EU funded projects


transLectures is an EU-funded project to develop innovative, cost-effective tools for the automatic transcription and translation of online educational videos.

Online collections of video material are fast becoming a staple feature of the Internet and a key educational resource. What we are working on at transLectures is a set of easy-to-use tools that will allow users to add multilingual subtitles to these videos. In doing so, they will make the content of these videos available to a much wider audience in a way that is cost-effective and sustainable over the vast collections of online video lectures being generated.

Automatic transcription tools will provide verbatim subtitles of the talks recorded on video, thereby allowing the hard-of-hearing to access this content. Language learners and other non-native speakers will also benefit from these monolingual subtitles. Meanwhile, machine translation tools will make these subtitles available in languages other than that in which the video was recorded.

Specifically, we will be developing tools for use on VideoLectures.NET, a collection of videos recorded at various academic events set up by JSI’s Centre for Knowledge Transfer, and for poliMedia, a lecture capture system designed and implemented at the UPVLC. Our tools will also be fully compatible with Matterhorn, a free, open-source platform for the management of educational audio and video content

The language pairs being targeted in this project are English, Spanish and Slovenian for transcription, and English<>Spanish, English<>Slovenian, English>French and English>German for translation


The foundation promotes the spread of knowledge and vivid academic debate to anyone with access to the internet anywhere in the world. It therefore benefits all those interested in academic knowledge and debate, where they do not currently have immediate access to such resources and debate. It also helps to develop more widespread interest in such resources and debate.
The Foundation promotes the open access to academic resources (such as video lectures, learning objects, paper, reports, books, and scientific data), together with tools to give users access to these resources and to match them to their needs. Furthermore, the Foundation aims to help overcome the barriers of limited discoverability and accessibility, as well as enable interaction between users and providers, and among users with common interests.

The Foundation is a forum where creators, technology developers, managers and users of such resources and tools can meet to actively promote the free availability and distribution of such content and tools, as well as develop strategies for fostering interactions between users and providers and among users with common interests.

The Foundation has its main office in London, England, but it operates globally together with a subsidiary “Zavod Znanje za Vse” in Ljubljana, Slovenia, responsible for infrastructure development as well as the maintenance and development of an exemplar site,

Last call for Challenge Proposals! Deadline 3rd February 2012

Next Call for Challenge Proposals – Winter 2012
Deadline, Feb. 3rd, 2012

The goal of Pascal-II Challenges is to advance the state of the art about cognitive systems. The cognitive banner is large: welcome are proposals related to

* communication (language, voice, vision, haptics, brain signals, representation, feature construction, – non exhaustive list)
* interaction (games, robotics, social networks, preferences, validation, experiment design, distributed/decentralized decision – n.e.l.)
* applicative settings (multi-task and transfert, drift, privacy and anonymization – n.e.l.)
* theoretical and/or algorithmic aspects of communication, interaction, computational thinking, and cognition at large.

Challenges come in three possible flavors:

* Applicative challenges aim at advancing the state of the art in some real-world domain; they should come with real-world, comprehensive datasets, with different levels of difficulty if possible.
* Exploratory challenges aim at investigating a new field/mode of ML; they should come with highly flexible settings, in order to understand where the difficulty is and to perform lesion studies.
* Theoretical challenges aim at long term research; they should provide (experimental or theoretical) milestones for the road.

NB: A legacy of Pascal-I is a perennial repository, storing all previous challenge datasets; Pascal-II challenges will participate to this repository, contributing to a principled, well-recognized and up-to-date benchmarking methodology.

One funded PhD position in Big Data Analytics, University of Surrey, UK

Applications are invited for a 3-year Ph.D. project hosted in the Department of Computing, University of Surrey, UK.

Supervisor: Dr Norman Poh
Co-supervisor: Dr David Windridge

Due to technological advances, addressing the growth in the size of data sets used by science, medicine and industry has become an increasingly central concern. In this PhD, the candidate will work towards advancing machine-learning and data-mining algorithms for processing big data by addressing some or all of the following issues: handling of sampling bias and structural noise, handling of under-sampled and miss-labelled data; handling of covariates or confounding factors; exploitation of temporal logics; and finally, efficient retrieval of related data queries. The techniques developed will be applied to a number of application domains, including healthcare records, bioinformatics, business data, and data collected from ubiquitous sensing.

