PhD Studentship – Learning to Recognise Dynamic Visual Content from Broadcast Footage

Supervision: Dr Mark Everingham, University of Leeds

Deadline: Open until filled

Project Description:

A PhD studentship is available as part of an EPSRC funded project on “Learning to Recognise Dynamic Visual Content from Broadcast Footage” being jointly undertaken by the University of Leeds (Mark Everingham), the University of Oxford (Andrew Zisserman), and the University of Surrey (Richard Bowden).

The objective of the project is to develop automated tools that allow temporal visual content, such as a human gesturing, using sign language, or interacting with objects or other humans, to be learnt from standard TV broadcast signals using the transmitted annotation in the form of subtitles and annotation for the visually impaired as supervision. This requires the development of models of the visual appearance and dynamics of actions, and learning methods which can train such models using the weak supervision provided by the subtitles. Once the models have been learnt they can then be used without supervision, e.g. for sign language interpretation or automatic description of the content of video footage, and during the project demonstrators will be engineered for both of these applications.

The student will focus on the development of visual descriptors and learning algorithms for sign language and action recognition in broadcast video. S/he will be based in the School of Computing at the University of Leeds, and will be supervised by Dr Mark Everingham (http://www.comp.leeds.ac.uk/me/).

Funding Notes: The studentship is funded by an EPSRC project studentship and will start from 1st October 2011 or as soon as possible thereafter. The studentship is funded for 3 years and covers Home/EU fees and maintenance at the standard EPSRC rate (currently £13,590 per annum). Applications are welcome from overseas students, but such students would have to provide the difference between the UK/EU and the overseas student rates for university fees from some other source, such as a scholarship or personal funds.

Academic Staff Contact Details: Dr Mark Everingham. M.Everingham(at)leeds.ac.uk (for informal enquiries about the project only – do not send applications to this address).

Entry Requirements: The PhD candidate should have or expect to obtain a first class or strong 2.1 honours degree in computer science, mathematics, or related discipline. The following qualities are desirable: demonstrable experience in computer vision or machine learning; excellent record of academic and/or professional achievement; strong mathematical skills; strong programming skills, especially C/C++ and Matlab; good written and spoken communication skills in English.

Details on how to apply can be found at:

http://www.leeds.ac.uk/rds/prospective_students/apply/I_want_to_apply.html

Application Procedure: Formal applications for research degree study must be made either on line through the University website, or on the University’s application form. Detailed information of how to apply on line can be found at: http://www.leeds.ac.uk/students/apply_research.htm

The paper application form is available at: http://www.leeds.ac.uk/rsa/prospective_students/apply/I_want_to_apply.html

Please return the completed application form to the Research Degrees & Scholarships Office, University of Leeds, LS2 9JT.

Please note, if you intend to send academic references we can only accept them if they are on official letter headed paper and contain an original signature and stamp; they must arrive in sealed envelopes. Alternatively, the School will contact your named academic referees directly.

RA in Computational Biology / Bioinformatics for Systems Biology (Sheffield)

RA position in Computational Biology / Bioinformatics for Systems Biology
University of Sheffield
Chemical and Biological Engineering

Closing Date: 14 July 2011

Chemical and Biological Engineering is a thriving department within the University’s Faculty of Engineering and is experiencing a period of considerable growth in both our research and teaching.

The Chemical Engineering at the Life Science Interface (ChELSI) Institute is located within the Department of Chemical and Biological Engineering. Inhabiting newly extended and refurbished state of the art laboratory and office space, the institute aims to foster interactions between the various traditional fields of Life Sciences and Engineering. The institute possesses a strong record in high-throughput data generation (specifically mass-spectrometry-based, quantitative proteomics), Systems Biology and more recently, Synthetic Biology and provides a multidisciplinary environment for modelling and engineering in the life sciences, including medical applications.

