News Archives

ECCV10 Workshop: Sign Gesture & Activity

International Workshop on Sign Gesture and Activity 2010

Saturday September 11, 2010, Hersonissos, Heraklion, Crete, Greece in conjunction with ECCV 2010.

www.ee.surrey.ac.uk/Personal/R.Bowden/SGA2010

Topic: The workshop will bring together researchers from vision, learning and related areas to present and discuss the recognition of spatio-

temporal motion of people across a broad range of application areas ranging from sign language recognition through to gesture and activity.

Important Dates:

Submission deadlines: Wed, 16th June 2010

Acceptance decisions: Thurs, 8th July 2010

Camera-ready papers: Tue, 13th July 2010

The list of topics will include (but are not limited to):

• Continuous Sign Language Recognition & analysis

• Non-Manual Features and Facial expression recognition

• Feature Extraction for recognition

• Human torso tracking and modelling

• Hand Shape Classification

• Gesture Recognition

• Activity and Action Recognition

• Facial expression analysis

• Lip Reading

• Fusion methods for Recognition

• Multimodal human behaviour analysis

• Non Verbal Communication

• Affective Computing

• Hand and Face Tracking

• Corpora for training and testing

• Semi-automatic corpora annotation tools

• Probabilistic sequence modelling

Workshop organisers: Richard Bowden, Uni of Surrey, UK < r.bowden@surrey.ac.uk>

Philippe Dreuw, RWTH Aachen Uni, DE

Petros Maragos, NTUA, Greece,

Justus Piater, Uni of Liège, Belgium,

Submission site: https://cmt.research.microsoft.com/SGA2010

Workshop site: http://www.ee.surrey.ac.uk/Personal/R.Bowden/SGA2010

Main Conference site: http://www.ics.forth.gr/eccv2010/intro.php

KDD-2010 CfP for Pascal Network

=============================================================================
Call for Participation
16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD-2010)
July 25-28, 2010
Washington, DC
http://www.kdd.org/kdd2010/

Key Dates
Early registration deadline: May 15, 2010
Regular registration deadline: June 30, 2010

Registration: http://www.kdd.org/kdd2010/registration.shtml
Accepted Papers: http://www.kdd.org/kdd2010/papers.shtml
Workshops: http://www.kdd.org/kdd2010/workshops.shtml
Tutorials: http://www.kdd.org/kdd2010/tutorials.shtml
KDD Cup: http://www.kdd.org/kdd2010/kddcup.shtml

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

The 16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
will be held in Washington, DC on July 25-28, 2010. KDD is the
premier international forum for data mining researchers and
practitioners from academia, industry, and government to share their
ideas, research results and experiences. KDD-2010 will feature
keynote presentations, oral paper presentations, poster sessions,
workshops, tutorials, panels, exhibits, demonstrations, and the KDD
Cup competition.

PAPERS

The conference will feature 102 Research Track papers and 20
Industrial and Government Track papers. In addition to oral
presentations, all papers will be showcased during evening poster
sessions. Full details are available at
http://www.kdd.org/kdd2010/papers.shtml.

WORKSHOPS

* Mining and Learning with Graphs Workshop 2010 (MLG-2010)
* Large-scale Data Mining: Theory and Applications (LDMTA-2010)
* Useful Patterns (UP)
* Social Media Analytics (SOMA 2010)
* KDD Cup 2010: Improving Cognitive Models with Educational Data
Mining (KDD Cup 2010)
* 9th International Workshop on Data Mining in Bioinformatics (BIOKDD10)
* Tenth International Workshop on Multimedia Data Mining(MDMKDD 2010)
* The Fourth International Workshop on Data Mining and Audience
Intelligence for Online Advertising (ADKDD’10)
* Human Computation Workshop (HCOMP 2010)
* ACM SIGKDD Workshop on Intelligence and Security Informatics (ISI-KDD)
* The 4th International Workshop on Knowledge Discovery from Sensor
Data (SensorKDD)
* The 4th SNA-KDD Workshop on Social Network Mining and Analysis (SNAKDD 2010)
* Novel Data Stream Pattern Mining Techniques (StreamKDD)
* Discovering, Summarizing and Using Multiple Clusterings (MultiClust)