The candidate will contribute towards building a critical mass of strategic competency in data analytics within the Computing department, and will work in a multidisciplinary team involving clinicians and IT engineers.
Required experience and qualifications:
– Masters-level degree in computer science, mathematics, statistics, or machine Learning; or equivalent research/industrial experience in data analysis
– A good command of English, as well as open-mindedness and the will to collaborate within a team

Additional desirable features:
– A record of peer-reviewed publication
– Evidence of system implementation
– Knowledge of statistical packages and high-level programming such as Matlab, R, and Python
– Knowledge of databases and SQL

The candidate will receive Home or EU fees (currently £3,828) and a tax-free maintenance grant of per annum (currently £11,400). Non-EU students are expected to be in a position to cover the difference between the Home and Overseas Fees (currently £14,400). The studentship should be taken up no later than 1 July 2013. If you are interested, please apply as soon as possible.

For full details and informal discussions, please refer to Dr Norman Poh’s website: and click the vacancy tab.
To apply, please email normanpoh(at) with a CV, and relevant supporting materials such as transcripts, research reports, and publications. Candidates with no previous research experience may be asked to sit a short written examination. Shortlisted candidates will then be asked to apply formally through the link:

CFP: 1st IEEE Workshop on Visual Analysis Beyond Semantics (CVPR13)

1st IEEE Workshop on Visual Analysis Beyond Semantics

28 June 2013

CVPR2013, Portland, Oregon, USA

Can we model high-level visual properties such as image quality, memorability and photographic style? Can we leverage large-scale datasets to mitigate the intrinsic uncertainty of these properties? And most importantly, can we successfully employ such models in applications for multimodal classification, retrieval and recommendation?
This workshop seeks to stimulate and inform researchers into tackling the next level of problems in this exciting area of research that we call visual analysis beyond semantics (VABS). The workshop itself is motivated from two directions:

1. While still in its nascent stage, research into computational models for visual analysis beyond semantics have already shown great potential and interesting results. However, as several recent papers published in latest CVPR and ICCV show, the techniques currently employed are mainly derived from content understanding (analysis pipelines involving SIFT, BOV and large-margin classifiers). Most recent and advanced computer vision/machine learning techniques like visual attributes, recommendation, implicit feedback, etc. are completely neglected. Moreover, current approaches are not leveraging multimodal information (visual and textual data).

2.VABS focuses on non-factual and uncertain information related to personal preferences, tastes and opinions. As a consequence, research in this novel field touches many aspects of learning, vision, cognitive science and perception. For this very reason, we believe that CVPR is the perfect venue to find and bring together such a heterogeneous and complementary set of competences.

Some specific areas of interest include, but are not limited to:

* analysis of image attractiveness ( high- and low-level image quality assessment)
* face analysis and aesthetics
* image and text memorability
* image and visual text understanding
* visual attributes for analysis beyond semantics
* multimodal/multimedia benchmarks
* visual style and affordances

The maximum paper length is 8 pages. The workshop paper format guidelines are the same as the Main Conference papers.
Submissions will be rejected without review if they: contain more than 8 pages, violate the double-blind policy or violate the dual-submission policy.

Submission: March 30th, 2013 11:59pm. EST
Notification: May 3rd, 2013
Camera ready: May 17th, 2013
Workshop: June 28th, 2013

Submission: March 30th, 2013 11:59pm. EST
Notification: May 3rd, 2013
Camera ready: May 17th, 2013
Workshop: June 28th, 2013

Luca Marchesotti, Xerox XRCE
Aude Oliva, MIT, CSAIL

Alexander Berg, Stony Brooks
Teofilo Campos, University of Surrey
Christel Chamaret, Technicolor
Serge Belongie, UCSD
Alessio Del Bue, IIT
Edward Gibson, MIT
Derek Hoiem, UIUC
Diane Larlus, Xerox Research Centre Europe Naila Murray, Xerox Research Centre Europe Devi Parikh, Virginia Tech Florent Perronnin, Xerox Research Centre Europe Hanspeter Pfister, Harvard Nicu Sebe, University of Trento Antonio Torralba, MIT Joost Van de Weijer, UAB Maria Vanrell, CVC Barcelona

Tamara Berg, Stony Brooks
Kristen Grauman, University of Texas
Alexei Efros, CMU
David Forsyth, UIUC
Aaron Hertzmann, University of Toronto
James Wang, Penn State

CAP 2013: 10 days before the deadline

CAP 2013

CAP is a French conference on Machine Learning.
July 3-5 2013

paper submission deadline: April 1st

You can submit in English!

