Cette page appartient aux archives web de l'EPFL et n'est plus tenue à jour.
This page belongs to EPFL's web archive and is no longer updated.

News of the MMSPG

Special Issue on Multimedia Quality Assessment of IEEE Signal Processing Magazine


Special Issue on Multimedia Quality Assessment



The field of multimedia is maturing and one of the positive outcomes is the increasing number of new, innovative and improved products and services. It is, however, no longer sufficient to just add features to a multimedia product or service; it is also vital to measure the added value, in terms of quality, for end-users.  The era of user-centric multimedia has already begun and Quality of Experience (QoE) plays a central role, bringing a new and fresh look at the quality and performance of multimedia systems. In contrast to traditional QoS, which aims to capture the system-related characteristics, QoE is not restricted to subjective perception based on fidelity measures. Instead, QoE extends to user behavior/needs, appropriateness, context, usability and other human factors pertaining to delivered content. Evaluation of QoE requires comprehensive subjective quality assessment methodologies and objective quality metrics based on models of human perception, behavior, and sense of presence. These metrics must also incorporate such issues as end-to-end system issues, environmental context, user preference, and human-machine interaction.

The aims of this special issue are to provide researchers and professionals in the field of multimedia signal processing with well‐written tutorial‐style papers addressing the latest advances in the evaluation and assessment of multimedia quality. The targets are not only traditional media such as speech, audio, image and video, but also new types of emerging media.


Scope of Topics

-        Speech and audio subjective and objective quality assessment and metrics

-        Image and video subjective and objective quality assessment and metrics

-        Audio-visual quality assessments and metrics

-        Subjective and objective quality assessment and metrics for new media (UHD, HDR, stereo and multiview, 3D audio, haptics, etc.)

-        Human sensory models and their applications to media quality assessment

-        Standards, and benchmarking efforts in media quality assessment

-        Applications of media quality assessment

-        Multimedia quality of experience assessment and metrics

Submission procedure

Prospective authors should submit white papers at http://mc.manuscriptcentral.com/spmag-ieee according to the timetable below. White papers should include the motivation, the significance of the topic to be addressed, a brief summary, an outline of the content and the key references. White papers should be no more than 2 pages in the IEEE single‐space double‐column format.



White paper due: July 19th, 2010

Invitation notification: August 30th, 2010

Manuscript due: November 15th, 2010

Acceptance Notification: January 17th, 2011

Revised Manuscript due: April 18th, 2011

Final Acceptance Notification: May 16th, 2011

Final Manuscript due: July 15th, 2011

Publication date: November 2011


Guest Editors:

Touradj Ebrahimi, EPFL/NTNU, Switzerland/Norway (Touradj.Ebrahimi@epfl.ch)

Lina Karam, ASU, US (karam@asu.edu)

Fernando Pereira, IST-IT, Portugal (fp@lx.it.pt)

Khaled El-Maleh, Qualcomm, US (kelmaleh@qualcomm.com)

Ian Burnett, RMIT, Australia (ian.burnett@rmit.edu.au)

Posted by Touradj Ebrahimi at 17:55
Hot 3D - International Workshop on Hot Topics in 3D


International Workshop on Hot Topics in 3D

(in conjunction with ICME 2010)

Singapore, July 23, 2010

The 3D research community is at a potentially revolutionary point. From one side, 3D display technology is at the verge of becoming widespread and reasonably priced, and that includes autostereoscopic displays. From another direction, increases in computational power - including powerful GPUs - has allowed an ever-increasing realism in 3D scene generation. 3D audio in now often tightly integrated with 3D envi-ronments, including 5.1 (and higher) and even 3D soundfield reproduction. Haptic sys-tems are also being tightly integrated within 3D systems. Quality evaluation of 3D systems itself is of great importance, and is also showing fast progress. Finally, new depth cameras, coupled with new 3D analysis and synthesis algorithms is close to enable commercial-quality 3D rendering of real scenes, instead of being restricted to synthetic scenes as in the past.