You will contribute the theoretical tools for modelling biological systems and analysing biological data. It is expected that you will have a strong background in mathematical modelling and programming, and will possess a broad range of skills, including, statistical / bayesian modelling, programming, working with heavy datasets, network analyses, numerical methods, biological databases, etc. Applicants should have a PhD in Systems Biology, Bioinformatics, Computational Biology, Computer Science or a related discipline (or have equivalent experience). The work will require a creative, independent mind to tackle problems of:

* Network integration of high-throughput data (transcriptomics, proteomics, metabolomics)

* Statistical modelling of quantitative proteomics dataset(for example, multilevel, bayesian, etc.)

* Strategies for inverse metabolic engineering through quantitative proteomics

* Systems biology modelling

* Metaproteomics

This is a ChELSI-funded position and will run for a fixed term, completing on the 30 June 2012.

More information can be found at http://www.jobs.ac.uk/job/ACU777/research-associate-in-computational-biology-bioinformatics-for-systems-biology/

Funded PhD in Computer Vision

University of Surrey

Faculty of Engineering & Physical Sciences

Centre for Vision, Speech and Signal Processing

(CVSSP)

PhD Studentship in Learning to Recognise Dynamic Visual Content from Broadcast Footage

This is your opportunity to study for a PhD at the Centre for Vision, Speech and Signal Processing, one of the UK’s premier research centres in Computer Vision. The studentship is available from Oct and covers both tuition fees and a maintenance grant for 3.5 years. The funding is available to UK or EU students.

Successful applicants will join an expanding research group within the Centre for Vision Speech and Signal Processing which has over 120 people working in vision, machine learning and related disciplines. It has an international reputation for the excellence of its research and, in the last Research Assessment Exercise; the Department (of Electronic Engineering) was rated as second in the country with the highest return of staff for any institution.

The project is collaboration between the University of Surrey (Prof Bowden), the University of Oxford (Prof Zisserman) and the University of Leeds (Dr Everingham). The objective of this project is to develop automated tools that allow temporal visual content, such as a human gesturing, using sign language, or interacting with objects or other humans, to be learnt from standard TV broadcast signals using the transmitted annotation in the form of subtitles, scripts and annotation for the visually impaired as supervision.

Candidates should hold a 1st or strong 2.1 honours degree or Masters degree or equivalent in a scientific discipline (e.g., Engineering, Physics, Mathematics or Computing), and should have good written/spoken English and demonstrate an aptitude for the research area. Prior experience in computer vision, image processing or machine learning would be advantageous.

The studentship includes tuition fees for UK or EU candidates and a tax free maintenance grant of £13,920 for 3.5 years.

The post will remain open until filled. For further information please contact Prof Richard Bowden. Applicants should send a CV and covering letter to Prof Bowden r.bowden(at)surrey.ac.uk.

PhDs and Postdocs Positions in Neuroelectronics and Neuroengineering: newly launched NAMASEN European Training Network

9 Marie-Curie PhD and Postdoc positions across Europe: 1st round openings
Within the framework of the Marie Curie Initial Training Network “NAMASEN”, European top research centers seek to recruit 7 Early Stage Researcher (ESR) and 2 Experienced Researcher (ER) positions, as of January 1st, 2012.
We offer research training in Neuroelectronics and Nanotechnology: towards a Multidisciplinary Approach for the Science and Engineering of Biological Neuronal Networks.
A second round, for 2 more ESRs and 1 more ER, will be launched during 2012.
First-round application deadline: October 31st, 2011.
Appointments for Early Stage Researcher (Marie Curie Fellow) are full-time, fixed terms for three years, tenable from January 1st, 2012. Appointments for Experienced Researcher are full-time, fixed terms for two years, tenable from January 1st, 2012.
The Early Stage Researchers will receive supervision for the preparation of a PhD thesis and benefit from the combined resources of the NAMASEN Network.