TUTORIALS

* Large-scale Data Mining: MapReduce and Beyond; Jimeng Sun (IBM
Research), Spiros Papadimitriou (IBM Research), Rong Yan (Facebook)
* New Developments in the Theory of Clustering; Sergei Vassilvitskii
(Yahoo! Research), Suresh Venkatasubramanian (U. of Utah)
* Temporal Pattern Mining in Symbolic Time Point and Time Interval
Data; Fabian Moerchen (Siemens Corporate Research)
* A Tutorial on Learning through Exploration; Alina Beygelzimer (IBM
Research), John Langford (Yahoo! Research)
* Geometric Tools for Graph Mining of Large Social and Information
Networks; Michael W. Mahoney (Stanford)
* Mining Web Search and Browse Logs: Challenges, Methods, and
Applications; Daxin Jiang (Microsoft Research Asia), Jian Pei (SFU),
Hang Li (Microsoft Research Asia)
* Privacy-aware Data Mining in Information Networks; Kun Liu (Yahoo!
Research), Gerome Miklau (UMass), Jian Pei (SFU), Evimaria Terzi
(Boston U.)
* Introduction to Graphical Models for Data Mining; Arindam Banerjee
(U. of Minnesota)
* Mining Heterogeneous Information Networks; Jiawei Han (UIUC), Yizhou
Sun (UIUC), Xifeng Yan (UCSB), Philip S. Yu (UIC)
* Outlier Detection Techniques; Hans-Peter Kriegel (LMU Munich), Peer
Kroger (LMU Munich), Arthur Zimek (LMU Munich)
* Recommender Problems for Web Applications; Deepak Agarwal (Yahoo!
Research), Bee-Chung Chen (Yahoo! Research)
* Indexing and Mining Time Sequences; Christos Faloutsos (CMU), Lei Li (CMU)

REGISTRATION

http://www.kdd.org/kdd2010/registration.shtml

We hope to see you in Washington, DC!

Xerox – Two Research Scientists – Machine Learning and Machine Translation

Positions: Two Research Scientists, Machine Translation and Machine Learning

The Cross-Language Technologies (CLT) group of the Xerox Research
Centre Europe conducts research in Statistical Machine Translation
and Cross-Language Information Retrieval, Categorization and
Clustering using and extending advanced machine learning
methods. The team is part of the PASCAL 2 European Network of
Excellence, ensuring a strong network of academic collaboration. We
are opening two positions for researchers interested in Statistical
Machine Translation. For the first position, we are looking for a
candidate with a strong Machine Learning background; for the second
position for a candidate with a strong Statistical Machine
Translation (SMT), or statistical Natural Language Processing (NLP)
background.

Required experience and qualifications.

For the first position:

* PhD in computer science, statistics or mathematics with focus on
Machine Learning.
* Acquaintance with SMT or NLP is a plus.

For the second position:

* PhD in computer science or computational linguistics with focus on
SMT or statistical NLP.
* Acquaintance with Machine Learning is a plus.

For both positions:

* Strong publication record and evidence of implementing systems.
* A good command of English, as well as open-mindedness and the will
to collaborate within a team.

Expected starting date: September 2010
Duration: 18 months

Application instructions

Please email your CV and covering letter, with message subject
“Cross-Language Technologies Researcher” to xrce-candidates and to
nicola dot cancedda at xrce.xerox.com. Inquiries can be sent to
nicola dot cancedda at xrce.xerox.com.

XRCE is a highly innovative place and we strongly encourage
publication and interaction with the scientific community. About
XRCE The Xerox Research Centre Europe (XRCE) is a young, dynamic
research organization, which aims at creating innovative document
technologies to support growth in Xerox content and document
management services across the different Xerox businesses XRCE is
both a multicultural and multidisciplinary organization set in
Grenoble, France. Our domains of research stretch from the social
sciences to computing. We have renowned expertise in natural
language applications, work practice studies, image-based document
processing, distributed applications and knowledge management
agents. The diversity of culture and disciplines at XRCE makes it an
interesting and stimulating environment to work in, leading to often
unexpected discoveries! XRCE is part of the Xerox Innovation group
made up of 800 researchers and engineers in four world-renowned
research and technology centres. Xerox is an equal opportunity
employer. XRCE ensures equal opportunities for all.

