ranked 2nd in the 2008 RAE with the highest number
of research active staff.

Applicants are required to have a First Class (or good 2.1) Honours or
Masters Degree in a related discipline (for example, Electronic
Engineering or Computer Science). The successful candidate will receive
a studentship paying full “Home” (UK/EU) level fees, and a maintenance
grant for three years subject to satisfactory progress.

CFP – First International Workshop on Parts and Attributes (ECCV)

First International Workshop on Parts and Attributes
In conjunction with ECCV 2010, September 10th, 2010, Crete, Greece
http://rogerioferis.com/PartsAndAttributes/

Important Dates:
* Deadline for submission of papers: June 16th, 2010
* Notification of acceptance: July 6th, 2010
* Final version of submission: July 14th, 2010

Overview:
Recent advances in probabilistic modeling and optimization have lead to
a renewed interest in part-based methods for solving fundamental
problems in computer vision, in particular object detection,
classification, and pose estimation. Although substantial progress has
been made to adequately parse objects into parts and build models to
handle variations such as object pose and lighting, many open problems
still remain to be solved. At the same time, part-based models for scene
understanding are being developed that for the first time allow a
holistic understanding of natural scenes based on local image regions
and their interaction. In parallel to part-based models, attributes
based classification has recently been rediscovered, e.g. as a promising
tool to overcome the problem that there are too many visual object
categories to train individual classifiers for each of them. Attributes
also make a more targeted search in large image databases possible,
allowing e.g. queries like “person with blond hair, long nose and a red
shirt”. The goal of this workshop is to bring together emerging research
on part-based methods and attributebased methods. We believe there is a
strong link between these two research areas which has not been
previously explored.

Call for Participation:
We invite high quality, original submissions for oral presentation
during the workshop. Contributions
from the following areas are especially welcome:

* Part-based Methods:
– Localization of object parts
– Deformable and rigid part-based models
– Generative vs. discriminative part-based models
– Structured prediction for part estimation
– Context and hierarchy in part-based models

* Attribute-based Methods:
– Learning visual attributes across object classes
– Attribute-based classification with few examples
– Semantic attributes as object representations

* Hybrid Part/Attribute-based Methods
– Semantic parsing of objects and scenes
– Joint learning of object parts and attributes

* Applications:
– Object detection and recognition
– Visual image search
– Soft-biometrics
– Innovative applications of parts and attributes

We also invite submissions from related domains including theoretic
results relevant to the workshop’s topic. Papers must be in PDF format
and should not exceed 14 pages (ECCV format). All submissions are
subject to a double-blind review process by the program committee.
Further details can be found on the workshop homepage.

Workshop Chairs:
– Rogerio S. Feris, IBM
– Tiberio Caetano, NICTA
– Christoph H. Lampert, IST Austria
– David Forsyth, UIUC

8th Summer School on Data Mining, Maastricht, The Netherlands

8-th SUMMER SCHOOL ON DATA MINING, Maastricht, The Netherlands
http://www.cs.unimaas.nl/datamining/

Summer School: Data Mining

An intensive 4-day introduction to methods and applications

Department of Knowledge Engineering, Maastricht University,
Maastricht, The Netherlands
August 30 – September 2, 2010

Introduction
Most business organizations collect terabytes of data about business
processes and resources. Usually these data provide just “facts and
figures”, not knowledge that can be used to understand and eventually
re-engineer business processes and resources. Scientific community in
academia and business have addressed this problem in the last 20 years
by developing a new applied field of study known as data mining.
In practice data mining is a process of extracting implicit,
previously unknown, and potentially useful knowledge from data. It
employs techniques from statistics, artificial intelligence, and
computer science. Data mining has been successfully applied for
acquiring new knowledge in many domains (like Business, Medicine,
Biology, Economics, Military, etc.). As a result most business
organizations need urgently data-mining specialists, and this is
the point where this course comes to help.

Course Description
The course is well balanced between theory and practice. Each lecture
is accompanied by a lab in which course participants experiment with
the techniques introduced in the lecture. The lab tool is Weka, one
of the most advanced data-mining environments. A number of real data
sets will be analysed and discussed. In the end of the course
participants develop their own ability to apply data-mining techniques
for business and research purposes.

Course Description
The course focuses on techniques with a direct practical use.
A step-by-step introduction to powerful (freeware) data-mining tools
will enable you to achieve specific skills, autonomy and hands-on
experience. A number of real data sets will be analysed and discussed.
In the end of the course you will have your own ability to apply data-
mining techniques for research purposes and business purposes.

Course Content
The course will cover the topics listed below.
– The Knowledge Discovery Process
– Data Preparation
– Basic Techniques for Data Mining:
+ Decision-Tree Induction
+ Rule Induction
+ Instance-Based Learning
+ Bayesian Learning
+ Support Vector Machines
+ Regression Techniques
+ Clustering Techniques
+ Association Rules
– Tools for Data Mining
– How to Interpret and Evaluate Data-Mining Results

Intended Audience
This course is intended for four groups of data-mining beginners:
students, scientists, engineers and experts in specific fields who need
to apply data-mining techniques to their scientific research, business
management, or other related applications.

SIKS
Participating in this course is a part of the advanced components stage
of SIKS’ educational program. SIKS has reserved a number of places for
those Ph.D-students working on the course topics.

Prerequisites
The course does not require any background in databases, statistics,
artificial intelligence, or machine learning. A general background in
science is sufficient as is a high degree of enthusiasm for new
scientific approaches.

Certificate
Upon request a certificate of full participation will be provided after
the course.

Registration
To register for the course please send an email to the registration office
specifying the following information:
– Name
– University / Organisation
– Address
– Phone
-E-Mail

Please register before August 9, 2010

Registration fees
Academic fee 600 Euros
Non-academic fee 850 Euros

Included in the price are: course material and coffee breaks. The local
cafeteria will be available for lunch (not included).

SIKS-Ph.D. students
Participating in this course is a part of the advanced components stage
of SIKS’ educational program. SIKS has reserved a number of places for
those Ph.D-students working on the course topics. SIKS-Ph.D.-students
interested in taking the course should NOT contact the local organization,
but send an e-mail to office(at)siks.nl and confirm that their supervisor
supports their participation

E-mail should be sent to: smirnov(at)maastrichtuniversity.nl

Regular mail should be sent to:

Evgueni Smirnov
Department of Knowledge Engineering
Faculty of Humanities and Sciences
Maastricht University
P.O.Box 616
6200 MD Maastricht
The Netherlands
Phone: +31 (0) 43 38 82023
Fax: +31 (0) 43 38 84897