News Archives

BMVC 2012: Prize for the Best Demo/Video/Supplementary material

Update: There will be a prize for the best demo/video/supplementary material. 3 August 2012.

BMVC 2012 offers the opportunity to showcase your research to the computer vision community.
The following two types of contributions are both encouraged:

(1) Live demonstrations showing the effectiveness of computer vision methods. These are not limited to methods described in papers that will appear at BMVC 2012. Prospective demo participants should submit the application form (http://bmvc2012.surrey.ac.uk/demo_application_bmvc12.pdf)
via email to the Demo and Video Chair. Commercial products should be presented as part of the exhibits rather than demonstrations. Accepted demonstrations will be held concurrent with the poster sessions.

(2) Any precompiled videos showing the results of computer vision related research. Videos should not exceed three minutes in length or 100MB in size. Prospective video participants should submit an FTP/HTTP link to the video via email. Videos advertising commercial products are not appropriate. Accepted videos will be shown throughout the conference.

Please be advised that at least one of the authors of each demo/video must be registered for the conference. The conference also reserves the right to select demos and videos based on the degree of appropriateness for BMVC.

24 August 2012 Demo and video submission due
27 August 2012 Demo and video notification

For further information, please contact the Demo and Video Chair.

Looking forward to your submissions,

Fei Yan, BMVC 2012 Demo and Video Chair
f.yan@surrey.ac.uk
Centre for Vision, Speech and Signal Processing, University of Surrey Guildford, United Kingdom
GU2 7XH

Assistant Professor Position at Telecom ParisTech (France)

Associate Professor in statistical learning

The group dedicated to Research in Statistics (the research group STA), within the Signal & Image processing department (the TSI Dpt.), is recruiting an Assistant Professor in the domain of statistical machine-learning. All fields related to statistical learning are of interest for the team. A specialization in reinforcement learning or optimization will be favorably considered but is not mandatory.

Research

• Academic research programs in statistical learning will be carried out.
• Research results will be published in leading journals and conferences. Activities in scientific bodies, organization of special sessions, workshops as well as involvements in committees of scientific conferences will contribute to the visibility.
• The research activities will rely on the team expertise, which covers both theoretical and methodological works in Bayesian estimation, statistical learning, reinforcement learning, and distributed statistics with collaborative computing.
• Contributing to scientific projects involving industrial partners will be done by participating to proposals to national and international research project calls, in the context of an academic chair or by co-supervising PhD theses (CIFRE thesis, involving industrial partners). The current applications considered within the group often deal with signal processing applications, which encompass forecasting, design of computer experiments, source separation, localization/tracking/cartography, control in multi-agent system.
Teaching

• In the domain of statistics and machine learning, teaching at Telecom ParisTech mainly occurs at the level of bachelor or master courses, as well as in specialized training courses. The master courses include courses in joint master with partner universities, such as MVA Master.

Skills

• Education : PhD or equivalent.
• An international postdoctoral experience is welcome but not mandatory.
• English: fluent; French: good or the candidate should be willing to improve it.

Knowledge and necessary experience

• Research publications in statistical learning (non-parametric statistics, machine learning or statistical signal processing)
• Teaching experience at the university level.

Preferred skills

• Knowledge on the numerical aspects of statistical learning and data processing.
• Theoretical or practical knowledge in optimization.
• Theoretical or practical knowledge in reinforcement learning

Other Qualities and skills

• Capacity to work in a team and develop good relationships with colleagues and peers
• Good writing and pedagogical skills

Additional information

In the context of the Paris Saclay University, activities in stochastic modeling and statistical data processing at the STA group are complementary with that conducted in the Labs LMO, CMAP and CMLA. STA and these groups are partners of the Labex LMH. The Labex
DigiWorlds also include some of the research activities of STA, for instance through partnerships with the labs LRI and LIMSI.