The “Charte de la diversite'”, adopted by Xerox, proves our
engagement in favour of cultural, ethnic and social diversity. The
Grenoble site is set in a park in the heart of the French Alps in a
stunning location only a few kilometers from the city centre. The
city of Grenoble has a large scientific community made up of
national research institutes (CNRS, Universities, INRIA) and private
industries. Stimulated also by the presence of a large student
community, Grenoble has become a resolutely modern city, with a rich
heritage and a vibrant cultural scene. It is a lively and
cosmopolitan place, offering a host of leisure opportunities. Winter
sports resorts just half an hour from campus and three natural parks
at the city limits make running, skiing, trekking, climbing and
paragliding easily available. Grenoble is close to both the Swiss
and Italian borders.

(French speaking) Position opening in Paris

A position of assistant professor is available at ESPCI-ParisTech (http://www.espci.fr), a renowned scientific education and research institute in Paris.

Research will be carried out at the SIGMA (SIGnal processing and MAchine Learning) laboratory of ESPCI-ParisTech (http://www.neurones.espci.fr).

Teaching will include mainly laboratory sessions in Electronics and in Process Control during the first year of the curriculum (http://www.espci.fr/formations/ingenieur-espci).

The ideal candidate will have an excellent background in machine learning research, and a strong motivation for interdisciplinary research. A very good level in French (read, written and spoken fluently) is mandatory.

Detailed information on the position and on the application procedure is available at
http://www.neurones.espci.fr

Post-Doctoral Opportunities in Computational Statistics

As a result of recent research grant awards there are outstanding opportunities at the Inference Group of the University of Glasgow for two ambitious post-doctoral research associates with an excellent research background in computational statistics. Both of these posts are of three years duration in the first place. A further post-doctoral position will become available within the group later in the year.

The Inference Research Group at Glasgow is at the forefront of developing advanced statistical methodology for scientific applications in particular at the life-sciences interface and presents tremendous substantive collaborative opportunities with major biological research groups in Inflammatory Response, Cancer Research, Pathway Signaling, Parasitology, Cardiac Systems, Plant Biology, and Medical Statistics. The group led by M. Girolami is very well resourced with current research income in excess of £2M and two dedicated high-performance computing clusters supporting seven post-doctoral researchers and six PhD candidates.

Informal enquiries and further details are available from Prof Mark Girolami (girolami(at)dcs.gla.ac.uk)

Position. 1. Research Associate
We seek a post-doctoral research associate to work on the development and application of advanced statistical methodology for nonlinear dynamical system models of biochemical processes. This will be as part of an exciting and ambitious integrated multi-disciplinary project studying the metabolism of the parasitic protozoan Trypanosoma brucei. The project will be led by Professor Mark Girolami at the University of Glasgow.

The purpose of the position is to develop theory and methods for appropriate Markov Chain Monte Carlo (MCMC) based inference over nonlinear differential equations that will exhibit high degrees of ‘evolutionary redundancy’. Other areas of investigation will include model-based experiment design and software emulation as well as cluster-based computation for MCMC.

The focus of application will be on practical inference over dynamic system models of metabolic and protein based regulation in trypanosomes as they respond to oxidative stress with particular emphasis on pathways implicated in redox metabolism in these parasites.

The project is part of a pan-European programme to determine regulation of these pathways at the levels of transcription, translation and metabolic control in conjunction with world leading biologists.

The ideal applicant will have experience in the development and application of MCMC methods for Bayesian inference, experiment design and software emulation. A genuine interest in Systems Biology is required. Some background in high performance computing development for MCMC would be preferred.

This post is linked to the BBSRC funded project The Silicon Trypanasome

Informal enquiries and further details are available from Prof Mark Girolami (girolami(at)dcs.gla.ac.uk)

Position. 2. Research Associate
We seek a post-doctoral research associate to work on developing Bayesian methods to assist in the systematic and rational choice of mathematical models describing natural systems in population and systems biology. This will be part of a collaborative three-centre BBSRC funded research project that includes the University of Glasgow, Imperial College London, and Royal Holloway University of London.