Description of NAMASEN
NAMASEN is the acronym for an Initial Training Network (http://www.namasen.net), funded by the European Commission under the FP7 Marie-Curie PEOPLE programme. Its ultimate mission is to lay the foundation of a virtual scientific institute for the multi-disciplinary study of Neuroengineering and Network-Neurosciences that will train a new generation of scientists and professionals and that will contribute to Europe’s leading role in scientific innovation.
NAMASEN targets both technological and scientific priorities, such as the development of novel multi-electrode arrays and advanced interfaces that functionally interact with neurons and networks. NAMASEN investigates neuro-electronic hybrids as devices able to undergo a functional and anatomical reconfiguration, on the basis of the activity-dependent plasticity and rewiring properties of neurons, under some control by the experimenter.
The NAMASEN ITN Network consists of the 10 academic and 3 industrial partners: the University of Antwerp (Belgium), The University of Sheffield (UK), the Institute of Molecular Biology and Biotechnology (IMBB) at the Foundation for Research and Technology-Hellas (FORTH, Greece), the Hebrew University of Jerusalem (Israel), the Swiss Federal Institute of Technology of Lausanne EPFL (Switzerland), the Italian Institute of Technology (Italy), the Nencki Institute of Experimental Biology (Poland), the Interuniversity Center for Microelectronics IMEC (Belgium), the University of Freiburg (Germany), the Natural and Medical Sciences Institute at the University of Tuebingen (Germany), Janssen Pharmaceutica (Belgium), 2-Sight Europe (Switzerland), and Gersteltec Engineering Solutions (Switzerland).
Altogether 10 Early Stage Researchers (PhD researchers) and 3 Experienced Researchers (Postdocs) will be recruited during 2011-2012. As a part of their training experience, each researcher will be based in one country but will spend some of their time abroad during secondment periods within the network. Scientific and technological disciplines targeted by each position are diverse and heterogeneous, ranging from microfabrication and nanotechnologies, to experimental neurobiology and computational neuroscience. Individual openings, advertised on the electronic job application page of NAMASEN (http://www.namasen.net), contain relevant information and links to the hosting institutions.
The NAMASEN ITN Network offers a unique research environment where leading academics will integrate accepted applicants into their research teams, providing a top-notch structured training programme in Neuroelectronics, Neuroengineering, and Nanotechnologies. Academic partners within the NAMASEN ITN Network will support the Early Stage Researchers to work successfully towards a PhD defense.
More information on the NAMASEN ITN Network and its job openings can be found at: http://www.namasen.net

Salary and Benefits for the Positions
The Researchers will be appointed on a full-time temporary contacts, for a period of three years (ESRs) or two years (ERs), including a two-to-six-month secondments at different NAMASEN partner.
The Researcher will be a Marie Curie fellow and will profit from all Marie Curie benefits, including living, mobility, travel, and career exploratory allowances according to the Marie Curie Framework 7 requirements (http://ec.europa.eu/mariecurieactions).

Eligibility

Candidates for ESR positions must be, at the time of recruitment, in the first four years (full-time equivalent) of their research careers and not yet have been awarded a doctoral degree. This is measured from the date when they obtained the degree, which would formally entitle them to embark on a doctorate, either in the country in which the degree was obtained or in the country in which the research training is provided. In practice, this means they should not have obtained any degree before 31st December 2007 that would entitle them to enroll for a doctorate. In general, this is usually a suitably qualifying Masters degree.
Candidates for ER positions must not have worked in a research position / received research training for more than 5 years of their undergraduate degree. The undergraduate degree is the first degree, which allowed them to embark on a PhD program, typically a BA or BSc. Years since the undergraduate degree working outside research do not count.
Candidates are normally required to undertake trans-national mobility (i.e. move from one country to another) when taking up their appointment. At the time of recruitment by the host organization, candidates must not have resided or carried out their main activity (work, studies, etc.) in the country of their host organization (i.e. depending on the NAMASEN network partner to apply for) for more than 12 months between 1 November 2008 and 31 December 2011.
Applicants for the position at NAMASEN may be a national of any Member State of the European Union, of any Associated Country or of any other third country, but they may not be a national of the hosting country.
Availability to travel (including internationally), for the purpose of the research and training activities, is a requirement for the positions.