All these factors together create the 'perfect storm': an environment prone for an explosion of related technology and applications, with a speed of development that will not fit in the (slower) cycle of traditional conferences and journals. In other words, while appropriate venues for presenting research at advanced stages is plentiful, the 3D Multimedia community lacks an appropriate venue for receiving feedback during early or initial stages of the development of radical or potentially disruptive technology.

This is exactly the void that Hot3D tries to fill, providing an environment for lively discussion of early-stage, potentially disruptive research.


Papers in all areas of Multimedia 3D are solicited. Early stage or preliminary re-sults from potentially disruptive technology is particularly encouraged. Full papers (up to 6 pages) will be published in the ICME proceedings.

Additionally, and maybe most importantly, position papers are solicited for short presentation and discussion of preliminary work or ideas. Submit a proposal of up to 2 pages, with a decision expected up to 3 weeks after submission.

The 1-day workshop will be held on Thursday, July 23, and is co-located with ICME, the flagship multimedia conference sponsored by four IEEE societies. The work-shop will be a unique opportunity to interact with other researchers working on 3D Multimedia. With an environment designed to facilitate discussion and feedback in ear-ly stage research, as well as forge new collaboration, this is an event not to be missed.


  • Submit Regular Paper (up to 6 pages) by: March 22, 2010
  • Notification of Regular Paper Acceptance: April 7, 2010
  • Camera-Ready Paper Due: April 15, 2010
  • Position Paper (up to 2 pages) Submission: ASAP, up to May 15, 2010
  • Notification of Position Paper Accept.: April 7, 2010 (for papers submitted March /20)


Uptodate information on hot3d.org

You can download a PDF version of this Call for Paper by clicking on the link below

Posted by Lionel Rhyn at 17:19
VCIDS'10: Call for Papers


Workshop on Visual Content Identification and Search (VCIDS’10)

Singapore, July 23, 2010, in conjunction with ICME 2010


Sponsored by the Technical Committee on Multimedia Computing of IEEE Computer Society

Research and development in visual content identification and search have reached a watershed that large-scale commercial applications start to emerge. In the last few years, major Hollywood movie studios and TV networks have adopted video fingerprinting and content identification technologies to track and manage their content at the Internet scale. In the meantime, major Internet search engines such as Google and Microsoft Bing have added content-based visual similarity search to supplement traditional keyword-based queries. While the wave of commercialization is underway, many technical challenges remain and significant progress is made continuously in research and development.

It is recognized that despite unique requirements for diverse applications, visual content identification and search, specifically for image and video content, share some fundamental technologies such as visual features and descriptors, and indexing and search techniques and strategies. This Workshop focuses on algorithms, systems, applications and standards for visual content identification and search. It aims to bring together researchers and practitioners in both industry and academia to discuss the latest advances and exchange views and ideas in related technologies and applications. Topics of interest include, but are not limited to


Visual Content Identification and Search Algorithms and Techniques

  • Visual features and descriptors for image and video content
  • Indexing, matching, and search in large database
  • Content clustering and classification by visual similarity
  • Machine learning and data mining for visual content discovery
  • Modeling and evaluation of content-based identification and search

Visual Content Identification and Search Systems and Standards

  • Visual content identification (copy/duplicate/near-duplicate detection systems
  • Visual search engines
  • Visual search in mobile devices
  • Emerging standards related to visual content identification and search

Applications of Visual Content Identification and Search

  • Content filtering, tracking, and protection
  • Content recommendation and contextual ad targeting
  • Content-based ID in media asset management
  • Visual content search in online shopping
  • Landmark identification and augmented reality


The Workshop will contain both invited presentations and those accepted from open submissions. Additionally, the Workshop will feature a keynote and a panel discussion by leading researchers and industry experts.

Prospective authors are encouraged to submit full-length papers following the same guidelines and requirements for the regular ICME papers by the deadline below. All submissions will be peer-reviewed and must contain original, previously unpublished research or engineering work.