The purpose of this position is to build upon the work reported in the recent Science signalling paper from the Girolami group (http://stke.sciencemag.org/content/vol3/issue113/cover.dtl) where the rationale design of biological experiments to assess the evidential support for competing signalling pathway topologies was enabled employing estimates of Bayes factors. From a methodological perspective the development of probabilistic methods for the solution of differential equations and the exploitation of the recently developed Riemann manifold Monte Carlo methods along with current advances in estimating marginal likelihoods is anticipated.

The ideal applicant will have an extensive background in the development of Bayesian methodology and have recent experience at the life sciences interface.

This post is linked to the BBSRC funded project Inference-based Modelling in Population and Systems Biology.

Informal enquiries and further details are available from Prof Mark Girolami (girolami(at)dcs.gla.ac.uk)
This post has initial funding for 36 months

AERFAI International Summer School on Pattern Recognition and Machine Learning in Multimedia Systems

Call for Participation (apologies for multiple copies)
_____________________________________________________

AERFAI International Summer School on Pattern Recognition and Machine Learning
in Multimedia Systems — Benicàssim, June 7-11, 2010

URL: http://www.aerfaiss2010.uji.es
E-mail: info@aerfaiss2010.uji.es

DESCRIPTION

The AERFAI Summer School 2010 is organized by the Spanish Association
for Pattern Recognition (AERFAI) in collaboration with the Institute
of New Imaging Technologies at Universitat Jaume I of Castelló
(Spain). This is the fifth edition in a series of AERFAI Summer
Schools devoted to a wide range of topics in the fields of Pattern
Recognition and Machine Learning. The focus of this year Summer School
is to study the most relevant approaches to Pattern Recognition and
Machine Learning in Multimedia Systems. This event is open to any
researcher or PhD-student who is interested in learning or refreshing
their knowledge about the most successful approaches in the fields of
object & human-action detection/categorization and recognition.

AERFAISS’2010 is organized as a five-days intensive course to be held
June 7-11 in Benicàssim (Spain). Leading experts in the field shall
present each tutorial, followed by a practice session with specific
software in order for participants to gain a better understanding of
the theory. A non-formal poster session will also be organized for the
participants to present their current research and interact with their
scientific peers.

ORGANIZATION CO-CHAIRS

Prof. J. Salvador Sánchez, Local Chair AERFAISS’2010, sanchez@uji.es
Prof. Filiberto Pla, Chairman of the AERFAI, pla@uji.es

LIST OF LECTURERS

Learning with Structured Inputs and Outputs
Dr. Christoph Lampert, Institute of Science and Technology, Vienna (Austria)

Interactive Video Retrieval
Dr. Cees G.M. Snoek, University of Amsterdam (The Netherlands)

Human Action Recognition (Video)
Dr. Ivan Laptev, INRIA, Paris – Rocquencourt (France)

Human Activity Modelling from Mobile Phone Sensors
Dr. Daniel Gatica-Perez, IDIAP Research Institute, Martigny (Switzerland)

Visual Recognition and Features
Dr. Krystian Mikolajczyk, CVSSP, University of Surrey (UK)

Multimodal Data Fusion
Dr. Stéphane Marchand-Maillet, University of Geneva (Switzerland)

New Challenges in Machine Learning
Prof. Ethem Alpaydin, Bogaziçi University, Istanbul (Turkey)

REGISTRATION

Fees for the AERFAISS’2010 are as follows:

AERFAI or PASCAL2 members – Early registration (by May 10, 2010): Full
… 500 Euros / Single lecture … 100 Euros

AERFAI or PASCAL2 members – Late registration (after May 10, 2010):
Full … 550 Euros / Single lecture … 110 Euros

Non-members – Early registration (by May 10, 2010): Full … 600 Euros
/ Single lecture … 120 Euros

Non-members – Late registration (after May 10, 2010): Full … 650
Euros / Single lecture … 130 Euros

The full registration fee includes access to all lectures, handling
material, coffee breaks, lunches, a guided tour and social dinner. The
single lecture registration allows access to the lecture chosen,
handling material, coffee breaks and lunch. Payment of registration
fee should be done by bank transfer (more information at
http://www.aerfaiss2010.uji.es).

VENUE

AERFAISS’2010 will be held at Hotel Intur Bonaire in Benicàssim. The
hotel is located 150 meters from one of the best fine sandy beaches in
Benicàssim at the Mediterranean coast. It is 10 minutes from the city
of Castellón and the train station, while the Valencia airport is 45
minutes by car.

ACCOMMODATION

Participants will have a special group rate at Hotel Intur Bonaire and
other hotels very close to the AERFAISS’2010 venue. More information
about reservation is available on the web site.

CONTACT

AERFAISS’2010
Dept. Llenguatges i Sistemes Informàtics
Universitat Jaume I
Av. Vicent Sos Baynat, s/n
12071 Castellón de la Plana (Spain)

Tel. +34 964728348 / +34 964728350 / +34 964728359
Fax +34 964728435

E-mail: info@aerfaiss2010.uji.es

CfP: ICML 2010 Workshop on Social Analytics

Call For Papers
Social Analytics: Learning from human interactions
http://webee.technion.ac.il/people/kirilld/ICML10_SNA_Workshop/description.shtml
Workshop held at the 27th International Conference
on Machine Learning (ICML 2010)
Haifa, Israel: June 25, 2010

Our social interactions are often made by electronic means, and are
thus recorded in accessible formats. This opens a range of
possibilities for studying human interactions from data such as social
network sites on the web and cell phone communications. These tasks
usually involve massive amount of data (billions of records) that is
often quite noisy and even corrupted. Social and artificial networks
suggest new challenges in modeling machine learning problems as there
are strong spatial and temporal correlations.
In this workshop we will hear researchers from academia and industry
share their insights about the theory and applications of social
analytics. Our focus will be on graph mining and predictive tools that
can be used in this area. We will also consider different applications
from recommender systems, marketing, search, network optimization and
other emerging areas.
Our goal is to bring people from different fields, ranging from
computer science to marketing, from both academia and industry, to
foster a discussion on the different approaches people have taken to
the study of social phenomena. A successful workshop will introduce
people to the tools and data available for social research in various
communities. A primary goal of the workshop is to create a set of
common theoretical problems to work on and to solicit data from
companies to facilitate common research challenges.

Invited Speakers (confirmed)
========================
Jure Lescovec (Stanford University)
Amit Amil Nanavati (IBM)
Duncan Watts (Yahoo!)

We are awaiting for confirmation from several additional speakers.

Submission Instructions
========================
If you would like to present at this workshop, please send an email
to
icml10.sna.workshop@gmail.com
no later than 23st May, specifying:
– Title
– Authors and affiliations
– A short paper – Length should be no more than 2000 words
(Postscript
or PDF format)

Dates & Deadlines
==================
May 16th: Abstract Submission
May 25th: Acceptance Notification

Organizing Committee
=====================
Shie Mannor
Faculty of Electrical Engineering, Technion, Israel
Yossi Richter
IBM Research Haifa Lab, Haifa, Israel
Elad Yom-Tov
IBM Research Haifa Lab, Haifa, Israel
Kirill Dyagilev
Faculty of Electrical Engineering, Technion, Israel

Open Postdoc position in Machine Learning in Paris

Lab: Imagine, Université Paris Est, France
Contact: Jean-Yves Audibert (audibert at imagine.enpc.fr)

Numerous problems linked to the exploration-exploitation trade-off remain open (even in the well-known *multi-armed bandit* problem). We want to address them, i.e. propose algorithms solving them and study their theoretical properties. In spirit, this is related to (i) the recent works on policies based on upper confidence bounds and (ii) the nice book: Prediction, learning, and games by Nicolò Cesa-Bianchi and Gábor Lugosi. The work is mainly theoretical but, as far as possible, we also intend to address some of the energy minimization problems that arise in Computer Vision, in particular combinatorial problems of 3D reconstruction, by using the proposed algorithms.

The position requires strong theoretical skills in probability and statistics. An ability to implement algorithms working on real-world data is also desirable.
To apply, please email CV, names and email addresses of 2-3
referees to Jean-Yves Audibert (audibert at imagine.enpc.fr) before May 15th, 2010.

The position is funded by a grant from the French National Research Agency (ANR). The successful candidate will have no mandatory teaching or administrative duties.