Applications and Enquiries
Candidates are invited to apply to the vacancies. Candidates are also requested to submit their CV in English (max. 5 pages), max. 10 academic publications (in English), including an electronic copy of university diploma (translated to English). A cover letter is also required, where motivations to apply to the NAMASEN consortium in general and to an individual partner, in particular, must be stated clearly. Spam applications will be trashed.
Formal applications should be made through the NAMASEN consortium and should be sent by means of the website http://www.namasen.net.
Final decisions will be taken upon joint consultations within the NAMASEN Supervisory Board.
Informal inquiries concerning the individual positions may be addressed to contact people indicated on online job electronic application forms at www.namasen.net.

Postdoctoral Position in Large Scale Bayesian Machine Learning

EPFL’s Probabilistic Machine Learning Lab (http://lapmal.epfl.ch/), headed
by Matthias Seeger, has an opening for a post-doctoral fellow in the
field of Bayesian machine learning / low level computer vision, as part of
a project funded by the European Research Council.

The initial appointment is for 12 months, extensions up to 3 years are possible.
Topics of interest are:

– Variational approximate Bayesian inference, particularly for large scale
generalized linear and/or hybrid models
– Approximate inference for large structured models (stacks of image frames,
video, text), with particular emphasis on parallel computing (multi-core,
graphics processing units)
– Exploring boundaries between approximate Bayesian inference, numerical
mathematics, and large scale optimization
– Theoretical and algorithmic progress for variational Bayesian inference
– Applications of variational Bayesian inference to adaptive compressive
sensing, magnetic resonance imaging, low-level computer vision, or other
large scale domains

Position:

The successful candidate would establish approximate Bayesian computations in
domains and at scales not previously attempted. The Probabilistic Machine
Learning Lab is set within a vibrant, world-class computer and communication
sciences faculty (highest-ranked in Europe) at EPFL, one of the leading
technical universities worldwide.

EPFL is located next to Lake Geneva in a beautiful setting 60 kilometers
away from the city of Geneva. Salaries are internationally competitive (among
the highest in Europe).

Education:

Applicants are expected to have finished, or be about to finish their
Ph.D. degrees. They must have an exceptional background in probabilistic
machine learning, numerical mathematics, or statistical physics. A firm grasp
of approximate Bayesian machine learning and/or advanced (medical) image
processing is desirable. A track record of publications at top ML or CV
conferences (NIPS, ICML, UAI, JMLR, CVPR, ICCV, PAMI, IJCV) and/or top-ranked
image processing or physics journals is essential.
Further pluses are strong scientific programming skills (C++, Matlab), prior
exposure to (medical) image/signal processing practice.
The working language at EPFL is English (good skills essential), French is
not required.

Application:

Please send your applications by email to
Matthias Seeger (matthias.seeger(at)epfl.ch)

Make sure to include:
– Statement of interest
– Curriculum vitae
– List of publications (add copies of 2-3 strongest papers in the area of
interest of this call)
– Contact details for three letters of reference

Six PhD studentships in Statistical Methodology and Its Application at University College London

The studentships are attached to the Department of Statistical Science at
University College London, and a subset of them are UCL Impact awards.
Impact awards support collaborative studentship projects with
organisations such as charities, companies, government institutions and
social enterprises. The impact awards are joint with Lloyds bank, Xerox
Research Centre Europe (www.xrce.xerox.com), and NCR Labs, respectively.

UCL is a member of the London Taught Course Centre (www.ltcc.ac.uk) that
provides additional training in foundations of Mathematics and Statistics.
UCL also offers training via its graduate school.

UCL is among the top-ten research institutions in the world and the
Department of Statistical Science is one of the three largest statistics
groups in the UK having a unique combined strength in Statistical
Methodology and Machine Learning. The studentships are based in the
Department of Statistical Science which has over twenty full time members
of staff, including Professors Tom Fearn, Mark Girolami, Valerie Isham,
Sofia Olhede and Trevor Sweeting. Together with other groups at UCL the
department forms the Centre for Computational Statistics and Machine
Learning (CSML) (www.csml.ucl.ac.uk), which is part of the European
Network of Excellence PASCAL (www.pascal-network.org).