Important Dates:

Paper submission deadline: March 1, 2010
Notification of Acceptance: April 1, 2010
Final camera-ready paper due: April 15, 2010


Jian Lu Xian-Sheng Hua Dong Xu
Vobile, Inc. Microsoft Research Asia Nanyang Technological University
jian@computer.org xshua@microsoft.com dongxu@ntu.edu.sg
Posted by Lionel Rhyn at 11:35
Elsevier Journal Signal Processing: Image Communication - Special Issue on Image and Video Quality Assessment


Elsevier Journal Signal Processing: Image Communication
Special Issue on Image and Video Quality Assessment


Call for Papers
Quality control of images and videos from the input (capture device) to the final output (display and its environment) presented to the human user is essential for image/video applications and services.
PSNR and other connected measures have long been the most popular quality criteria used by engineers and researchers to evaluate and optimise the performances of digital image and video processing schemes. However, these simple-to-compute measurements are not in good agreement with human visual quality judgment. Therefore, there is an established need for efficient Image and Video Quality Assessment schemes (IQA/VQA).
Over the two past decades, objective image & video quality assessment methods have been extensively studied, and many criteria have been designed. Depending on the application considered and the type of information accessible, IQA/VQA can be classified into three types: Full Reference metrics (FR), Reduced Reference metrics (RR), and No Reference Metrics (NR). All these types of visual quality metric are now considered for standardization by various groups, including the Video Quality Experts Group (VQEG) for video and JPEG Advanced Image Coding (AIC) for images.
Even if improvements have been achieved compared to PSNR, there is a need for more efficient and generic IQA/VQA algorithms that are more robust to the image & video content and also to the different types of impairments introduced by the degrading systems.
The aim of this special issue is to provide an overview of state-of-the-art IQA/VQA methods and to address new developments of quality criteria towards many directions such as higher performances in specific applications (coding scheme, resolution, etc.), robustness to the image/video content (content adaptation), and others. This issue calls for high quality, original contributions, including both theory- and practice-oriented papers. Topics of interest include, but are not limited to:
-          Impairment-based annoyance modelling (supra-threshold)
-          No reference robust visual impairment detection and measurement
-          Spatio-temporal mechanism modelling
-          Modelling of temporal human visual quality judgment (from on the fly to a global video quality assessment)
-          Modelling of spatial or spatio-temporal pooling
-          Error sensitivity-based approaches
-          Impact of transmission errors on visual quality (current coding standards and next generation standards)
-          HVS model-based objective quality metrics
-          Other objective quality metrics: impairment-based, structural-based, application-based (hybrid IQA/VQA), …
-          Objective quality metrics for multimedia (audio-visual quality assessment)
-          VQA metrics for mid- to low-quality regimes and for high-quality regime (HDTV)
-          Full color IQA/VQA metrics
-          Perception, annoyance, IQA/VQA modelling in 3D image/video

Special Issue Structure: the special issue will consist of two invited papers and the 7-8 best papers from an open call selected on a competitive basis. The invited papers will come from distinguished researchers in the field, presenting the latest developments of IQA and VQA criteria. The open call targets the wider research community.

Submission procedure: Prospective contributors are invited to submit manuscripts in PDF format only. Papers should be submitted electronically using online manuscript submission at http://ees.elsevier.com/image. Authors should indicate that their submission is intended for this special issue (on Image and Video Quality Assessment) in the remarks field.
Special issue timeline:
-          Manuscript submission deadline: 1 May 2009
-          Preliminary review results: 1 August 2009
-          Revised manuscript due: 1 October 2009
-          Expected publication date: January 2010
Guest Editors:
Dominique BARBA, Universit de Nantes, France, email: dominique.barba@univ-nantes.fr
Vittorio BARONCINI, FUB, Roma, Italy, email: vittorio@fub.it
Frdric DUFAUX, Ecole Polytechnique Fdrale de Lausanne, Switzerland, email: frederic.dufaux@epfl.ch
Stefan WINKLER, Symmetricom, San Jose, USA, email: swinkler@symmetricom.com
Posted by Frdric Dufaux at 14:55
Call for Papers: Special Issue on Distributed Video Coding in EURASIP Journal on Image and Video Processing
EURASIP Journal on Image and Video Processing

