Two Postdoc Positions in Computer Vision and Machine Learning

Two postdoc position in Computer Vision and Machine Learning are available immediately at
the Institute of Science and Technology Austria (IST Austria) in the group of Christoph
Lampert.

Applicants should hold a PhD and have experience in machine learning, optimization and/or computer vision. Prior knowledge of discriminative machine learning techniques (in particular
kernel methods, structured output learning, and/or probabilistic approaches) will be an
advantage, a strong analytical background is a must. We are looking a for highly motivated
and creative individuals who enjoy working in an excellent research environment including
adequate funding for equipment and conference travel. The successful candidates will have no
mandatory teaching or adminstrative duties, but they should be motivated to take an active
role in the further development of the newly established research group. Good
communication skills and fluency in English are required. German language skills not
required.

Conditions of employment: The post-doctoral positions is provided for one or two years with
the possibility for extension. Salaries are very competitive. The starting dates are flexible.
There is no fixed deadline, applications will be considered until the positions are filled.

Application procedure: Formal applications should include CV, a statement of research
experience and interests, list of publications, academic transscripts, as well as the contact
details of three references. Please send applications as single PDF document to Prof.
Christoph Lampert chl(at)ist.ac.at.

About the institute: IST Austria (www.ist.ac.at) is a new institute that opened its campus near
Vienna in 2009. It is dedicated to basic research in the natural sciences and related disciplines
(http://www.ist.ac.at/research). Established by the Austria Government, IST Austria has
substantial funding, allowing for over 500 employees and graduate students by 2016. The
language of the Institute is English.

Final CFP: IEEE International Workshop on Social Behavior Analysis @ FG 2011

Final Call for papers: IEEE International Workshop on Social Behavior
Analysis (SBA 2011)

Santa Barbara, CA , 21 or 25 March 2011 (This is a one day workshop,
exact date will be announced soon), in conjunction with FG 2011

Important Dates

* Paper submission (extended): 20 December 2010
* Notification to the authors: 13 January 2011
* Receipt of camera ready copy: 19 January 2011

Webpage: http://www.idiap.ch/~oaran/sba/index.html

=====================================

There is a strong interest in fields like computer vision, audio
processing, multimedia, HCI, and pervasive computing, in designing
computational models of human interaction in realistic social settings.
Such interest is boosted by the increasing capacity to acquire
behavioral data with cameras, microphones and other fixed and mobile
sensors. Unlike the traditional HCI view, which emphasizes communication
between a person and a computer, the emphasis of an emerging body of
research has been shifting towards communicative social behavior in
natural situations, with examples such as informal conversational
settings, general workplace environments, interviews, and meeting
scenarios.

The workshop will gather, discuss, and disseminate unpublished work on
computational models and systems for the analysis of social behavior.
Given the scope of Automatic Face and Gesture Recognition conference, we
would like to focus on automatic techniques for visual analysis of human
communication and on the applications that are built on top of it. We
welcome contributions that present robust techniques for the analysis of
gestures and facial expressions in natural conversational environments
to model social behavior in everyday life and reason about them. We also
strongly encourage the participation of colleagues from behavioral
sciences: studies of nonverbal behavior and social interaction provide
highly valuable information, concepts, and frameworks to guide automatic
analysis, while efforts in automatic analysis of social behavior provide
new tools, data, and insights to behavioral scientists interested in
nonverbal behavior and social interaction.

We invite contributions that address the following (non-exhaustive) list
of topics:

Social behavior analysis
* Analysis and recognition of visual social cues and others:
o Visual nonverbal cues (body postures, hand gestures, head
gestures, actions …)
o Multimodal affect recognition
o Nonverbal cues from other sensors
* Multimodal computational models for the analysis, estimation, and
prediction of social behavior aspects and dimensions (interest level,
dominance, rapport, deception…) and of individual properties affecting
it (e.g., personality traits, preferences…)
* Analysis of conversational dynamics
* Multimodal data corpora for social behavior analysis

Systems and devices for capturing social behavior
* Smart camera/microphone systems
* Novel sensor technologies
* Wearable devices
* Cell phones

Socially aware systems and applications
* Computers and robots in the human interaction loop
* Individual and group self-awareness
* Educational applications
* Workplace applications
* Healthcare applications
* Game applications
* Art & creative applications

Organizers:
Oya Aran, Idiap Research Institute
Daniel Gatica-Perez, Idiap Research Institute
Louis-Philippe Morency, University of Southern California
Fabio Pianesi, University of Trento