For informal inquiries please contact Professor Mark Girolami
girolami(at)stats.ucl.ac.uk or Professor Sofia Olhede, sofia(at)stats.ucl.ac.uk.
Candidates should complete the general UCL PhD application form, available
at www.ucl.ac.uk/prospective-students/graduate-study/application-admission

1. Advanced Monte Carlo Methods for Images and Text (with Xerox) – Prof.
M.Girolami
The Bayesian framework for statistical inference is largely dependent on
numerical simulation for all but the most straightforward of statistical
models. In the probabilistic representation of digital documents comprised
of texts, images and embedded information, sophisticated statistical
models are often required. It is hugely challenging to perform simulation
based inference over these classes of models due to a variety of factors
such as (1) exceedingly high number of parameters in the model, (2) the
discrete nature of the configuration space, (3) lack of strong
likelihood-based identifiability and (4) strong posterior correlation of
parameters. This project will seek to develop generic Monte Carlo
sampling methods that addresses some of the issues listed above. The
research will be carried out in close collaboration with Dr Cedric
Archambeau (cedric.archambeau@xerox.com) and Dr Guillaume Bouchard
(guillaume.bouchard@xerox.com). The successful candidate will have the
opportunity to visit Xerox Research Centre Europe (www.xrce.xerox.com) on
a regular basis.

2. Evolving Lead and Lag Times of Credit Cycles (with Lloyds) – Prof. S.
Olhede
For policymakers and companies constructing accurate business and credit
cycle indicators is pivotal for future planning, as well as for managing
risk and troughs in cycles. Such indicators are constructed from
observations of multiple time series, such as gross domestic product,
production for certain sectors, employment, spread of interest rates, that
is from collections of multiple observations of many different processes
at several time instances. It is particularly important to identify
leading credit cycle indicators in such data, as these will show effects
of a changing financial climate ahead of other variables changing and thus
they will allow for prior warning of a worsening or improving climate.
This studentship will develop time series methods to estimate leads and
lags, as well as the common cyclical structure in multiple time series, in
particular accounting for evolving structure in the relationships to
identify evolving leading indicators.

3. Geometric Markov chain Monte Carlo – Prof. M.Girolami
A recent paper read before the Royal Statistical Society developed
sampling methodology based on Riemannian geometric principles and provided
a way forward in systematically addressing some of the biggest challenges
faced in modern day computational statistics. The ability to design
proposal mechanisms for Markov chain Monte Carlo (MCMC) that traverse
geodesics and transform in a covariant manner across the statistical
manifold brings great potential to what problems can conceivably be
addressed. In this project the student will work on the further
development and analysis of this methodology from a number of possible
perspectives such as considering alternative geometries.

4. Probabilistic Models for Adaptive Content Creation (with Xerox) – Prof.
M.Girolami
This research project will focus on the development of structured
prediction models to build document templates and learn to customize texts
or sentences according to user preferences and habits. Conditional
language models to generate human readable text based on the specific
target application and device appropriate algorithms for the generation of
small pieces of text, such as introductory sentences will also be
developed. This project will draw upon recent advances in Natural Language
Processing tools, Machine Learning algorithms and Stochastic Optimization
techniques, in developing intelligent document creation tools. The
research will be carried out in close collaboration with Dr Cedric
Archambeau (cedric.archambeau@xerox.com) and Dr Guillaume Bouchard
(guillaume.bouchard@xerox.com). The successful candidate will have the
opportunity to visit Xerox Research Centre Europe (www.xrce.xerox.com) on
a regular basis.