Special Issue on Distributed Video Coding

Call for Papers

Distributed source coding (DSC) is a new paradigm based on two information theory theorems: Slepian-Wolf and Wyner-Ziv. Basically, the Slepian-Wolf theorem states that, in the lossless case, the optimal rate achieved when performing joint encoding and decoding of two or more correlated sources can theoretically be reached by doing separate encoding and joint decoding. The Wyner-Ziv theorem extends this result to lossy coding. Based on this paradigm, a new video coding model is defined, referred to as distributed video coding (DVC), which relies on a new statistical framework, instead of the deterministic approach of conventional coding techniques such as MPEG standards.

DVC offers a number of potential advantages. It first allows for a flexible partitioning of the complexity between the encoder and decoder. Furthermore, due to its intrinsic joint source-channel coding framework, DVC is robust to channel errors. Because it does no longer rely on a prediction loop, DVC provides codec independent scalability. Finally, DVC is well suited for multiview coding by exploiting correlation between views without requiring communications between the cameras.

High-quality original papers are solicited for this special issue. Topics of interest include (but are not limited to):

* Architecture of DVC codec
* Coding efficiency improvement
* Side information generation
* Channel statistical modeling and channel coding
* Joint source-channel coding
* DVC for error resilience
* DVC-based scalable coding
* Multiview DVC
* Complexity analysis and reduction
* DSC principles applied to other applications such as encryption, authentication, biometrics, device forensics, query, and retrieval

Authors should follow the EURASIP Journal on Image and Video Processing manuscript format described at http://www.hindawi.com/journals/ivp/.

Prospective authors should submit an electronic copy of their complete manuscripts through the EURASIP Journal on Image and Video Processing Manuscript Tracking System at http://mts.hindawi.com/, according to the following timetable:

* Manuscript Due: May 1, 2008
* First Round of Reviews: August 1, 2008
* Publication Date: November 1, 2008

Guest Editors

* Frederic Dufaux, Ecole Polytechnique Fdrale de Lausanne, Lausanne, Switzerland
* Wen Gao, School of Electronic Engineering and Computer Science, Peking University, Beijing, China
* Stefano Tubaro, Dipartimento di Elettronica e Informazione, Politecnico di Milano, Milano, Italy
* Anthony Vetro, Mitsubishi Electric Research Laboratories, Cambridge, MA, USA
Posted by Frdric Dufaux at 23:04
Call for Papers in Applications of Digital Image Processing XXXI
Applications of Digital Image Processing XXXI
Conference OP317

Part of the SPIE International Symposium on Optical Engineering + Application
10-14 August 2008 ? San Diego Convention Center ? San Diego, CA USA

Conference Chair
Andrew G. Tescher, AGT Associates
Program Committee
Vasudev Bhaskaran, Marvell Semiconductor, Inc.; Bernard V. Brower, Eastman Kodak Co.; Wo L. Chang, National Institute of Standards and Technology; Touradj Ebrahimi, cole Polytechnique Fdrale de Lausanne (Switzerland); Ali Habibi, The Aerospace Corp.; T. Russell Hsing, Telcordia Technologies, Inc.; Kristina M. Johnson, Johns Hopkins Univ.; C.-C. Jay Kuo, Univ. of Southern California; Catherine Lambert-Nebout, Ctr. National d'tudes Spatiales (France); Andre J. Oosterlinck, Katholieke Univ. Leuven (Belgium); Sethuraman Panchanathan, Arizona State Univ.; Fernando Pereira, Instituto Superior Tcnico (Portugal); John A. Saghri, California Polytechnic State Univ.; Peter Schelkens, Vrije Univ. Brussel (Belgium); Gary J. Sullivan, Microsoft Corp.; Pankaj Topiwala, FastVDO LLC; Mihaela van der Schaar, Univ. of California/Los Angeles
The field of digital image processing has experienced continuous and significant expansion in recent years. The usefulness of this technology is apparent in many different disciplines covering medicine through remote sensing. The advances and wide availability of image processing hardware has further enhanced the usefulness of image processing. The Application of Digital Image Processing conference welcomes contributions of new results and novel techniques from this important technology.