More information can be found on the workshop web site:
http://www.idiap.ch/~oaran/sba/index.html

CFP: Self-* Search (GECCO 2011 New Frontiers Track)

—————————————————–
Call for papers: Self-* Search (New Frontiers Track)
at GECCO, July 12-16, Dublin, Ireland
Visit http://www.sigevo.org/gecco-2011/
—————————————————–

Search and optimization problems are everywhere, and search algorithms
are getting increasingly powerful. However, they are also getting
increasingly complex, and only autonomous self-managed systems that
provide high-level abstractions can turn search algorithms into widely
used methodologies. Such systems should be able to configure themselves
on the fly, automatically adapting to the changing problem conditions,
based on general goals provided by their users.

The aim of the Self-* Search track at GECCO 2011 is to bring together
all researchers interested in software systems able to automatically
tune, configure, or even generate and design optimization algorithms
and search heuristics.

The Self-* Search track is a brand new track in 2011, selected among
the competing entries to the “New Frontiers Track” for its novelty and
potential. It is an exciting opportunity to explore emerging new
research directions, and to confront ideas originating from the
different fields of Computer Science concerned with adaptive search and
optimization, from Artificial Intelligence to Operational Research and
Mathematical Programming.

We invite all papers related to Self-* Search, in particular (but not
limited to) those in the following subject areas: hyper-heuristics,
adaptive and self-adaptive parameter control, adaptive operator
selection, automated construction of search heuristics, systems to
build systems, computer-aided algorithm design, multi-level search,
experimental analysis of algorithms, automatic algorithm configuration,
adaptive multimeme algorithms, software self-assembly, reactive search,
intelligent optimization, algorithm selection and portfolios, and all
applications of self-* techniques to multi-objective, dynamic, and
complex real-world problems.

Self-* Search related papers were scattered across several GECCO tracks
in previous editions. We have this year a unique opportunity to both
gather and unify these threads into a single track, and open up the
scope for new and ambitious research directions in automated
heuristic design, and autonomic computing in general. Our hope is
that your numerous submissions will demonstrate the importance of
this line of research, and that this track will continue to flourish
with your support and enthusiasm.

URL:
http://www.cs.nott.ac.uk/~gxo/selfstar2011/
http://www.sigevo.org/gecco-2011/organizers-tracks.html#ss

Track Chairs: Gabriela Ochoa and Marc Schoenauer
Paper submission: GECCO submission procedure and guidelines

———————————————————————–
2011 Genetic and Evolutionary Computation Conference (GECCO-2011)
July 12-16, Dublin, Ireland
Organized by ACM SIGEVO
20th International Conference on Genetic Algorithms (ICGA) and
the16th Annual Genetic Programming Conference (GP)
One Conference – Many Mini-Conferences 15 Program Tracks
———————————————————————–
GECCO is sponsored by the Association for Computing Machinery Special
Interest Group on Genetic and Evolutionary Computation (SIGEVO). SIG
Services: 2 Penn Plaza, Suite 701, New York, NY, 10121, USA,
1-800-342-6626 (USA and Canada) or +212-626-0500 (Global).

Head of Department & Research Fellow, Oxford Brookes, UK

Fixed term research fellowship in computer vision,
full details available here
https://edm.brookes.ac.uk/hr/hr/vacancies.do?id=8144704

Head of department in department with emphasis on computer vision
full detaild available here
https://edm.brookes.ac.uk/hr/hr/vacancies.do?id=8176959

APA- FIRST CALL FOR PAPERS – DEADLINE 10th January 2011

First Call for Papers for:

Special Session on Automatic Photo Albuming (APA)
http://www.imagapp.visigrapp.org/APA.asp

Satellite event of IMAGAPP 2011
5-7 March, 2011 – Algarve, Portugal

The Special Session on Automatic Photo Albuming (APA) addresses the major challenges in automating photo album and derived product creation from large image collections. These collections can be composed by consumer’s personal photos, by images related to social events shared in social networks and they can be enriched with photos of third-party repositories (e.g. flickr, photo.net). Statistics shows that due to the time needed for completing the album editing tasks, about 50% of all photo books started online are never finished: creating a photo-album is still a tedious and sometimes frustrating experience. In fact, despite the recent advances in image understanding and multimedia content creation, many essential image manipulation and document editing tools are not yet integrated in albuming workflow. This is true for several reasons: current tools accuracy is limited; it is difficult to create user friendly applications where such tools are effectively used to assist the users and reducing the time to press. The aim of this special session is to offer an opportunity for researchers, developers and photo service providers, to interact and exchange ideas about methods to assist users in the creation of high quality photo books within minimum efforts and time. Hence authors are solicited (but are not limited) to submit papers on the following topics:

* Automatic image quality assessment and enhancement
* Image clustering and near duplicate detection
* Image set summarization
* Saliency detection and image auto-crop
* Analyzing image aesthetics
* Advanced photo editing tools (image inpainting, color transfer, object removal/object rearrangement, scene carving)
* Automatic layout (images reflow, background color selection, etc)

Organizers:
Luca Marchesotti (Xerox), Joost Van de Weijer (CVC of Barcelona) and Gabriela Csurka (Xerox)

Important dates:
Regular Paper Submission: January 10, 2011 (strict deadline)
Authors Notification: January 25, 2011
Final Paper Submission and Registration: February 3, 2011

All accepted papers will be reviewed by 3 experts from the Imagapp Program Committee (http://www.imagapp.visigrapp.org/program_committee.asp). Accepted papers will be published in the conference proceedings book, under an ISBN reference and on CD-ROM support that will be available at the SciTePress Digital Library (http://www.scitepress.org/DigitalLibrary/). In addition, we intend to publish extended versions of best papers in a special issue of an international journal.

Should you have any question please don’t hesitate contacting the chairs or the Imagapp secretariat (imagapp.secretariat(at)insticc.org)

MIRAD – FIRST CALL FOR PAPERS – DEADLINE 10th January 2011

First Call for Papers for:
Special Session on Medical Image Repositories Assisting Diagnoses (MIRAD)

http://www.imagapp.visigrapp.org/MIRAD.asp

Satellite event of IMAGAPP 2011
5-7 March, 2011 – Algarve, Portugal

The Special Session on Medical Image Repositories Assisting Diagnoses (MIRAD) aims to address major challenges in assisting physicians to make diagnostic decision using medical image repositories. Traditionally, decision-making involves evidence provided by the patient data coupled with a physician’s a priori experience of a limited number of similar cases. Advances in electronic health record systems facilitate the creation of large numbers of pre-diagnosed patient data sets. These repositories become a key component for the diagnosis of many pathologies, follow-up and treatment. However, it is not straightforward how to efficiently and effectively exploit these repositories. There is a clear need for advanced techniques in medical image analysis and database indexing, multimodal data mining tools to efficiently discover associations between image and non-image (structured or free text) data and enhanced visualization techniques to assist physicians.

The aim of this special session is on the one hand to bring together researchers to discuss new techniques in these fields and their use in clinical decision support. On the other hand, we invite practitioners and healthcare professionals to submit papers clearly describing the major problems and the limitations of existing technologies and raising open issues for which they would need clear solutions.

Organizers:
Henning Müller (HES-SO), Gabriela Csurka (Xerox) and Mario Jarmasz (Xerox)

Important dates:
Regular Paper Submission: January 10, 2011 (strict deadline)
Authors Notification: January 25, 2011
Final Paper Submission and Registration: February 3, 2011

All papers will be reviewed by 3 experts from the Imagapp Program Committee (http://www.imagapp.visigrapp.org/program_committee.asp). Accepted papers will be published in the conference proceedings book, under an ISBN reference and on CD-ROM support that will be available at the SciTePress Digital Library (http://www.scitepress.org/DigitalLibrary/). In addition, we intend to publish extended versions of best papers in a special issue of an international journal.

Should you have any question please don’t hesitate contacting the chairs or the Imagapp secretariat (imagapp.secretariat(at)insticc.org)

ICCS 2011 workshop on High-dimensional Data Visualization: CFP

Call for papers

ICCS 2011 workshop on High-dimensional Data Visualization

A workshop in conjunction with the ICCS 2011 conference,
International Conference on Computational Science,
Tsukuba (Japan), June 1-3, 2011

http://www.dice.ucl.ac.be/~verleyse/ICCS%202011

Deadline for submission of papers: January 8, 2011

Short overview (see http://www.dice.ucl.ac.be/~verleyse/ICCS%202011 for more detailed CFP):

Data visualization plays an important role in data analysis and mining, by helping to find specificities of data (clusters, outliers, densities,…) that in turn determine the choice for analysis tools and algorithms. Recently, there has been an increasing scientific activity in the development of nonlinear algorithms for visualizing data, in the contexts of nonlinear dimensionality reduction and manifold learning. While algorithms are now established, there is still a lack of applicability in real-world situations, on high-dimensional data, and of objective criteria to assess the quality of the visualization. This workshop will concentrate on recent developments, including the applicability to high-dimensional data, the methodology to choose methods, and their objective evaluation.

Workshop organizers:
Michel Verleysen, Université cat. Louvain (Belgium), michel.verleysen(at)uclouvain.be
Fabrice Rossi, Télécom ParisTech (France), fabrice.rossi(at)telecom-paristech.fr
John Lee,Université cat. Louvain (Belgium), john.lee(at)uclouvain.be

Paper submission and format :
See http://www.dice.ucl.ac.be/~verleyse/ICCS%202011 for detailed instructions.

2nd CFP: International Workshop on Pattern Recognition in Neuroimaging (PRNI 2011)

* 2nd CALL FOR PAPERS (deadline extension) *

International Workshop on Pattern Recognition in Neuroimaging (PRNI 2011)
Seoul, Korea, May 16-18, 2011

http://brain.korea.ac.kr/prni2011

Pattern recognition and machine learning techniques provide
a new way to analyze complex and huge brain imaging datasets.
Many challenges are also present in other applications of pattern
recognition, such as non-stationary distributions, model regularisation,
high-dimensional time series, or causality modeling.

Following the success of the first Workshop on Brain Decoding
(Istanbul, 2010), this three-day workshop aims at providing an opportunity
for discussing recent advances in methods and applications, while trying to
narrow the gap between imaging modalities. A subfield where discussion is
of special interest is that of real-time methods, as they are at the
confluence of modalities (EEG/fMRI) and at the forefront of machine
learning research (incremental learning, non-i.i.d. data). Interpretability
of classification and regression machines is also critical to increasing
interactions between methods and application-oriented researchers, and is
of particular interest for this workshop.

Several travel scholarships will be available for Ph.D. students and
post-docs, and will be awarded competitively based on reviewer scores
of the papers.

Keynote speakers will include
Stephen Strother (University of Toronto, Canada)
Stephen LaConte (Baylor College of Medicine, USA)

SCOPE

The workshop welcomes original contributions using relevant modalities
(e.g. functional/structural MRI, EEG, ECoG, MEG) including the following
areas:

* Data representation
Voxel / channel / feature selection
Linear and non-linear dimensionality reduction
Sparse time-course representations
Interpretability and validation

* High-dimensional learning
Regularisation
Transfer learning
Multimodal / ensemble classification
Incremental / online learning and adaptation

* Applications
Cognitive, affective, and social neurosciences
Man-machine interfaces
Clinical applications

SUBMISSION AND PROCEEDINGS

Authors should prepare full 4-pages papers (double-column, IEEE style).
Extended abstract are not accepted. The review process will be double-blind.

Proceedings will be published by IEEE Computer Science Society in
electronic format. They will be permantently available on the IEEExplore
and IEEE CS Digital Library online repositories, and indexed in IEE
INSPEC, EI Compendex (Elsevier), Thomson ISI, and others.

DATES AND DEADLINES

Full paper submission: December 17th, 2010
Acceptance notification: January 31st, 2011
Travel scholarship notification: February 15th, 2011
Camera-ready paper: March 1st, 2011
Workshop: May 16-18, 2011

PROGRAMME COMMITTEE

R. Abugharbieh (U. of British Columbia, CA)
T. Adali (U. of Maryland, Baltimore County, USA)
J. Ashburner (UCL, UK)
B. Blankertz (TU Berlin, DE)
M. Brammer (King’s College London, UK)
V. Calhoun (Yale, USA)
C. Chu (NIH, USA)
T. Ethofer (U. Tübingen, DE)
C. Gaser (U. Jena, DE)
P. Golland (MIT, USA)
L. Grosenick (Stanford, USA)
G. Hamarneh (Simon Fraser U., CA)
D. Hardoon (Inst. for Infocomm Research, SG)
T. Jiang (Chinese Academy of Sciences, CN)
K. Kryszczuk (IBM Research, CH)
G. Langs (MIT, USA)
F. Lotte (A*STAR, SG)
A. Marquand (UCL, UK)
J. Meynet (Bestofmedia Group, FR)
J. Sato (Federal U. of ABC, BR)
S. Schwartz (U. of Geneva, CH)
N. Schuff (UCSF, USA)
B. Thirion (Neurospin, FR)
P. Vemuri (Mayo Clinic, USA)
P. Vuilleumier (U. of Geneva, CH)
M. Van Hulle (K.U. Leuven, BE)

ORGANISING COMMITTEE

General Chairs: S.-W Lee (Korea University, KR), C. Davatzikos (U. of
Pennsylvania, USA), D. Van De Ville (EPFL/U. of Geneva, CH)

Program Chairs: J. Richiardi (EPFL/U. of Geneva, CH), J. Mourão-Miranda
(UCL/King’s College, UK), Y. Kamitani (ATR, JP)

Tutorial Chair: F. Pereira (Princeton U., USA)

Local Arrangements Chair: J.-H. Lee (Korea University, KR)

Publication Chair: C. Wallraven (Korea University, KR)

Finance Chair: J. Kwag (Korea University, KR)

Registration Chair: S.-P. Kim (Korea University, KR)

GREAT10 PASCAL challenge launches Monday 6th Dec

PASCAL GRavitational lEnsing Accuracy Testing 2010 (GREAT10)

We announce the launch of the gravitational lensing accuracy testing challenge
GREAT10. The challenge has two aspects, the star challenge and the more
demanding galaxy challenge.

The star challenge is to estimated the convolution kernel in astronomical images.
The kernel is sparsely sampled by stars in the images, which are coarsely pixelated and
contain noise. The challenge is to reconstruct the convolution kernel
at non-star positions.

The galaxy challenge is to measure the correlation function of the
shear effect (an additional 1% ellipticity caused by gravity and present in
every galaxy image) over 52 million simulated galaxy images. The
images are noisy and have been blurred by a known convolution kernel.

We provide the images, 1Tb in total, some development code, training data,
and more information here

http://www.great10challenge.info

The winner of the challenge will receive an iPad (or similar) and an expenses
paid trip to the final challenge workshop at JPL, Pasadena in September 2011.

The key dates associated with this challenge are :

* 6th December 2010 : Challenge Launch

* 26th-28th January 2011 : Challenge Workshop I, eScience Institute, Edinburgh

* 3rd-5th May 2011 : Challenge Workshop II, UCL, London

* 2nd September 2011 : Challenge Closes

* 26th-29th September 2011 : Final Challenge Workshop, JPL NASA, Pasadena

Open Postdoc Positions in Reinforcement Learning at INRIA Lille

The project team SEQUEL (Sequential Learning) of INRIA Lille, France, https://sequel.lille.inria.fr/ is seeking to appoint one Postdoctoral Fellow. We welcome applicants with a good mathematical background who are interested in theory and applications of reinforcement learning and bandit algorithms.

The research will be conducted under the supervision of Remi Munos, Mohammad Ghavamzadeh, and Daniil Ryabko.

The positions are research only and are for one year, with the possibility of being extended.

The starting date is flexible, from Spring 2011 to Fall 2011.

INRIA is France’s leading institution in Computer Science, with over 2800 scientists employed, of which around 250 in Lille. Lille is the capital of the north of France, a metropolis with 1 million inhabitants, with excellent train connection to Brussels (30 min), Paris (1h) and London (1h30).

The Sequel lab is a dynamic lab at INRIA with over 25 researchers (including PhD students) which covers several aspects of machine learning from theory to applications, including statistical learning, reinforcement learning, and sequential learning.

The positions will be funded by the EXPLO-RA project (Exploration-Exploitation for efficient Resource Allocation), a project in collaboration with ENS Ulm (Gilles Stoltz), Ecole des Ponts (Jean Yves Audibert), INRIA team TAO (Olivier Teytaud), Univ. Paris Descartes (Bruno Bouzy), and Univ. Paris Dauphine (Tristan Cazenave).

See: http://sites.google.com/site/anrexplora/ for some of our activities.

Possible topics include reinforcement learning, possibly with sparsity, random projections, bandit algorithms for solving large MDP, POMDPs.

Candidates must have a Ph.D. degree (by the starting date of the position) in computer science, statistics, or related fields, possibily with background in reinforcement learning, bandits, or optimization.

To apply please send a CV to remi.munos(at)inria.fr or mohammad.ghavamzadeh(at)nria.fr, or daniil.ryabko(at)inria.fr.

If you are planning to go to NIPS this year, we could set up an appointment there with Mohammad Ghavamzadeh.