5. Spatio-Temporal Statistical Models of Banknote Ageing (with NCR) –
Prof. M.Girolami
A practical challenge to fully realising automated currency validation in
Automated Teller Machines (ATM) is the variable quality of banknotes
presented to the machine. It is desirable that a probabilistic generative
model, and associated inferential machinery, of the ageing effects on
banknote images be made available. This project will adopt advanced
Bayesian modeling and inferential methodology in developing note ageing
process models. NCR Labs collections of machine readable banknotes will be
employed in formally assessing model adequacy as well as the ability to
generate sample ageing profiles of banknotes. The theory, analysis, and
methodology developed within this project will push the boundaries of
spatio-temporal statistical modelling and presents a superb opportunity in
making important advances in computational statistics in general.

6. Statistical Machine Learning methods for fMRI Analysis – Prof. M.Girolami
Functional magnetic resonance imaging (fMRI) is providing the means for
both early detection of a number of neurodegenerative diseases and to
study their origin and the mechanisms underlying them. Multivariate
statistical methods show great promise in the systematic study and
analysis of fMRI images and associated genetic data. There are still many
methodological statistical challenges to be addressed in this research and
the student will have the opportunity to work in a cross-disciplinary
group seeking to develop appropriate statistical models and associated
methods for this ongoing research.

Three PhD STUDENTSHIPS: Advanced Bayesian Computation for Cross-Disciplinary Research

PhD studentships

Universities of Warwick, Kent, and Cambridge

Starting September/October, 2011

We are looking for three PhD students to join our interdisciplinary team. These studentships are fully funded (for UK or EU candidates) for 3.5 years as part of an EPSRC project on Advanced Bayesian Computation for Cross-Disciplinary Research. Candidates should have a good first degree in a relevant quantitative field such as applied mathematics, statistics, computer science, engineering, physics, or chemistry. Good programming skills in a high level language such as Matlab, R or C/C++ are very desirable.

The students will be part of an interdisciplinary research project to develop advanced statistical theory and algorithms that will directly address current challenges in scientific modeling in biology, astronomy and econometrics. This research is a collaboration between bioinformatics and systems biology (Prof. David Wild, Warwick), statistical machine learning (Prof. Zoubin Ghahramani, Cambridge), statistics and econometrics (Dr. Jim Griffin, Kent) and astronomy (Prof. Andrew Liddle, Sussex).

Choice of topics for the studentships are:

o Studentship 1 (Warwick; Prof. Wild): Applications of nonparametric Bayesian modeling to a number of contemporary problems in computational biology. New methods for Bayesian experimental design.

o Studentship 2 (Kent; Dr Griffin): Bayesian nonparametric methods for Econometrics.

o Studentship 3 (Cambridge; Prof. Ghahramani): Nonparametric Bayesian machine learning. The construction of efficient algorithms for inference in statistical models based on GPU computation.

Applicants should include a full CV, names and contact details of two referees, and an accompanying cover letter outlining their interests and any previous research experience to Ms Diane Unwin, dsu21(at)eng.cam.ac.uk . * The cover letter must specify which studentship the applicant is applying for. *

** Deadline: July 5th, 2011. **

Funding Note: The award will cover Home/EU tuition fees and a stipend for 3.5 years. Note that students from outside the EU would need to cover the difference between Home/EU and Overseas fees.

CFP – Data Streams Track – ACM SAC 2012

The 27th Annual ACM Symposium on Applied Computing
in Trento University, Italy, March 20-23, 2012.
http://www.acm.org/conferences/sac/sac2012/

DATA STREAMS TRACK
http://www.cs.waikato.ac.nz/~abifet/SAC2012/

CALL FOR PAPERS
The rapid development in information science and technology in general
and in growth complexity and volume of data in particular has
introduced new challenges for the research community. Many sources
produce data continuously. Examples include sensor networks, wireless
networks, radio frequency identification (RFID), health-care devices
and information systems, customer click streams, telephone records,
multimedia data, scientific data, sets of retail chain transactions,
etc. These sources are called data streams. A data stream is an
ordered sequence of instances that can be read only once or a small
number of times using limited computing and storage capabilities.
These sources of data are characterized by being open-ended, flowing
at high-speed, and generated by non stationary distributions.

