News Archives

CFP – Workshop on applications of pattern analysis

Workshop on Applications of Pattern Analysis
1 – 2 September 2010, Cumberland Lodge (Windsor, UK)
Submission deadlines: may 9th for abstract; may 16th for full paper.
www.pascal-network.org/wapa2010

DESCRIPTION

Pattern Analysis and Statistical Learning cover a wide range of
technologies and theoretical frameworks, and significant activity in
the past years has resulted in a remarkable convergence and many
advances in the theory and principles underlying the field.

Bringing these technologies to real world demanding applications is
however often treated as a separate problem, one that does not
directly affect the field as a whole. It is instead important to
consider the field of Pattern Analysis as fully including all issues
involved with the applications of this technology, and hence all
issues that arise when deploying, scaling, implementing and using the
technology.

We call for contributions in the form of Demo papers, Case Studies, Working
Systems, Real World Applications and Usage Scenarios. Challenges may
stem from the violation of common theoretical assumptions, from the
specific types of patterns and noise arising in certain scenarios, or
from the problem of scaling up the implementation of state of the art
algorithms to real world sizes, or from the creation of integrated
software systems that contain multiple pattern-analysis components.

We are also interested in new application areas, where Pattern
Analysis has been deployed with success, and in issues involving the
visualisation and delivery and exploitation of the patterns discovered
by PA technologies. Systems working in noisy and unstructured
environments and situations are particularly interesting.

SUBMISSION PROCEDURE
We welcome papers (and possibly also related demos) in all of the areas
described above. Papers should be max 7 pages long, in PDF, using
the provided style file which is available on the workshop website, describing a working system that makes use of Pattern Analysis technology and for which interesing challenges were
encountered and overcome during its deployment, or an application that
has benefited another field of research.
Papers describing software and web demos are
welcome, as are case studies.

Submissions should be sent by email to wapa2010@pascal-network.org.
Abstracts are due on may 9th, and full papers on may 16th, 2010.

Proceedings will be published containing the accepted papers within
the JMLR Proceedings Series:
http://jmlr.csail.mit.edu/proceedings/

IMPORTANT DATES

9 May 2010
Deadline for abstract submission

16 May 2010
Deadline for paper submission

28 June 2010
Notification of Acceptance

31 August 2010
Workshop arrival at 4pm

1 – 2 September 2010
Workshop

ORGANISERS:

Tom Diethe
University College London

John Shawe-Taylor
University College London

Nello Cristianini
University of Bristol

CFP: Shared Control for BMI

2010 IEEE Int. Conf. on Systems, Man, and Cybernetics
Workshop on Brain-Machine Interfaces

Brain-machine interfaces (BMI) offer the possibility of a new generation of technologies that allow users to directly control devices directly via the nervous system. BMIs can be used to develop new communication pathways to restore and augment sensory and motor function in disabled individuals. At the core of BMI system design is a controller that must accommodate the seamless interaction between systems of neurons with electronics and robotics. This workshop solicits papers in any area of BMI, but it will prioritize contributions on innovations in signal processing, controls, and robotics to revolutionize information handling between the nervous system and computing machines.

The concept of “sharing control” between humans and machines has its roots back to the early history of Cybernetics. Compared to that early history, the challenges for BMIs involves developing control systems capable of handling biological signals that are sparse, noisy and dynamic in nature. Moreover, these systems are operating in a wide variety of dynamic environments encountered in the activities of daily life. One of the goals of this workshop is to identify leading advancements in Cybernetics theory that can improve performance in BMIs through cooperative control. Several examples of such systems include intelligent robotics that can assist with obstacle avoidance or accurate grasping, and adaptive algorithms that can learn the robot’s optimal behavior from the user’s nonstationary brain signals.

Of particular interest in this workshop are the principles that allow bi-directional communication and assistance between the user’s nervous system and the device being controlled as well as how to support the dynamic sharing of roles and responsibilities of a control task. In addition, topics sought include the design of collaborative, cognitive workspaces and signal analysis that supports a shared understanding of the task and environment.

The workshop will feature some prominent invited speakers active in research on “shared control” in BMI and other fields such as robotics and human-computer interaction.

Best contributions presented during the workshop will be invited to submit an extended version to a special issue of the IEEE Transactions on Systems, Man and Cybernetics – Part B that will undergo a normal full review process. The theme of this special issue of SMC-B is “Shared Control in Brain-Machine Interfaces”, and submissions are open to active researchers in the field independently of whether or not they participate in this workshop.

Place & Dates: Istanbul, Turkey. October 10-13, 2010. http://www.smc2010.org

PAPER SUBMISSIONS:
Papers should follow the IEEE format and conference guidelines. The template is available at: http://www.smc2010.org/SMC2010_Paper_Format.zip
Send a PDF copy of your paper to
jose.millan AT epfl.ch
with the title “SMC’10-BMI Workshop”.

ORGANIZERS:
José del R. Millán, Ph.D.
EPFL, Switzerland (http://people.epfl.ch/jose.millan)

Jose M. Carmena, Ph.D.
University of California, Berkeley, CA, USA (http://www.eecs.berkeley.edu/~carmena)

Justin C. Sanchez, Ph.D.
University of Florida, Gainesville, FL, USA (http://nrg.mbi.ufl.edu)

Michael Smith, Ph.D.
University of California, Berkeley, CA, USA

Schedule:
Deadline for submissions: April 15th, 2010
Notification of review: May 15th, 2010
Final manuscript due: June 27th, 2010

PDRA in Single Molecule Statistical Signal Processing

Single Molecule Statistical Signal Processing

Applications are invited for a postdoctoral research assistant to work under the supervision of Professor Hagan Bayley (Oxford Chemistry) and Dr Nick Jones (Oxford Physics) on a research project for an initial period of one year. The project involves the development of advanced statistical signal processing techniques to facilitate low-cost, rapid nanopore-based DNA sequencing, with the eventual aim of making reliable base calls from long DNA strands driven through the nanopore. The group is located in the Chemistry Research Laboratory at Oxford www.chem.ox.ac.uk/ Find out more about the Bayley research group at www.chem.ox.ac.uk/researchguide/hbayley.html and the Jones group at www.physics.ox.ac.uk/cm/cmt/jones/

Applicants should either already have a PhD in a relevant subject area, or have submitted their thesis prior to taking up the post. The applicant should have a working knowledge of modern statistical signal processing methods; Effective Matlab (or equivalent), programming skills, a good background understanding of relevant physical applied mathematics and statistics.

The post will be based in the Chemical Biology Group of the Chemistry Research Laboratory, Mansfield Road, Oxford OX1 3TA. The researcher will also have a desk in the Physics department. For further particulars of the post, including how to apply, visit our website http://www.chem.ox.ac.uk/jobs.asp . These should be obtained before an application is made. Informal enquiries should be addressed to max.little@physics.ox.ac.uk or hagan.bayley(at)chem.ox.ac.uk Please quote reference DQ10001/HB in all correspondence.

Further Details are available for download here: http://www.chem.ox.ac.uk/jobs/DQ10001-HB-FPs.pdf or by e-mail to recruitment(at)chem.ox.ac.uk quoting reference DQ10001/HB.
Application deadline for this post is 16 April 2010

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

Structured Models in Computer Vision – Call for Papers

__________________

CALL FOR PAPERS
__________________

STRUCTURED MODELS IN COMPUTER VISION

Workshop at CVPR 2010, June 14th, San Francisco, USA

Zurich, 16-20 August 2010

http://SMiCV2010.kyb.tuebingen.mpg.de/

email: smicv2010(at)tuebingen.mpg.de

submission deadline: 27 March 2010

OVERVIEW

A central question in Computer Vision is how human prior knowledge can
be integrated in order to build efficient and accurate learning
systems. Computer Vision and Machine Learning Researchers have come up
with many different models to incorporate their prior knowledge about
the domain structure – such as probabilistic graphical models,
conditional random fields, or structured support vector machines –
which have been applied successfully to many different areas of
application. The goal of this workshop is to bring together
researchers from different directions of Computer Vision and Machine
Learning, and to stimulate the discussion about the shared concepts,
the recent progress and the remaining problems of learning and
inference algorithms for structured representations in Computer
Vision.