CAP tutorials and lectures will be given by:
– Antoine Bordes
– Radu Patrice Horaud

Accepted papers will be publicly available on open archive (provided that authors consent). CAP is organized within the AI french platform with other conferences (Planning and sequential learning; Agent based systems; knowledge representation;…)

Philippe Preux
Marc Tommasi


IbPRIA 2013 – 6th Iberian Conference on Pattern Recognition and Image Analysis Madeira, Portugal June 4-7, 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.

For this edition, the conference venue will be the outstanding Pestana Casino Park Hotel, part of the most emblematic tourist complex of Madeira Island.

Further information can be found on the conference website:

We are very pleased to announce that invited speakers Prof. J.K, Aggarwal, Prof. Joachim M. Buhmann and Prof. Fernando Lopes da Silva will be giving talks at IbPRIA 2013:

Prof. J.K. Aggarwal (University of Texas, USA) Human Activity Recognition

Prof. Joachim M. Buhmann (ETH Zurich, Switzerland) Big Data: where is the information?

Prof. Fernando Lopes da Silva, (University of Amsterdam, The Netherlands) Analysis and modeling of brain signals dynamics: some insights and many queries

Apart from the invited speakers, the programme will mainly consist of oral and poster presentations given by authors of accepted papers. A preliminary program can be found here:

In addition, two tutorials and two special sessions will be held at IbPRIA 2013:

Full registration includes: conference sessions, proceedings, lunches, coffee breaks and conference dinner.
Student registration includes: conference sessions, proceedings, lunches and coffee‐breaks. Conference dinner is not included.
For AERFAI/APRP members tutorial registration is free of charge.

Discounts for early registration is open to 25 of March 2013:

General Chairs :
João M. Sanches , Instituto Superior Técnico, Universidade Técnica de Lisboa, Portugal Luisa Micó, University of Alicante, Spain

Local Chair:
Jaime S. Cardoso, INESC TEC and Faculty of Engineering of University of Porto, Portugal

Local Committee:
Pedro Quelhas, INEB and Faculty of Engineering of University of Porto, Portugal Luis F. Teixeira, Faculty of Engineering of University of Porto, Portugal Lucian Ciobanu, INESC TEC, Portugal Ines Domingues , INESC TEC and Faculty of Engineering of University of Porto, Portugal

Co-Chairs Area 1. Computer Vision:
Filiberto Pla, University Jaume I, Spain Majid Mirmehdi, University of Bristol, United Kingdom

Co-Chairs Area 2. Pattern Recognition and Machine Learning Nuno Vasconcelos, University of California, San Diego, USA J. K. Aggarwal, University of Texas, USA

Co-Chairs Area 3. Image and Signal Processing José Príncipe, University of Florida, USA Mario Figueiredo, Universidade Técnica de Lisboa, Portugal

Co-Chairs Area 4: Applications
Aurélio Campilho, University of Porto, Portugal Jelena Kovacevic, Carnegie Mellon University, USA

ACML-2013 (5th Asian Conference on Machine Learning), Call for Workshop Proposals

Call for Workshop Proposals

5th Asian Conference on Machine Learning,
Canberra, Australia

The 5th Asian Conference on Machine Learning invites proposals for workshops to be held on Wed 13 Nov, 2013, at the Australian National University, Canberra, Australia. The conference aims at providing a leading international forum for researchers in machine learning and related fields to share their new results, ideas and discuss emerging topics. Submissions from outside the Asia-Pacific region is also highly encouraged.

Workshop proposals that explore the application of machine learning methods to real-world problems are preferred. Of particular interest is exploratory research that describes novel learning tasks and applications requiring non-standard techniques. Submissions that demonstrate both theoretical and empirical rigor are especially encouraged.