Papers are solicited in the broad areas of digital image processing applications, including:

* medical applications
* restorations and enhancements
* digital cinema
* image transmission and coding
* color processing
* remote sensing
* robot vision
* hybrid techniques
* facsimile
* pattern recognition
* registration techniques
* multidimensional image processing
* image processing architectures and workstations
* video processing
* programmable DSPs for video coding
* high-resolution display
* high-quality color representation
* super-high-definition image processing
* impact of standardization on image processing.

Abstract Due Date: 28 January 2008
Manuscript Due Date: 14 July 2008

See more details in the attached pdf file.
Posted by Touradj Ebrahimi at 15:03
Special Issue on Visual Media Quality Assessment at the IEEE Journal of Selected Topics in Signal Processing.
Call for Papers

IEEE Journal of Selected Topics in Signal Processing
IEEE Signal Processing Society
Special Issue on Visual Media Quality Assessment

With the increasing demand for digital image and video technologies in applications as broad as entertainment and communications, security, monitoring, and medical imaging, there is a growing need for the automatic assessment of the quality of visual media. Many factors can affect and impair the quality of visual media including compression, transmission, protection, display, printing, acquisition and reproduction systems. Automatic visual media quality assessment is crucial for monitoring and controlling the visual quality in existing and emerging multimedia systems, and has the potential to impact next-generation systems by providing objective metrics for use during the design and testing stages and by reducing the need for extensive evaluation with human subjects.

Visual media quality assessment aims at quantifying the quality of visual media, including still pictures, image sequences, 3D visual data, and 3D models, by means of quality metrics. These metrics vary with the considered applications, and range from metrics that measure specific visual impairments to those that assess the overall visual quality in the presence of various impairments. For applications and products that target human consumers, it is desirable to have metrics that will predict the perceived visual quality as measured with human subjects. Visual quality assessment metrics can be further divided into full-reference, reduced-reference, and no-reference quality metrics. Full-reference visual quality metrics compare the to-be-assessed visual media to a reference, which is typically the original visual data. In many applications where the original visual data is not available, reduced-reference and no-reference metrics are used. Reduced-reference metrics make use of a set of reference features or characteristics, which could have been extracted from the original visual data. No-reference quality metrics attempt to predict the visual quality without any reference, which is very useful in practice but very challenging.

A great deal of interest and research have been devoted to the design and development of visual quality metrics, particularly full-reference and reduced-reference metrics for image quality assessment. However, for many applications, reliable automatic visual quality assessment is lacking, particularly those requiring no-reference visual quality assessment. In addition, there is a need for methods that can reliably assess the visual quality of video and other 3D visual media. The motivation for this special issue is to highlight the importance, challenges, and applications of visual media quality assessment and its interdisciplinary nature which includes vision science, optics, color science, signal processing, psychology, and biology. Our goal is to feature recent advances in the area of automatic visual media quality assessment, including theoretical, experimental, and computational methods and results. We invite researchers to submit original papers describing new approaches in all areas related to automatic visual media quality assessment including, but not limited to, the following topics:
- Global and impairment-specific visual quality assessment metrics
- Full-reference, reduced-reference, and no-reference visual quality assessment of still-pictures and video.
- Visual quality assessment of 3D visual data and 3D models
- Visual quality assessment of High-Definition image and video content
- Statistical methods for automatic visual quality assessment
- Perceptually/Biologically-inspired automatic visual quality assessment
- Visual quality metrics for specific applications

Submission procedure
Prospective authors can find submission information at http://www.ece.byu.edu/jstsp. Submitted manuscripts should not have been previously published nor be currently under consideration for publication elsewhere. Authors are advised to follow the Author's Guide for the formats of manuscripts submitted to the IEEE Transactions on Signal Processing as detailed at http://ewh.ieee.org/soc/sps/tsp/. The manuscript will undergo a standard peer review process.
Manuscript submissions due: April 30, 2008
First review completed: July 31, 2008
Revised manuscripts due: September 15, 2008
Second review completed: October 31, 2008
Final manuscript due: November 30, 2008