CfP: RSS10 Workshop Towards Closing the Loop: Active Learning for Robotics

—————————————————————-
CALL FOR CONTRIBUTIONS – RSS WORKSHOP
Towards Closing the Loop: Active Learning for Robotics
Zaragoza, Spain, June 27, 2010
http://www.isr.ist.utl.pt/~rmcantin/rss2010.php
—————————————————————-

Important Dates:
—————-
* Submission of extended abstracts: May 19, 2010
(later submission might not be considered for review)
* Notification of acceptance: May 28, 2010
* Workshop date: June 27, 2010

Overview:
———
The ability to adapt to changing environment autonomously will be
essential for future robots. While this need is well-recognized, most
machine learning research focuses largely on perception and static
data sets. Instead, future robots need to interact with the
environment to generate the data that is needed to foster real-time
adaptation based on all information collected in previous interactions
and observations. In other words, we need to close the loop between
the robot acting, robot sensing and robot learning. Novel active
methods need to outperform passive methods by a margin that
compensates the potential the extra computational burden and the cost
of the active data sampling.

During the last years, there has been an increasing interest in
related techniques that could potentially become applicable in this
context. These include techniques from statistics such as adaptive
sensing or sequential experimental design as well novel reinforcement
learning methods that have the potential to scale into robotics. In
this context, we would like to bring together researchers from both
the robotics and active machine learning in order to discuss for which
problems the autonomous learning loop can be closed using learning,
and to identify the machine learning methods that can be used to close
it.

Invited speakers:
—————–
* Mark Coates, McGill University
* Andrew Davison, Imperial College London
* Manuel Lopes, University of Plymouth
* Pierre-Yves Oudeyers, INRIA
* Nick Roy, MIT
* Jo-Ann Ting, UBC
* John K. Tsotsos, York University

Submission instructions:
————————
We invite submission of extended abstracts to the workshop. Extended
abstracts should be up to 2 pages in length, formatted in according to
RSS style. However, submissions should not be blind. Extended
abstracts should be sent in PDF or PS file format by email to
alrss10@gmail.com

The selected submission may be accepted either as an oral presentation
or as a poster presentation. We encourage participants who can
contribute in the following areas:

* Active learning
* Active filtering
* Sequential experimental design
* Adaptive sensing
* Optimal information gathering
* Autonomous exploration
* Bayesian optimization
* Active cognitive development
* Attention systems or gaze control
* Sensor placement
* Active vision
* Online decision making
* Selection criteria/Utility functions
* Information theoretic metrics in the context of robotics.

The above list is not exhaustive, and we welcome submissions on highly
related topics too. Accepted extended abstracts will be made available
online at the workshop website.

Steering Committee:
——————-
* Florence d’Alché-Buc
* Jun Morimoto
* Nick Roy
* Marc Toussaint

Organizers:
———–
* Ruben Martinez-Cantin, Instituto Superior Tecnico
* Jan Peters, Max Plank Institute for Biological Cybernetics
* Andreas Krause, Caltech

Contact:
——–
mailto:alrss10@gmail.com
http://www.isr.ist.utl.pt/~rmcantin/rss2010.php

Research software engineer on face recognition

Duration of the contract: 18 months.
Location: INRIA Rhône-Alpes (Grenoble, France)
Salary: 2500 to 3000 € brut (gross) per month

LEAR (Learning and Recognition) is a research team at INRIA’s site in Grenoble in the French Alps, see http://lear.inrialpes.fr. LEAR’s main focus is learning based approaches to visual object recognition and scene interpretation, particularly for object category detection, image retrieval, video indexing and the analysis of humans and their movements.

The research engineer will evaluate and optimize different components for robust face recognition in images and videos that have been developed in the team into a robust and highly efficient set of tools. The components for face detection, feature extraction, metric learning, and recognition, are currently coded partly in Matlab and C, and need to be packaged, optimized, and parallelized where possible.

In a collaboration with a local start-up company you will extensively evaluate the system on public and private data sets, in order to optimize the various design choices of the different components. You will closely collaborate with other team members working on planned (inter-)national projects in which face/person recognition will play an important role.

The ideal candidate

* holds a PhD or engineering degree in Computer Vision and/or Machine Learning
* has proven strong programming and development skills in C(++) and Linux scripting
* has good communication skills in English and French

If interested please provide a cover letter, resume and references to Cordelia.Schmid(at)inria.fr and Jakob.Verbeek(at)inria.fr

Application closes 31 May 2010