The position

• Permanent position
• Place of work: Paris until 2017, and then Saclay (Paris outskirt)
• For more info on being an Associate Professor at Telecom ParisTech (in French)
http://www.telecom-paristech.fr/telecom-paristech/offres-emploi-stages-theses/recrute-enseignants-chercheurs.html

Application

Candidacy are done electronically by sending a mail to
recrutement@telecom-paristech.fr

The candidacy should include :
• A complete and detailed curriculum vitae
• A letter of motivation,
• A document detailing past activities of the candidate in Teaching and Research: the two types
of activities will be described with the same level of detail and rigor.
• The text of the main publications,
• The names and addresses of two references,
• A short teaching project and a research project (maximum 3 pages)

Important dates (provisional)
• September 15 2012: application deadline

Contact :
François Roueff (Head STA group), www.telecom-paristech.fr/~roueff
Yves Grenier (Head TSI department), www.telecom-paristech.fr/~grenier/

Other web Sites :

Département Traitement du Signal et des Images: http://www.tsi.telecom-paristech.fr/
Groupe STA: http://www.tsi.telecom-paristech.fr/sta
Télécom ParisTech: http://www.telecom-paristech.fr/

Algorithmic Learning Theory and Discovery Science, October 29-31

Dear PASCAL colleagues,

The 23rd International Conference on Algorithmic Learning Theory (ALT
2012) will be held in Lyon, France, at Université Lumière Lyon 2, on October 29-31, 2012.

The conference is on the theoretical foundations of machine learning and is a PASCAL event (sponsored by the PASCAL network… this is why you get this email!).

The conference will be co-located with the 15th International Conference on Discovery Science (DS 2012); the joint website of these conferences is:
http://eric.univ-lyon2.fr/alt-ds-2012/

The invited speakers include:
— Luc De Raedt (Department of Computer Science, Katholieke Universiteit Leuven, Belgium)
— Shai Shalev-Shwartz (School of Computer Science and Engineering, The Hebrew University of Jerusalem, Israel)
— Pascal Massart (Département de Mathématiques, Université Paris-Sud, Orsay, France)
— Toon Calders (Faculty of Math and Computer Science, Eindhoven University of Technology, The Netherlands)
— Gilbert Ritschard (Department of Economics and Institute for Demographic and Life Course Studies, Université de Genève)

The papers to be presented at the two conferences were selected: Their lists can be found on the indicated website.
(The detailed programs will be available mid-September.)

Please note that the early registration deadline (with a reduced fee) is September 7.

Meanwhile: Enjoy your summer!

Gilles Stoltz, on behalf of the PC chairs and conference chairs

PhD or Postdoc position at the University of Stuttgart

The Institute of Stochastics and Applications (ISA) of the Department of Mathematics at the Universität Stuttgart is offering a research position for a

Post-Doc or PhD Student

available starting October 1, 2012 or later. The appointment is for up to three years at salary scale up to 100% TVL-13. The position is funded within joint DFG-project with the Institute for Natural Language Processing (IMS) at the Universität Stuttgart.

ISA’s part of the project focuses on the design and mathematical analysis of new, fully adaptive methods for cluster analysis, which are then applied to sentiment analysis by the IMS. Solid mathematical knowledge, in particular in stochastics and functional analysis are required. Moreover, a close cooperation with the computer scientists at the IMS is expected.

Universität Stuttgart wishes to increase the proportion of female academic staff and, for this reason, especially welcomes applications from women.
Severely challenged persons will be given preference in case of equal qualifications.
Please, send applications in electronic form (pdf) to

Prof. Dr. Ingo Steinwart (applications@isa.uni-stuttgart.de)

by September 15, 2012.

BMVC 2012: bursaries and call for impromptu contributions

—————————————-
STUDENT BURSARIES
—————————————-
Link: http://bmvc2012.surrey.ac.uk/bursary.php
Deadline: Friday, 10 August

Thanks to PASCAL sponsorship, we will provide bursaries for up to two PASCAL student members who otherwise would not be able to attend the conference.
Additionally, the BMVA will provide 10 bursaries, but they will give priority to UK students.