TOPICS OF INTEREST
We are looking for original, unpublished work related to algorithms,
methods and applications on data streams. Topics include (but are not
restricted) to:

– Data Stream Models
– Data Stream Management Systems
– Data Stream Query Languages
– Continuous queries and Summarization from Data Streams
– Sampling Data Streams
– Single-Pass Algorithms
– Scalable Algorithms
– Change Detection Algorithms
– Clustering on Data Streams
– Classification and Regression on Data Streams
– Association Rules on Data Streams
– Feature Selection on Data Streams
– Visualization Techniques for Data Streams
– Evaluation of Data Streams Models
– Data Stream applications
– Sensor Networks
– Real-Time Applications

IMPORTANT DATES (strict)
– Paper Submission: 31 August, 2011
– Author Notification: 12 October, 2011
– Camera-ready Copy: 2 November, 2011

PAPER SUBMISSION GUIDELINES
Papers should be submitted in PDF using the SAC 2012 conference
management system: http://www.softconf.com/c/sac2012/. Authors are
invited to submit original papers in all topics related to data
streams. All papers should be submitted in ACM 2-column camera ready
format for publication in the symposium proceedings. ACM SAC follows a
double blind review process. Consequently, the author(s) name(s) and
address(s) must NOT appear in the body of the submitted paper, and
self-references should be in the third person. This is to facilitate
double blind review required by ACM. All submitted papers must include
the paper identification number provided by the eCMS system when the
paper is first registered. The number must appear on the front page,
above the title of the paper. Each submitted paper will be fully
refereed and undergo a blind review process by at least three
referees. The conference proceedings will be published by ACM. The
maximum number of pages allowed for the final papers is 6 pages. There
is a set of templates to support the required paper format for a
number of document preparation systems at:
http://www.acm.org/sigs/pubs/proceed/template.html

ICCV 2011 – Call for demos

Deadline: September 11, 2011

http://www.iccv2011.org/call-for-demos

ICCV 2011 will host demonstrations. The purpose of demos is to give
researchers the opportunity to showcase live demonstrations of their
contributions. The demonstrations need not be limited only to papers
that have been presented at ICCV 2011. Researchers are encouraged to
demonstrate the effectiveness of methods described in papers presented
in the past conferences and in other venues, so long as they fall
within the broad context of ICCV. During the conference, the Demo
Chairs will select the recipient of the Best Demo Award.

Prospective demo participants should fill out and submit a demo
application form and email it to demo(at)iccv2011.org. Please be advised
that all of the people presenting the demo must be registered at the
conference. If there are more applications than the available space
allows, the time of submission of the complete application will be
used for selection. The conference also reserves the right to select
demonstrations based on the degree of appropriateness for ICCV.

Demonstrations can be made with the help of industrial partners, but
commercial products should be presented as part of the ICCV exhibits,
rather than demonstrations.

Deadline for application: September 11, 2011
Space assignment Emailed: September 18, 2011

For further information about demos please contact the demo chairs
demo(at)iccv2011.org

Open PhD position: Large-scale machine learning for video analysis

Location:
LEAR team, INRIA, Grenoble, France

Supervisors:
Jakob Verbeek and Cordelia Schmid

Duration:
36 months, preferrably starting September 2011.

Keywords:
statistical machine learning, computer vision

Expected skills:
strong knowledge in machine learning and/or computer vision, good skills
in programming in python and/or C

Context:
Video interpretation and understanding is one of the long-term research
goals in computer vision. Realistic videos such as movies and TV series
present a variety of challenging machine learning problems, such as
action classification/action retrieval, human tracking, human/object
interaction classification, etc. Recently robust visual descriptors for
video classification have been developed, and have shown that it is
possible to learn visual classifiers in realistic difficult settings.
However, in order to deploy visual recognition systems on large-scale in
practice it becomes important to address the scalability of the
techniques. The main goal is this thesis is to develop scalable methods
for video content analysis (eg for ranking, or classification). Topics
of interest include scaling to large volumes of training data, and
transfer learning for large numbers of categories to be recognized.

More information:
http://lear.inrialpes.fr/job/thesis_2011_learningvideo.php