Workshop proposal should contain the following within 2 pages, and submitted via email in PDF format to the Workshop Chair

• Title and specific goals
• Specific topics to be addressed
• Relevance and significance of this workshop to the main conference • A history of the workshop, if not being offered for the first time • Invited speaker(s) for the workshop, and whether they have been contacted • Estimated paper submission volume and paper acceptance rate • Expected attendance • Length – Full day or half day • A draft workshop call for contributions with:
• The names, affiliations, and email addresses of the workshop organizers, who should be experts in the related topics and preferably from multiple institutions
• The paper selection process
• A list of potential Program Committee members and their affiliations

Workshop proposals will be evaluated based on:
• Quality and level of detail of the proposal • Theme of the workshop and its relevance to the main conference • Overall balance of the conference workshop program

**Important dates**
Workshop proposals due 10 April, 2013
Acceptance notification 1 May, 2013
Workshop material/Website due Sept, 2013 ACML workshop Nov 13, 2013

ACML 2013:
General Co-chairs: Wray Buntine (NICTA and ANU) and Bob Williamson (ANU and NICTA)
PC Co-chairs: Tu Bao Ho (JAIST, Japan) and Cheng Soon Ong (NICTA)
Tutorial and Workshop Chair: Lexing Xie (ANU)
Publication Chair: Justin Domke (NICTA)

Workshop on Dynamics of Biological Networks, Edinburgh 25-26 June

Dynamics of biological networks workshop, Informatics Forum, University of Edinburgh, 25-26 June 2013

Workshop and registration website

Dynamical models of biological systems have received considerable attention in the machine learning and systems biology community. Two problems which have received particular attention are the inference of network structures from data (structure learning problem) and the identification of parameters and functional forms describing the dynamic of the systems given a networks structure. This workshop will bring together experts in dynamical systems, network inference and systems biology to define and address the outstanding challenges in the field, as well as presenting the latest research.

Confirmed Keynote Speakers
Dirk Husmeier (Glasgow)
Heinz Koeppl (ETH Zurich)
Olga Troyanskaya (Princeton)
Eric Xing (CMU)

The workshop registration will start at 11:30am on Tuesday, 25 June (followed by lunch at 12:00), and end at 3pm on Wednesday 26 June. There will be lunch available on both days, and a workshop dinner on 25. June. The programme will include invited keynote lectures, contributed talks and posters, and a discussion session.
Attendance of the workshop is free. At this point we invite contributed talks and posters. Please register and submit your abstract using the following website: Workshop Registration

Guido Sanguinetti (Edinburgh)
Edoardo Airoldi (Harvard Statistics)
Matthias Hennig (Edinburgh)

BBSRC International Partnering Award between Edinburgh and Harvard (to G.S.)
The Scottish Informatics and Computer Science Alliance

IEEE Computational Intelligence Magazine: Special Issue on space systems and operations

IEEE Computational Intelligence Magazine (impact factor 3.368)
Special Issue on “Computational Intelligence for Space Systems and Operations”

Call for Papers

Current and future space missions require an increasing level of autonomy or intelligence distributed across the space systems that have computing capabilities to implement intelligent functionalities for decision making. Such computational intelligence (CI) allows spacecraft (vehicles and robots alike) to respond rapidly to opportunistic events in deep space when remote operations are not practical due to communication latency, or to enable ground operators to optimize complex mission (e.g., involving multiple spacecraft) planning and scheduling processes, and so on. Typical CI approaches that can be used to improve spacecraft autonomy include mathematical, probabilistic and statistical modelling, control, automation and optimization, safety and reliability, system identification, monitoring and fault detection, etc. There are therefore strong motivations to develop these expertise areas for answering to the research challenges posed by astronautics and space engineering.

This special issue invites papers that tackle space engineering problems using CI techniques, with particular interests in the following topics:
• Autonomous mission planning and scheduling for manned/unmanned single/multiple spacecraft
• Autonomous 2-dimensional or 3-dimensional path planning for space and planetary robots
• Autonomous fault detection, isolation and recovery
• Automated spacecraft vision-based feature tracking identification
• Complex space systems modelling and control
• Space software validation and verification
• Human-machine interface within space missions

Submission of Manuscripts: 1st May 2013
Notification of Acceptance: 1st June 2013
Submission of Camera-Ready Papers: 1st July 2013

Paper Submissions
The maximum length for the manuscript is typically 25 pages in single column with double-spacing, including figures and references. Authors of papers should specify in the first page of their manuscripts corresponding author’s contact and up to 5 keywords. Submission should be made via email to one of the guest editors below:

Guest Editors
Prof. Dr. Yang Gao
Surrey Space Centre, University of Surrey, UK
Email: yang.gao(at)

Dr. Nicola Policella
ESOC, European Space Agency, Germany
Email: nicola.policella(at)

Prof. Dr. Frank Kirchner,
DFKI, Germany,
Email: frank.kirchner(at)

More information
Visit the following webpage for further information: