Vidi Video

Prof. Dr. ir. Arnold Smeulders
a.w.m.smeulders@uva.nl

The Intelligent Systems Lab Amsterdam at the University of Amsterdam
UvA-ISLA
The University of Amsterdam is one of the largest universities of the Netherlands. the Informatics Institute of the UvA consists of three labs, one for computational science and one for human computer studies. The one engaged here is the Intelligent Systems lab Amsterdam, ISLA, a research group of ten faculty, 24 post-docs and engineers, and 40 Ph.D students on the theory, practice and implementation of multimedia information analysis including image and text search engines, learning from sensory data and indexing of large repositories. An important topic of the ISLA is video and text search engines. In addition it has performed well in the leading international competitions for video (TRECvideo best interactive search in 2004 and in 2005) as well as query – answer text competitions (IMMIX) and as well as robot soccer (won the world simulation title in 2003). ISLA produces more than 5 papers per year in the top-ranked journals of the field such as the IEEE transactions PAMI, the International Journal of Computer Vision, and the ICCV conference series. ISLA has an extensive record in co-operations with Dutch institutions and industry in the area of multimedia and video analysis. ISLA has the leading role in MultimediaN the national public-private partnership of multimedia with a budget of 32 MEuro. The international review committee for the evaluation of the quality of computer science in the Netherlands, ranked the ISLA-ISIS-group of A. Smeulders highest overall of all groups in the Netherlands.

Vasileios Mezaris
bmezaris@iti.gr

Informatics and Telematics Institute at the Centre for Research and Technology Hellas
CERTH-ITI
The Informatics and Telematics Institute ITI at the Centre for Research and Technology Hellas, CERTH-ITI, has participated in more than 50 EC IST projects and 75 National projects and subcontracts. Over the last eight years, the ITI research team has authored over 125 publications in scientific journals, 35 book chapters and over 360 presentations to international conferences in areas such as image and video analysis, multimedia indexing and retrieval, informational retrieval and knowledge discovery for semantic-web applications, intelligent human computer interaction and intelligent agents, MPEG-7 and MPEG-21 standards. The Multimedia Knowledge Laboratory of CERTH-ITI is participating inthe IST-FP6 Integrated Project aceMedia and is leading the “Ontology Infrastructure, Knowledge-Assisted Content Analysis, Semantic Reasoning and Intelligent Content Retrieval” area. It is also participating in the IST-FP6 NoE "Knowledge Web" and in the COST 292 "Semantic Multimodal Analysis of Digital Media". CERTH-ITI is also participating in the recently started projects: ”MESH: Multimedia Semantic Syndication for Enhanced News Services, IST-IP”, “X-Media: Knowledge Sharing and Reuse Across Media, IST-IP”, “K-Space: Knowledge Space of Semantic Inference for Automatic Annotation and Retrieval of Multimedia Content, “BOEMIE”: Bootstrapping Ontology Evolution with Multimedia Information Extraction, IST-STREP”, and “ELU: Enhanced Learning Unlimited, IST-STREP. CERTH¬ITI is also leading the Greek national R&D Training Network MULTI-MINE. The Greek General Secretariat for Research and Technology has funded the set-up of the following CERTH-ITI spin-off company: “SerVisio: Providing Services in Intelligent Content-Based Management and Search of Visual Data”. CERTH-ITI was the coordinator of the successful IST-FP5 NoE “SCHEMA: Network of Excellence in Content-Based Semantic Scene Analysis and Information Retrieval”.

Prof. Isabel Trancoso
isabel.trancoso@inesc-id.pt

Institute for Systems and Computer Engineering: Research and Development
INESC-ID
The Institute for Systems and Computer Engineering is a non-profit institution dedicated to research in the field of information and communication technologies. Its mission is to develop tomorrow' technologies by excelling in research today. It holds more than 70 staff – mostly university professors – and numerous post-graduate students. INESC-ID has generated in the last 5 years more than 1000 scientific papers in journals and international conferences, dozens of industrial prototypes and computer systems based on state-of-art technologies, and a number of patents and awards. Currently the five main activities are: Information and Decision Support Systems, Interactive Virtual Environments, Embedded Electronic Systems, Communications and Mobility Networks, and Spoken Language Processing. The latter area of activity is carried out at L2F which aims to bridge the gap between natural spoken language and the underlying semantic information. The lab includes approximately 30 researchers. Their background ranges from Electrical Engineering to Computer Science and Linguistics. This strongly interdisciplinary group is actively involved in speech recognition, synthesis, coding, and understanding. Also audio indexation, language identification, and semantic processing paradigms, are topics of study to name just a few. L2F's work has been internationally recognized through close cooperation with other research centers in Europe and in the United States, as well as through the recent organization of the conference INTERSPEECH'2005. Some landmarks were the first text-to-speech synthesizer in 1991, and the first large vocabulary continuous speech recognition system for our language in 1997. Among the many European projects in which we have been involved in, we mention the E-Circus project (Education through Characters with Emotional Intelligence and Role-playing Capabilities that Understand Social Interaction), and the Alert project (Alert System for Selective Dissemination of Multimedia Information (2000-2003). The topic of the current proposal is within one of the 3 main areas of activity of L2F: semantic processing of multimedia contents. We are using large vocabulary speech recognition system, associated with audio segmentation and classification, automatic topic indexing and segmentation and summarization techniques, to generate category information as semantic markup of multimedia data. This type of processing has been extensively applied to Broadcast News and, more recently in the development of meeting browsers and lecture browsers.

Dr. Krystian Mikolajczyk
k.mikolajczyk@surrey.ac.uk

The Centre for Vision, Speech and Signal Processing at the University of Surrey
UniS-CVSSP
The Centre for Vision, Speech and Signal Processing of the University of Surrey (UniS) is one of the UK largest group in image analysis and computer vision. Research in the Centre for Vision, Speech and Signal Processing (CVSSP) focuses on image interpretation and understanding. The Centre enjoys international reputation for its contributions to various aspects of computer vision and pattern recognition. In many research topics it is acknowledged as a leading player, including sensory data representation and, in particular, the identification of significant attributes for sensory data interpretation. CVSSP's work on machine learning and on contextual decision making received the BMVA award of the Science Prize and Pattern Recognition Society Prize respectively. The method of perceptual grouping based on the Robust Hough Transform pioneered by the Centre has become a widely used tool for shape analysis and detection, motion estimation and segmentation and even for mixed pixel classification in remote sensing. CVSSP shared an EU Grand Challenge Prize in computer imaging for its role in the development of the software for the winning 3D Scanners IT product Model Maker in 1996. Its success in collaborating with industry is reflected in the DTI, the Secretary of State's University/Industry Partnership First Prize in 1999 and the spin out companies that emanated from the Centre. The Centre successfully participated in a number of EU projects in computer vision (VAP, VAP2, RETINA,SAM) image communication (SCALAR), visual inspection (AVIS, ASSIST), personal identity verification (M2VTS,Banca), video retrieval (ASSAVID) and cognitive vision based video annotation project VAMPIRE where it had the responsibility for contextual decision making and its role in sports video interpretation. Currently CVSSP is engaged in project COSPAL, where it has the responsibility for symbolic reasoning and learning.

Prof. Alberto Del Bimbo
delbimbo@dsi.unifi.it

Media Integration and Communication Centre at the Università degli Studi di Firenze
UniFi-MICC
The Università degli Studi di Firenze is a public institution providing higher level education to more than 50.000 students. The Media Integration and Communication Centre was established in September 2001 by the Italian Ministry as a national “Centre of Excellence”. Its mission is to develop qualified research and innovation transfer in cooperation with national and international universities, research institutions and companies, as well as high¬level education, in cooperation with the Master in Multimedia of the University of Firenze, focusing on
(a) information Access and Human-Machine Interaction: image analysis pattern recognition and computer vision; image and video understanding; image, video and 3D content based retrieval; multimodal interaction; interface usability and accessibility, engineering and ergonomic factors.
(b) Multimedia Communication: advanced solutions for the distribution of objects and multimedia applications via Internet; legal aspects; self¬governing regulations at different territorial levels; quality of the service.
(c) Information protection: security aspects, protection of intellectual property, privacy of information, local regulations; technological solutions that allow strengthening of legal bonds; techniques for copyright protection; protocols and standards for the representation and distribution of images and videos at various levels of security.

Dr. Jordi Gonzales
jordi.gonzalez@cvc.uab.es

Computer Vision Center
CVC
The CVC is a non-profit institution founded in 1995 by CIRIT (Consell Interdepartamental de Recerca i Innovació Tecnològica), CIDEM (Centre d'Innovació i Desenvolupament Empresarial) and UAB (Universitat Autònoma de Barcelona). The strategic objective of CVC is to do both Research and Development of quality on Computer Vision. From a scientific point of view, the CVC wants to contribute to increase the knowledge in this field. From a technological point of view, the CVC aims to contribute to innovation and industrial competitiveness collaborating with companies to develop technological projects.

Johan Oomen Ma
joomen@beeldengeluid.nl

Stichting Nederlands Instituut voor Beeld en Geluid
S&V
The Stichting Nederlands Instituut voor Beeld en Geluid (Netherlands Institute for Sound & Vision) archives 700,000 hours of television, radio, music and film, making Sound & Vision one of the largest audio-visual archives in Europe. Sound & Vision is the ‘working archive’ of the national broadcasting corporations, a cultural history institute and also a unique media experience for its visitors. Media production professionals use the collections for new programs and the archive is a unique source of information for research, not only for students and academics, but also for journalists. Furthermore, the audiovisual material is a most valuable addition to traditional teaching methods; hence Sound & Vision also promotes the use of media in education. Sound & Vision has launched a large-scale IT framework to anticipate digital media production. Since March 2005 key parts of the internal workflows have been automated. Sound & Vision is a member of the International Federation of Television Archive. It has been involved in the following EU-funded projects. FP4: VICAR (Video Indexing Classification Annotation Retrieval). FP5: AMICITIA (Asset Management Integration of Cultural heritage in the Inter-exchange between Archives), PRESTO (Preservation Technology); ECHO (European Chronicles Online). MediaPLUS program: BIRTH (Building of Interactive Research and delivery network about Television History). FP6 PrestoSpace (Preservation towards Storage and Access), P2P FUSION (Finding, Utilizing, and Sharing medIa Objects over P2P Networks), and MultiMATCH (Multicultural and Multilingual Access to Cultural Heritage)

Prof. Maurizio Lunghi
lunghi@rinascimento-digitale.it

Fondazione Rinascimento Digitale
FRD
The Digital Renaissance – New Technologies for Culture Heritage Foundation, works to stimulate the adoption of new ICT technologies and in collaboration with other research institutions it enables the documentation, promotion, training in best practices in the management and the archiving of digital materials, and the preservation of digital memories. In order to reach such objectives, the Foundation looks for establishing a reference point on: define standard methodologies and working modalities and practical tools for long term preservation of digital memory (both digitalized or born digital), develop effective strategies on digital memory preservation of culture heritage; design, produce and test architectures and tools for “Trusted Digital Repositories” for the most kind of different digital object concerned on cultural heritage; select and develop ‘good practice examples’; invest in training activities to facilitate optimal use of new languages and technologies by culture heritage operators. The Digital Renaissance Foundation has launched in 2005 some strategic projects on digitalization, on designing and building archives based on integrated data strategies, on digital memory preservation, for a total amount of co-funding of about 1.7 M. At the moment, for example, FDR is supporting the establishing and Italian national network, involving different actors interested in Digital Libraries Application (DLA), like cultural institutions, e-government bodies, research community, industry, multimedia content producers to bring co-ordination to action at national level. The aim of the workgroup is to define the state of the art in the sector, and to locate characteristics and functions of digital libraries applications focused on user expectations and needs. In this direction FRD is building different significant user groups collecting the most important Italian user of the different digital objects. For the audiovideo framework, FRD is now collaborating with Istituto Luce, Mediatica Regionale Toscana and the Italian production structure of National Geographic (video). The FDR has acted in cooperation with the EU Projects of PRESTOSPACE, DELOS, MINERVA projects and others to co-fund initiatives aimed at creating a map of risks for sound and musical archives in Italy, at producing some technical guidelines, linked to the IASA ones (International Association of Sound Archives), at developing a training programme for Italian professionals. The FDR also brings experience in managing technology watch activities to the project (e.g. it is leading a study on risks of ICT technology ageing and fragility: in particular the mass memory support like CD, DVD and magnetic disks, will be tested).

Prof. Rita Cucchiara
rita.cucchiara@unimore.it

University of Modena and Reggio Emilia
Unimore

A very old academic institution, founded in 1177 with 12 different Faculties; Computer system education is covered in two Faculties of Engineering, in Modena and in Reggio Emilia. The Dipartimento di Ingegneria dell’Informazione is the research institution grouping research activities in computer engineering, electronics and telecommunications with about 30 staff people and 100 external collaborators. Within DII, the Imagelab group is involved in researches in image analysis, computer vision and multimedia with many collaborations with public and private institutions. In medical imaging, Imagelab collaborates with medical Departments and with the Burhnam Institute USA. In motion analysis and surveillance is involved in several projects for Formula-1 car telemetry with Ferrari SpA, urban traffic control with Traficon Belgium, people surveillance with Hebrew Univ. (Israel), Univ. of Tech. in Sidney (Australia), Univ. of Central Florida (USA). In multimedia ImageLab participated to the European NoE DELOS VI FP and in the Vidi-VIDEO Project VI FP. In machine vision collaborates with several companies for robot vision. Imagelab is staffed by ten permanent members, together with several graduating students and collaborators. ImageLab comprehends also a spin-off VISION-E working in surveillance and robot vision applications.