—————————————-
CALL FOR DEMOS AND VIDEOS
—————————————-
Link: http://bmvc2012.surrey.ac.uk/cfp.php
Deadline: Friday, 24 August

Please follow the link above for further information.

—————————————-
CALL FOR IMPROMPTU POSTERS
The 4th UK Students Workshop (BMVW)
—————————————-
Link: http://bmvc2012.surrey.ac.uk/workshopPosters.php
Deadline: Monday, 20 August

For students in the UK

In addition to the workshop programme in which full peer-reviewed papers and invited talks will be presented, we are also welcoming “impromptu” contributions to be presented as posters.

The goal of this call is to make this workshop more inclusive so that students can discuss their ongoing research and preliminary results with a wide computer vision public.
Published material is also welcome, excluding posters that have already been presented at the main conference.

In order to be considered for inclusion in this program, please submit a short abstract (about 10 lines) using the form at the web page above.

Best regards,

Teo de Campos
PS: please send any query about BMVC to bmvc2012@list.surrey.ac.uk

CFP IbPRIA 2013 – 6th Iberian Conference on Pattern Recognition and Image Analysis

CALL FOR PAPERS

IbPRIA 2013 – 6th Iberian Conference on Pattern Recognition and Image Analysis Madeira, Portugal June 5-7, 2013

http://www.ibpria.org/2013

The Iberian Conference on Pattern Recognition and Image Analysis
(IbPRIA) is an international event co-organised every two years, by the Portuguese and Spanish Associations for Pattern Recognition.

IbPRIA is a single track conference that includes tutorials, special sessions, invited speakers as well as oral and poster presentations.
The conference is intended to act as a forum for research groups, engineers and practitioners to present recent results, algorithmic improvements and promising future directions in pattern recognition and image analysis.

SCOPE
The conference is looking for new theoretical results, techniques and main applications on any aspect of pattern recognition and image analysis, including but not restricted to the following topics:

Pattern Recognition
Image Analysis
Computer Vision
Multimedia Systems
Statistical and Structural Pattern Recognition Machine Learning and Data Mining Computer Vision for Robotics and Automation Bioinformatics Image Coding and Processing Shape and Texture Analysis Information Systems Biometric Technologies Speech Recognition Document Processing Character and Text Recognition Robotics Remote Sensing Industrial Applications of Pattern Recognition Special Hardware Architectures

PAPER SUBMISSION
Papers should describe original and unpublished work on the topics of the conference. Prospective authors should prepare a full paper, written in english, not exceeding
8 pages and must submit it
electronically. Further information can be found on the conference
website: http://www.ibpria.org/2013

Each paper will be blind-reviewed by at least two reviewers and will be accepted based on its originality, signficance and clarity. All accepted papers will appear in the conference proceedings, and will be published in Springer Lecture Notes in Computer Science Series, LNCS Series. A copy of the proceedings will be distributed to all participants at the Conference.

Moreover, the IbPRIA 2013 conference provides additional opportunities for journal publicaction and best paper awards. Contacts are being established with an indexed journal for a special issue.

Submission implies that at least one of the authors has to register and to present the communication at the conference if the paper is accepted.

IMPORTANT DATES

Submission of papers November 19, 2012
Notification of acceptance January 19, 2013 Camera-Ready February 2, 2013

For more information please visit http://www.ibpria.org/2013

CfP: BBCI Workshop 2012 – Submission Extended

Call for Participation
Call for Poster Submissions

BBCI Workshop 2012 on Advances in Neurotechnology September 17-19, Berlin, Germany

Official: http://bbci12.ml.tu-berlin.de/

************************************************************************

Important Dates
===============

Submission Date: 2012-08-12
Notification of Acceptance: 2012-08-17
Workshop Date: 2012-09-17 – 2012-09-19

Organization
============

Bernstein Focus: Neurotechnology (BFNT-B) Humboldt University Berlin (HU) Berlin Institute of Technology (TUB) Charité – University Medicine Berlin Bernstein Center Computational Neuroscience Berlin (BCCN-B)

– Benjamin Blankertz (chair), Berlin Institute of Technology
– Ulrich Egert, University of Freiburg
– Siamac Fazli (poster co-chair), Berlin Institute of Technology
– Dario Farina, University of Göttingen
– Stefan Haufe (poster co-chair), Berlin Institute of Technology
– Klaus-Robert Müller (chair), Berlin Institute of Technology
– Susanne Schreiber (co-chair), Humboldt University Berlin
– Michael Tangermann (poster chair), Berlin Institute of Technology
– Jochen Triesch, University of Frankfurt

Matthias L. Jugel, BFNT-B/Industry
Imke Weitkamp, BFNT-B/Coordination

Description
===========

Different approaches to Brain-Computer Interfaces have been developed, each one with specific solutions that range from understanding and explaining cognitive functions over communicating with real and virtual environments by thought alone to real-time monitoring of cognitive states.

The Advances in Neurotechnology Workshop presents an overview, in-depth tutorials and discussions on the latest research at all levels of Neurotechnology and BCI research. What is presented will cover invasive recording, semi-invasive ECoG, non-invasive EEG, non-invasive NIRS and fMRI measurement and potential combinations of the different methods. Additional focus will be devoted to advances in data analysis.

The poster session following the tutorials will cross over into the BBCI barbecue, smoothing discussions with drinks and food.

Following the workshop there will be a summerschool on selected topics in BCI and neurotechnology from September 20th to 28th.
It has educational tutorials in the morning session (two tutorials of 2h each, held by internationally renowned researchers), and practical hand-ons sessions in the afternoon. The practical sessions are partly multi-track and will allow researchers in BCI/neurotechnology to complement their expertise in the interdisciplinary field.

Submission
==========

Please send your posters (in PDF) or abstracts (max. 2 pages, PDF or plain text) to the poster chair Michael Tangermann , no later than 2012-07-30.

Poster size should be a maximum of A0 (width x height: 841mm × 1189mm)

Confirmed Speakers
==================

– Felix Biessmann, Berlin Institute of Technology
– Benjamin Blankertz, Berlin Institute of Technology
– Mark Cohen, UCLA
– Tom Eichele, Haukeland University Hospital, Bergen, Norway
– Dario Farina, BFNT Göttingen
– Rainer Goebel, University Maastricht
– John-Dylan Haynes, Bernstein Center for Computational Neuroscience
– Bo Hong, Tsinghua University, Beijing, China
– Yukiyasu Kamitani, ATR Computational Neuroscience Laboratories, Kyoto
– Motoaki Kawanabe, ATR Computational Neuroscience Laboratories, Kyoto
– Christof Koch, California Institute of Technology
– Andrea Kübler, Universität Würzburg
– Seong-Whan Lee, Dept. of Brain and Cognitive Engineering, Korea
– Donatella Mattia, Fondazione Santa Lucia, IRCCS, Italy
– José del R. Millán, Ecole Polytechnique Fédérale de Lausanne (EPFL)
– Klaus-Robert Müller, Berlin Institute of Technology
– Gernot Müller-Putz, TU Graz
– Gerwin Schalk, Wadsworth Center

Venue
=====

Audimax der Humboldt-Universität zu Berlin, Unter den Linden 6 / Dorotheenstr. 17-19, Berlin, Germany

Workshop Fees
=============

Business: 300 EUR
Standard: 250 EUR

* Early Registration Discount (until 2012-08-19)

Academic : 200 EUR
Bernstein: 100 EUR
Students : 50 EUR

Funding
=======

The workshop is supported by the Bernstein Focus: Neurotechnology Berlin.

ECML PKDD 2012 – Call for Participation – Early Registration: July 31

*** ECML PKDD 2012 *** CALL FOR PARTICIPATION *** EARLY REGISTRATION:
JULY 31 ***

The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) will take place in Bristol, UK from September 24th to 28th, 2012.

ECML-PKDD is the prime European scientific event in machine learning and data mining. It will feature presentations of contributed papers and invited speakers, a wide program of workshops and tutorials on the first and last days, a discovery challenge, and a DINe track with demo, industry, and ‘nectar’ talks.

Keynote talks

Workshops

Tutorials

The list of accepted research track papers can be accessed at http://ecmlpkdd2012.webfactional.com/ .

The early registration deadline with reduced registration fee is July 31st, 2012.

Accommodation is booked directly with the hotels: reduced rates are available on a first-come-first-serve basis, so please act now to avoid disappointment!

Registration

Hotels

We look forward to welcoming you in Bristol this September.

Peter Flach, Tijl De Bie and Nello Cristianini, University of Bristol ECML-PKDD 2012 General and Programme Chairs ECMLPKDD2012@cs.bris.ac.uk

Open PhD Position: Learning Representations of large-scale Multi-relational Data. Application to link prediction in Knowledge Bases.

Supervision : Antoine Bordes and Yves Grandvalet, CNRS – Université de Technologie de Compiègne.

Dates : position open from November 1st, 2012 to January 1st, 2013.
(earlier or later start dates can be negotiable)

Context :

A PhD studentship is available as part of the French ANR funded project EVEREST on “lEarning high-leVEl REpresentations of large Sparse Tensors”
being undertaken by Heudiasyc laboratory in Université de Technologie de Compiègne, with a partnership of Xerox Research Center Europe (Grenoble, France). See https://www.hds.utc.fr/everest for more details on the project.

The student will be based in the Heudiasyc laboratory in Compiègne
(France) and join the DI team headed by Yves Grandvalet. He/she will be supervised by Antoine Bordes (https://www.hds.utc.fr/~bordesan) and Yves Grandvalet (https://www.hds.utc.fr/~grandval). Heudiasyc is a joint laboratory with the Université de Technologie de Compiègne (UTC) and the French governmental agency for research (CNRS). In 2011, it was rated A+ (the highest rate) by the French Research evaluation agency (AERES).
Heudiasyc fosters interdisciplinary research on information science and technology including machine learning, uncertain reasoning, operations research, robotics and knowledge management. In 2011 Heudiasyc was awarded with an excellence project (LabEx) on the « Control of Technological Systems of Systems ». The project will also include a collaboration with Xerox Research Center Europe, through interactions with Guillaume Bouchard (http://www.xrce.xerox.com/).

The studentship is funded by an ANR project and will start between November 1st, 2012 and January 1st, 2013. The studentship is funded for 3 years (currently 1850€ per month — gross salary).

Requirements :

The PhD candidate should have or expect to obtain a MSc or equivalent in computer science or mathematics. The following qualities are desirable :
strong interests in machine learning or statistics ; excellent record of academic and/or professional achievement ; strong mathematical skills ; strong programming skills ; good written and spoken communication skills in French or English. The ideal candidate should be able to conduct theoretical research, but also implement and test models on very large datasets.

Project description :

Huge amounts of structured and relational data are available in many domains of engineering, industry or research ranging from the Semantic Web, or bioinformatics to recommender systems. As a result, knowledge bases (KBs), such as Freebase, WordNet or GeneOntology, became essential tools for storing, manipulating and accessing information, but they are also incomplete, imprecise and far too large to be used as efficiently and broadly as they could. Hence, there is need for methods able to summarize, complete or merge these large databases. This is the motivation of the project.

The data of these KBs is naturally represented as a so called multi-relational graph consisting of nodes associated with entities and of different types of edges between nodes corresponding to the different types of relations. The first phase of the project will consist in developing and evaluating an approach based on energy-based learning [4] for deriving high-level representations of such multi-relational graphs.
By high-level, we mean that these representations should enable to condense the original databases, to complete them by filling in missing values, and to ease their matching and merging. Energy-based models could provide a new direction to deal with multi-relational data, which will be compared with traditional low-rank methods [5] or Bayesian approaches [2,6]. They have already shown some promising preliminary results [1]. A goal of the thesis will also be to bridge energy-based learning in this context and tensor factorization [3].

In a second phase, the qualities of these new representations will be applied to link prediction, i.e. uncover relationships in a multi-relational graph that probably exist but have not been observed, on benchmark data and on real-world data provided by Xerox.

References :

[1] Bordes, A., J. Weston, R. Collobert, and Y. Bengio. “Learning Structured Embeddings of Knowledge Bases.” Proceedings of the International Conference on Artificial Intelligence (AAAI). AAAI Press, 2011.
[2] Kemp, C., J.B. Tenenbaum, T.L. Griffiths, T. Yamada, and N. Ueda.
“Learning Systems of Concepts with an Infinite Relational Model.”
Proceedings of the International Conference on Artificial Intelligence (AAAI). AAAI Press, 2006.
[3] Koida, T.G., and B.W. Bader. “Tensor Decompositions and Applications.”
SIAM Review, 2008.
[4] Lecun Y, Chopra S, Hadsell R, marc’aurelio R, Huang f (2006) A tutorial on Energy-Based learning. In: Bakir G, Hofman T, sch ̈olkopf B, Smola A, Taskar B (eds) Predicting Structured Data, MIT Press [5] Nickel, M., V. Tresp, and H.-P. Kriegel. “A Three-Way Model for Collective Learning on Multi-Relational Data.” Proceedinsg of the International Conference on Machine Learning (ICML). Bellevue, WA:
Omnipress, 2011.
[6] Sutskever, I., R. Salakhutdinov, and J.B. Tenenbaum. “Modelling Relational Data using Bayesian Clustered Tensor Factorization.” Avances in Neural Information Processing Systems (NIPS). Vancouver, BC, 2010.

Contact and application :

Applicants should send (preferably as a single PDF file):
* a CV
* a brief statement of research interests
* references (with email and phone number)
* their academic transcript
* a sample of strongest publications or course work (e.g. Master thesis)

Applications and inquiries should be directed to:
* Antoine Bordes – antoine.bordes@hds.utc.fr
* Yves Grandvalet – yves.grandvalet@hds.utc.fr

MLSB 2012: Call for Participation

=============== Call for Participation ===============

Machine Learning in Systems Biology
September 8 and 9, 2012
Basel, Switzerland
http://mlsb.cc

===============================================
We invite you to join us for the 6th installment of

Machine Learning in Systems Biology (MLSB) 2012,

which will be held as a 2-day ECCB workshop on September 8 and 9
in Basel, Switzerland.

The full program of MLSB 2012 can be found online on http://mlsb.cc
The highlights of MLSB 2012 include four invited talks by

* Uwe Ohler, Duke University & Berlin Institute for Medical Systems Biology/Max Delbrück Center & Humboldt Universität Berlin
Deciphering transcription regulation: from individual sites to cell type specific expression
* Yves Moreau, KU Leuven
Kernel methods for genomic data fusion
* Pascal Falter-Braun, TU München
Signatures of evolution and systems organization from an Arabidopsis interactome network map

* Ben Lehner, Centre for Genomic Regulation, Barcelona
The genetics of individuals: why would a mutation kill me, but not you?

Please note the early registration for MLSB/ECCB on July 31, 2012 (for registration visit http://www.eccb12.org/registration-info).

We are looking forward to meeting you in Basel!

Best regards,
Karsten Borgwardt and Gunnar Rätsch


Karsten Borgwardt
http://agkb.is.tuebingen.mpg.de

Gunnar Rätsch
http://raetschlab.org