Ensemble Learning and Ensemble Pruning Methods with Application to Machine Learning

EURO 2012, 25th European Conference on Operations Research,
July 8-11, 2012, Vilnius, Lithuania
(www.euro-2012.lt)

Organisers: Sureyya Ozogur-Akyuz, Terry Windeatt

EURO is a major international conference in optimisation and operations research which consists of several streams. As part of the Machine Learning and Applications stream, we are organising a session on Ensemble Learning and Ensemble Pruning Methods.

“Ensemble Learning and Ensemble Pruning Method with Application to Machine Learning” session at EURO XXV calls for abstracts describing models for ensemble learning and pruning methods with application to machine learning problems.

Contributors are requested to contact the session organisers first for the submission (invitation) code and then submit their abstracts via the Conference web page (www.euro-2012.lt) by February 29, 2012. The abstracts must be written in English and contain no more than 600 characters (no formulas or mathematical notations are allowed). Please note that each participant is allowed to present one paper at the Conference. The EURO XXV Conference will be held in Vilnius, Lithuania from 8-11 July, 2012.

Instructions
In order to submit a contribution to the sessions, please go to the website below and sign up:
http://www.euro-online.org/conf/display.php?page=welcome

Then please paste the following code 0172f368 in the form, click on “Submit invited abstract” and follow the instructions.

Award for PASCAL members

The best abstract submitted by a member of the PASCAL network will be selected for sponsorship of all the travel expenses.

If you would like to be considered for this selection, please submit your abstract by the 31st of January. (This award is subject to us obtaining sponsorship from PASCAL — application under evaluation.)

Selected authors will be invited to present their work in a 20 min talk.

Tenure track or tenured position in machine learning, probabilistic modelling or data mining

The position is located at Aalto University, Department of Information and Computer Science (http://ics.tkk.fi/en/), Helsinki, Finland, and is open to outstanding individuals who hold a doctorate and have excellent potential for a successful scientific career. Candidates in the areas of machine learning, probabilistic modelling and data mining are especially welcome. Detailed information about the position, as well as the application process and its requirements, is provided at http://dept.ics.tkk.fi/calls/tenuretrack2012/#english

The closing date of the call is 13 January 2012.

Two Postdoctoral Research Fellows – LEAR research group at INRIA Grenoble

The LEAR research group at INRIA Grenoble is hiring two postdoctoral
fellows, each for a two year period. The topics are:

– Action recognition in real-world videos. The research project will
be fixed in discussion with the candidate.

– Object localization in still images. The task is to speed up and
improve 2D localization by designing more appropriate category
models as well as using 3D pose information. 2D image data and
corresponding pose information is available for testing the approach.

INRIA Grenoble and the LEAR team http://lear.inrialpes.fr provide a
stimulating research environment. The working language is
English. Grenoble lies in the south of France and provides excellent
living conditions.

Your profile:
* PhD degree in computer vision or related areas
* Solid programming skills; the projects involve programming in Matlab and C
* Solid mathematics and machine learning knowledge
* Creative and highly motivated
* Fluent in English, both written and spoken

Duration: 2 years

Start date: As soon as possible

Contact: Cordelia Schmid, Cordelia.Schmid@inria.fr

Please send applications via email, including:
* a complete CV, including a list of publications
* graduation marks
* the name and email address of three referees

Special issue on SPEECH SEPARATION AND RECOGNITION IN MULTISOURCE ENVIRONMENTS

COMPUTER SPEECH AND LANGUAGE
http://www.elsevier.com/locate/csl

Special issue on
SPEECH SEPARATION AND RECOGNITION IN MULTISOURCE ENVIRONMENTS

Submission Deadline: DECEMBER 31, 2011

One of the chief difficulties of building distant-microphone speech recognition systems for use in everyday applications is that the noise background is typically `multisource’. A speech recognition system designed to operate in a family home, for example, must contend with competing noise from televisions and radios, children playing, vacuum cleaners, and outdoors noises from open windows. Despite their complexity, such environments contain structure that can be learnt and exploited using advanced source separation, machine learning and speech recognition techniques such as those presented at the 1st International Workshop on Machine Listening in Multisource Environments (CHiME 2011). http://spandh.dcs.shef.ac.uk/projects/chime/workshop/

This special issue solicits papers describing advances in speech separation and recognition in multisource noise environments, including theoretical developments, algorithms or systems.

Examples of topics relevant to the special issue include:
• multiple speaker localization, beamforming and source separation,
• hearing inspired approaches to multisource processing,
• background noise tracking and modelling,
• noise-robust speech decoding,
• model combination approaches to robust speech recognition,
• datasets, toolboxes and other resources for multisource speech separation and recognition.

SUBMISSION INSTRUCTIONS:
Manuscript submissions shall be made through the Elsevier Editorial System (EES) at
http://ees.elsevier.com/csl/
Once logged in, click on “Submit New Manuscript” then select “Special Issue: Multisource Environments” in the “Choose Article Type” dropdown menu.

IMPORTANT DATES:
December 31, 2011: Paper submission
March 30, 2012: First review
May 30, 2012: Revised submission
July 30, 2012: Second review
August 30, 2012: Camera-ready submission

We are looking forward to your submission!

Jon Barker, University of Sheffield, UK
Emmanuel Vincent, INRIA, France

10 Postdoc / Research Associate positions in the new Finnish Center of Excellence in Computational Inference

The new Finnish Center of Excellence in Computational Inference Research (COIN), run by Aalto University and University of Helsinki, announces 10 new postdoc or research associate positions in Computational Inference. The objective of COIN is to push the boundaries of inference in the data-rich world of today and tomorrow, and the COIN consortium brings together several leading researchers in the relevant research area.

Successful candidates will work on fundamental questions of inference and in applications in Intelligent Information Access, Computational Molecular Biology and Medicine, Computational History, Computational Climate, Computational Neuroscience and other directions yet to be determined. Applicants with suitable background in machine learning, mathematics, statistics, computational logic, combinatorial optimization or statistical physics are encouraged to apply.

For further information, please see http://research.ics.tkk.fi/coin/vacancies.shtml

Call for Papers – Intl. Workshop on Social Media Applications in News and Entertainment (SMANE 2012) in conjunction with World Wide Web Conference 2012

http://smane2012.socialsensor.eu/
Lyon, April 16, 2012

*Aims and Scope*
The aim of this workshop is to encourage discussion and
sharing of ideas and research results on social media
research, techniques, and applications, in two crucial
areas: News and Entertainment. The workshop offers an
opportunity to promote interdisciplinary research in
these areas, not only between industry and academia,
but also involving different fields (computer science,
journalism, psychology, sociology, economics, history,
cultural anthropology, business). News and entertainment
have received huge impact from social media technologies,
and yet there are many open technical and social challenges.

SMANE 2012 is accepting proposals addressing some of the
research challenges we face in developing new methodologies,
including data mining and information extraction from
large-scale unstructured social data, real-time aspects,
local vs. global events and news discovery, aggregation of
information from heterogeneous sources, propagation of
information within social networks, and information visualization.
We are also interested in understanding how different technical
approaches can be used to enhance our understanding of user
behavior in social media within the specified contexts.

Topics of interest include but are not limited to:

* Data mining and information extraction from large-scale
social media related to news and entertainment
* Real-time aspects, efficient implementations and architectures
in news and entertainment applications
* Integration of professional and social media sources
in news and entertainment
* Psychological, sociological, and cultural factors
in consumption and production of news and entertainment
* News discovery and serendipity through social media
* Information visualization
* Business models and business needs of social media
in news and entertainment services
* Case studies including large-scale data analysis of
important news and cultural events
* Novel systems and applications

*Paper Submission*
We welcome contributions on related theory, methodology, and
algorithms. We also welcome position papers and interesting
applications and demos. The papers should follow the same
format as the WWW2012 Conference proceedings (ACM SIG format).
All research, applications and position papers should be up
to 6 pages maximum. For submission please use the SMANE2012
Easychair page (https://www.easychair.org/conferences/?conf=smane2012).

For more information:
http://smane2012.socialsensor.eu/submission

*Important Dates*
– 1 February 2012: Paper Submission
– 28 February 2012: Notification of acceptance
– 16 March 2012: Camera Ready paper
– 16 April 2012: Workshop

*Organization*
Yiannis Kompatsiaris, CERTH-Informatics and Telematics Institute, Greece
Alejandro Jaimes, Yahoo! Research, Spain
Daniel Gatica-Perez, Idiap & EPFL, Switzerland
Jochen Spangenberg, Deutsche Welle, Germany

Computer Vision sessions – EURO 2012, 25th European Conference on Operations Research, July 8-11, 2012, Vilnius, Lithuania

* Computer Vision sessions *
EURO 2012, 25th European Conference on Operations Research,
July 8-11, 2012, Vilnius, Lithuania
(www.euro-2012.lt)

Call for Abstracts

Organisers: Teo de Campos, Fei Yan and Ivan Reyer

EURO is a major international conference in optimisation
which consists of several streams. As part of the
*Machine Learning and Applications stream*,
we are organising two sessions on Computer Vision (CV).
These sessions will enable CV researchers
to present their work to an audience of people interested in
CV, machine learning and optimisation, and it will thus
broaden their network of connections in these Teo de Campos, Fei Yan and Ivan Reyer
fields.

Abstracts (up to 600 characters) are welcome in any area of
computer vision, in particular works presenting applications
of machine learning or optimisation to computer vision problems.
Selected authors will be invited to present their work in a 20 min talk.

* Award for PASCAL members *

The best abstract submitted by a member of the PASCAL network
will be selected for sponsorship of all the travel expenses.
If you would like to be considered for this selection,
please submit your abstract by the 31st of January.
(This award is subject to us obtaining sponsorship from PASCAL
— application under evaluation.)

* Instructions *

In order to submit a contribution to the vision sessions, please
go to the website below and sign up:
http://www.euro-online.org/conf/display.php?page=welcome
Then please paste the following code 2252d763 in the form,
click on “Submit invited abstract” and follow the instructions.

ECML-PKDD 2012 – The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases

September 24-28, 2012
Bristol, UK

Home

* Key Dates
– Abstract submission deadline: Thu 19 April 2012
– Paper submission deadline: Mon 23 April 2012
– Early author notification: Mon 28 May 2012
– Regular author notification: Fri 15 June 2012
– Camera-ready submission: Fri 29 June 2012

* Call For Papers
The European Conference on “Machine Learning” and “Principles and Practice of Knowledge Discovery in Databases” (ECML-PKDD) provides an international forum for the discussion of the latest high-quality research results in all areas related to machine learning and knowledge discovery in databases and other innovative application domains.
Submissions are invited on all aspects of machine learning, knowledge discovery and data mining, including real-world applications.

The overriding criteria for acceptance will be a paper’s:
– potential to inspire the research community by introducing new and relevant problems, concepts, solution strategies, and ideas;
– contribution to solving a problem widely recognized as both challenging and important;
– capability to address a novel area of impact of machine learning and data mining.
Other criteria are scientific rigour and correctness, challenges overcome, quality and reproducibility of the experiments, and presentation.

* Proceedings and Special Journal Issues
The conference proceedings will be published by Springer in the Lecture Notes in Artificial Intelligence series (LNAI).
Authors of selected papers will be invited to submit a significantly extended version of their paper to two post-conference special issues of the journals “Data Mining and Knowledge Discovery” and “Machine Learning”.

* Submissions
All aspects of the submission and notification process will be handled online via the CMT conference management toolkit at https://cmt.research.microsoft.com/ECMLPKDD2012/ .
The papers must be written in English and formatted according to the Springer LNAI guidelines. Authors instructions and style files can be downloaded at:
http://www.springer.de/comp/lncs/authors.html
The maximum length of papers is 16 pages in this format. Overlength papers will be rejected without review.
Papers submitted should report original work; ECML-PKDD 2012 will not accept any paper which, at the time of submission, is under review or has already been accepted for publication in a journal or another conference. Authors are also expected not to submit their papers elsewhere during the review period. To minimize the impact of this constraint, a significant proportion of rejected papers will be notified at the early notification date.

* Reviewing process
Papers submitted to ECML-PKDD 2012 will normally be reviewed by three referees. The review process is single-blind (reviewer identities unknown to authors) and there will be no opportunity for author rebuttal. This decision was made to minimize reviewer workload and to concentrate it in time, which may ultimately result in better quality reviews and decisions. If necessary, a discussion will take place among the reviewers of a paper until a decision is reached.

* Contact
You can contact the Program Committee Chairs at ECMLPKDD2012pcchairs@cs.bris.ac.uk .
Nello Cristianini, Tijl De Bie and Peter Flach (Intelligent Systems Lab, University of Bristol, UK)

JMLR Special Topic on Gesture Recognition – Second call for papers – Deadline May 15, 2012

The Journal of Machine Learning Research is preparing a special topic on gesture recognition.
Papers relevant to this topic may be submitted to the journal. Please also send email to the guest Editors with your paper number at gesture@ clopinet . com.

The participants of the Gesture Recognition Challenge are strongly encouraged to submit a paper.

We also invite other contributions relevant to gesture recognition, including:
– Algorithms for gesture and activity recognition, in particular addressing
o Learning from unlabeled or partially labeled data
o Learning from few examples per class, and transfer learning.
o Continuous gesture recognition and segmentation
o Deep learning architectures, including convolutional neural networks
o Gesture recognition in challenging scenes, including cluttered/moving backgrounds or moving cameras, or scenes where multiple persons are present.
o Integrating information from multiple channels (e.g., position/motion of multiple body parts, hand shape, facial expressions).
– Data representations
– Applications pertinent to the workshop topic, such as involving:
o Video surveillance
o Image or video indexing and retrieval
o Recognition of sign languages for the deaf
o Emotion recognition and affective computing
o Computer interfaces
o Virtual reality
o Robotics
o Ambiant intelligence
o Games
– Datasets and benchmarks

The papers of the special topic of JMLR will also be reprinted as a book in the CiML series of Microtome.

Guest Editors: Isabelle Guyon and Vassilis Athitsos
gesture@ clopinet . com.

Gesture Recognition Challenge

Dear colleagues,

The Pascal2 sponsored Gesture Recognition Challenge is now open to submit entries:
http://www.kaggle.com/c/GestureChallenge/

Develop a recognizer for the Microsoft Kinect (TM) and win prizes donated by Microsoft:

* First place: USD 5,000
* Second place: USD 3,000
* Third place: USD 2,000

and up to USD 100,000 of Intellectual Property licenses if your algorithm interests Microsoft.

View some data examples: https://sites.google.com/a/chalearn.org/gesturechallenge/data/data-examples

Thank you in advance for your participation!

The organizers