Lead Guest Editor
Lina Karam, Arizona State University, Tempe, Arizona (karam@asu.edu)

Guest Editors
Touradj Ebrahimi, EPFL, Lausanne, Switzerland (touradj.ebrahimi@epfl.ch)
Sheila Hemami, Cornell University, Ithaca, New York (hemami@ece.cornell.edu)
Thrasos Pappas, Northwestern University, Evanston, Illinois (pappas@ece.northwestern.edu)
Robert Safranek, Benevue, Warren, New Jersey (rjs@@benevue.com)
Zhou Wang, University of Waterloo, Waterloo, Ontario, Canada (z.wang@ece.uwaterloo.ca)
Andrew B. Watson, NASA Ames Research Center, Moffett Field, California (andrew.b.watson@nasa.gov)
Posted by David Marimon Sanjuan at 9:44
COST 292 Special Session: Towards Automated Robust Vision-based Surveillance
Call for Papers
COST 292 Special Session
Towards Automated Robust Vision-based Surveillance

Organisers: Dr. Noel E. O'Connor (DCU), Dr. Marzia Corvaglia (Uni. Brescia)

The members of the COST 292 action (http://www.cost292.org/) have a long tradition of involvement in WIAMIS, dating back to the establishment of this event. Since 2005, the action has been invited to organize a special session and this tradition will be continued for WIAMIS 2008. This year, the special session will focus on the newly identified priority areas of this action that fall into the broad area of automated visual surveillance. This new focus has been prioritized on the basis of the observation that research in Europe in this area is fragmented with no common forum for researchers working on different aspects of this broad topic. The goal of this special session is to help bring together researchers working on this topic and to help stimulate integration in this area.

Programme Subcommittee
Selim Aksoy, Bilkent Uni., Turkey
Michael Ansorge, EPFL, Switzerland
Yannis Avrithis, NTUA, Greece
Jenny Benois-Pineau, LABRI, France
Licia Capodiferro, FUB, Italy
Touradj Ebrahimi, EPFL, Switzerland
Alan Hanjalic, TU Delft, NL
Ebroul Izquierdo, QMUL, U.K.
Yiannis Kompatsiaris, ITI, Greece
Riccardo Leonardi, Uni. Brescia, Italy
Gorka Marcos Ortego, VICOMTech, Spain
Branimir Reljin, Uni. Belgrade, Serbia
Thomas Sikora, TU Berlin, Germany
Walter Stechele, TU Munchen, Germany

Topics of interest include, but are not limited to:
- Visual computation: background subtraction, object detection and tracking, body and face detection, face recognition,
- Event and activity modeling and analysis: human action modeling and recognition, crowd behaviour analysis;
- Multiple stream analysis: fusion across similar and/or differing visual modalities, augmenting visual analysis with other modalities such as audio;
- Architectures: video surveillance network architectures, new sensors and cameras;
- Annotation, Indexing and Storage: archival & retrieval of sensor data and extracted semantics, query paradigms and languages;
- Coding: event-/object-based compression for surveillance, scalable coding, distributed coding;
- Applications: crime prevention, aerial imaging (satellite, infrared), public transport systems, privacy protection, anonymity enforcement;

Important Dates
Paper Submission: Dec. 14, 2007
Review Results: Jan. 11, 2008
Camera-ready Papers: Feb. 01, 2008
Papers should conform to the usual WIAMIS guidelines for authors. All papers will be peer reviewed by the WIAMIS Technical Programme Committee and a special Programme Subcommittee set up specifically for this special session.

For more information contact:
Dr. Noel E. O'Connor, oconnorn (at) eeng (dot) dcu (dot) ie
Dr. Marzia Corvaglia, marzia (dot) corvaglia (at) ing (dot) unibs (dot) it
Posted by David Marimon Sanjuan at 9:42