FORMAT

The workshop will be a one-day event with one morning and two
afternoon sessions.

CALL FOR PARTICIPATION

We invite high quality, original submissions for presentation during
the workshop. Contributions from the following areas are especially
welcome:
* object recognition and localization
* image scene analysis
* human pose estimation
* image and video segmentation
* video analysis/surveillance
* shape analysis
* medical image analysis
We also invite submissions from related domains including theoretic
results relevant to the workshop’s topic.

Emphasis of the submissions should lie on aspects relevant to the
workshop topic, e.g. new learning methods for structured models,
modeling of new problems with prior knowledge of domain structure, or
efficient algorithms for inference in structured models. Papers must
be in PDF format and should not exceed 8 pages (CVPR format). All
submissions are subject to a double-blind review process by the
program committee. Further details about the submission process can be
found on the workshop homepage.

BEST PAPER PRIZE

The best paper will be awarded a google sponsored cash prize of 500US$.

DATES

* Deadline for submission of papers: 27th March 2010
* Notification of acceptance: 21th April 2010
* Camera-ready submission: 5th May 2010
* Workshop date: 14th June 2010

KEYNOTE SPEAKERS

* Daniel Huttenlocher, Cornell
* Antonio Torralba, MIT
* Thomas Hofmann, Google

ORGANIZERS

* Christoph Lampert, IST Austria
* Vittorio Ferrari, ETH Zurich
* Peter Gehler, ETH Zurich

The organizers can be contacted through smicv2010(at)tuebingen.mpg.de

ILP 2010, Florence (Italy) June 27-30, 2010

The 20th International Conference on Inductive Logic Programming (ILP 2010) will be held in Firenze, Italy, from Sunday 27th to Wednesday 30th June 2010. The conference is sponsored by PASCAL2 (as a non-core event).

ILP started in 1991 and is the premier international forum on logic-based and relational learning. The conference has recently explored several intersections to statistical learning and other probabilistic approaches, expanding research horizons significantly.

ILP 2010 will feature a tutorial day on June 27
Structural Decomposition Methods: Identifying easy instances of hard problems by Francesco Scarcello and Gianluigi Greco
Multivariate Models for Relational Learning by Volker Tresp

Confirmed keynote speakers so far are
Michael Kifer (Stony Brook University): AI Journal keynote speaker, Rule Interchange Format: Logic Programming’s Second Wind?
David Poole (University of British Columbia), Pascal keynote speaker, Probabilistic Relational Learning and Inductive Logic Programming at a Global Scale

A limited number of discounted student registrations are available, thanks to generous support from the Association for Logic Programming

Machine Learning Journal is our generous sponsor for the best student paper award.

More information on the conference website: http://ilp2010.dsi.unifi.it/

Machine Learning at Nokia Berlin

Vacancy details available at http://www.pascal-network.org/vacancies/nokia_ml.pdf

ECML PKDD 2010 Call for Demonstrations

ECML PKDD 2010 – Call for Demonstrations

The European Conference on Machine Learning and
Principles and Practice of Knowledge Discovery in Databases

http://www.ecmlpkdd2010.org/articles-mostra-2085-eng-demos.htm

We invite submissions for demos of working systems based on
state-of-the-art machine-learning and data-mining technology.

At ECML PKDD 2010 a special demonstration session will be held, an
exciting and highly interactive way to showcase the state of the art
in machine learning and knowledge discovery software. Accepted
demonstration papers will be published in the conference proceedings
(4 pages).

The focus will be on innovative prototype implementations, systems,
and technologies in machine learning and data analysis, concerned with
(non-exhaustive list):

* Information retrieval
* Text and language analysis/processing
* Media (image/video/audio/…) analysis/processing
* Visual data mining
* Mobile applications
* Sensor networks
* Robotics
* e-Science
* Industrial applications
* Business intelligence
* Multimodal HCI, including Brain Computer Interfaces

Submissions will be judged by a committee of technical experts with
expertise in machine learning, data mining, and software
engineering. Selection criteria include the relevance of the
contribution, its interest and usefulness for attendees, and its
technical difficulty. Special attention will be devoted to open-source
software, although not a requirement for submission.

Accepted contributions: At least one of the authors must register for
and attend the conference in order to present the demonstration
(precisions about demonstrations to be given with the acceptance
notification).

Submissions

Each demonstration should be accompanied by a short paper of at most 4
pages (including figures and screenshots if needed). The paper must be
in English and must be formatted according to the Springer-Verlag
Lecture Notes in Artificial Intelligence guidelines. Authors
instructions and style files can be downloaded at
http://www.springer.de/comp/lncs/authors.html

Please submit your paper electronically until May 14 to
demos(at)ecmlpkdd2010.org

In this accompanying paper, please try to answer the following
questions: What makes your piece of software unique and special? What
are the innovative aspects or in what way/area does it represent the
state of the art? For whom is it most interesting/useful? (an ML or
KDD researcher, a graduate or undergraduate student in these areas, an
industrial practitioner etc.) If there are similar/related pieces of
software: What are the advantages and disadvantages compared to these
related software?

Important Dates

Submission deadline: May 14
Notifications: June 7
Final versions due: June 21

Contact

In case you have any question, please do not hesitate to contact the
Demo Chairs Ulf Brefeld and Xavier Carreras via demos(at)ecmlpkdd2010.org

H-DIBCO 2010 – Handwritten Document Image Binarization Contest : Call for Participation

H-DIBCO 2010 – Handwritten Document Image Binarization Contest
in conjunction with the 12th International Conference on Frontiers in Handwriting Recognition (ICFHR’10), November 16-18, 2010, Kolkata, India.
http://users.iit.demokritos.gr/~bgat/H-DIBCO2010/

Document image binarization is an important step in the document image analysis and recognition pipeline. Due to this, it is imperative to have a benchmarking dataset along with an objective evaluation methodology in order to capture the efficiency of current document image binarization practices. Following the success of DIBCO 2009 organised in conjunction with ICDAR’09, the follow-up of this contest is organized in conjunction with ICFHR 2010. In H-DIBCO 2010 (Handwritten Document Image Binarization Contest), the general objective is to record recent advances in handwritten document image binarization using established evaluation performance measures. We will create a benchmarking dataset that is representative of the potential problems which are challenging in the binarization process and use a common evaluation platform in order to test and compare the submitted algorithms for handwritten document image binarization.

Sample image documents along with the corresponding ground truth will be given to all participants right after their registration.

We invite all researchers in the field of Document Image Binarization to register and participate in
H-DIBCO 2010. An agreement will be signed by the participants and the organizers in order to protect the Intellectual Property Rights (IPR) of the submitted software. The description of the methods and the evaluation scores will be presented during a dedicated ICFHR 2010 session. A report on the competition will be published in the ICFHR 2010 conference proceedings.

Important Dates

Registration is open due to 14/5/2010
Submission of executable due to 21/5/2010

The H-DIBCO 2010 Organizing Committee

I. Pratikakis, B. Gatos and K. Ntirogiannis
Computational Intelligence Laboratory
Institute of Informatics and Telecommunications
National Center for Scientific Research “Demokritos”
GR-153 10 Agia Paraskevi, Athens, Greece

BioTM-2010: Advances in Bio Text Mining / Call for Abstracts

Workshop BioTM-2010: Advances in Bio Text Mining

May 10-11, 2010, Ghent, Belgium

http://www.clips.ua.ac.be/BioTM2010/index.html

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

Abstracts are invited for the two-day workshop to be held in Ghent on
the 10th and 11th of May 2010.
Participants are encouraged to submit an extended abstract to the
workshop. Authors of selected abstracts will present their work in a
five minute bullet talk and their posters will be presented in a poster
session. Submitted abstracts will be reviewed by the organising committee.

The best abstracts will be published in an abstract supplement of BMC
Bioinformatics (http://www.biomedcentral.com/bmcbioinformatics/).
Submission deadline: April 1, 2010.

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

The program of the workshop includes:
– an extensive tutorial on Bio Text Mining by Martin Krallinger
– invited talks by leading scientists in the field: Sampo Pyysalo, Kevin
Cohen and Filip Ginter
– invited talks by experienced scientists from industry: Jean-Marc
Neefs, Luc Dehaspe and Maté Ongenaert

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

Text mining has become indispensible in many biological and biomedical
sciences. Having to keep up with an increasing number of publications,
text mining techniques enable retrieval and analysis of large amounts of
documents in a fully automated fashion. They allow for extraction of
facts described in the literature that have not yet been recorded in
databases, thus providing a necessary tool to obtain a complete overview
of all available knowledge.

Recently, the application of text mining and natural language processing
techniques to the biological and medical sciences has recieved
increasing interest. In addition to many new workshops and conferences
arising in this domain, recently also a number of community-wide tasks
were conducted to benchmark text mining techniques on specific
challenges (e.g. BioCreative, BioNLP Shared Task, …).

By discussing the latest developments and potentially new applications
in text mining amongst scientists in both academia and industry, this
workshop aims to provide a broad view on text mining tools in biology
and biomedicine. We are reaching out to a broad public, including
researchers with an interest in text mining but with little or no
experience in this domain. To this end, the workshop will start with an
extensive tutorial on text mining in the bio-sciences, providing
sufficient background knowledge for novices.

Next, a number of keynote talks will be given by leading scientists,
presenting the latest advances in the field. Furthermore, participants
are highly encouraged to submit an abstract describing their own work.
They will be given the opportunity to present this work in 5min flash
presentations, as well as to present a poster during the coffee and
lunch breaks.

Finally, we plan on having a round-table discussion about the broader
applicability of text-mining tools in the biological sciences, trying to
bridge the gap between theoretical algorithms and experimental work.

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

SUBMISSIONS: SCOPE

Submissions should present work related to any aspect of biomedical text
mining and bioinformatics. Additionally, we strongly encourage
submissions that describe shortcomings of current existing techniques,
tools, or resources, in order to detect problematic issues and work
towards their improvement.

SUBMISSIONS: INSTRUCTIONS

An abstract of maximum 400 words with at most 1 table or figure should
be submitted to the following e-mail address in pdf format:
biotm2010 at gmail dot com
Detailed formatting instructions can be found at
http://www.clips.ua.ac.be/BioTM2010/call.html
Submission is blind.

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

IMPORTANT DATES

1 April 2010 Submission deadline
15 April 2010 Notification of acceptance
30 April 2010 Camera-ready abstracts due
10-11 May 2010 Workshop in Ghent

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

ORGANISATION / PROGRAM COMMITTEE

Yvan Saeys
Thomas Abeel
Sofie Van Landeghem

Bioinformatics and Evolutionary Genomics group
VIB Department of Plant Systems Biology
Ghent University, Belgium

Walter Daelemans
Roser Morante
Vincent Van Asch

CLiPS – Text Mining Group
Faculty of Arts
University of Antwerp, Belgium