Proceedings of ICME 2011

Acoustic and Video Coding and Communication

Room: JH1.08 Date: 7/11/2011 Time: 9:00-18:00

Multimedia communication through mobile networks and the Internet has rapidly become an essential way for us to communicate in the recent years. Multimedia communication includes and is not limited to peer-to-peer video calls and chatting, multi-point video conferences, live or adaptive streaming of movies and events, interactive viewing of graphic applications fully running in the cloud, etc. It involves audio, speech and video, all at the same time. To guarantee QoS, bandwidth limitation and network congestion are the main issues to be tackled. Furthermore, arising importance of low-delay interactive multimedia communications and applications requires special care and robustness against network delay and jitter. In this workshop, we aim to bring together speech, audio, video, and communication experts to present their latest research ideas on how to improve the QoS of multimedia communication and applications from both source coding and transport perspectives.

For the video part, what is next for video coding is a frequently asked question since the finalization of H.264/MPEG4-AVC in 2003. In early 2010, ITU-T and MPEG joined force again and launched together a standardization effort to develop HEVC (High Efficiency Video Coding), the next generation video coding standard. Such an effort represents simultaneously new opportunities and new challenges. Any future video standard needs to address not only the basic question of higher compression efficiency, but also better support for existing and emerging features such as 3D video and high dynamic range video. Furthermore, since digital video is being processed more commonly by a combination of software, GPU, and dedicated ASIC, new architecture friendly designs and better parallelization capabilities are also important topics to be considered. When delivering video over the Internet or mobile network, , and specially for low-delay real-time interactive applications, in order to ensure QoS, congest control and error control must also be taken into consideration.

For the speech and audio part, speech and audio coding has long been an important component of communication system design, especially when voice communication service was the main traffic in telecommunication system. With the ever-increasing high data rate available in new generation of communication systems, especially wireless communication systems, the role of speech and audio coding becomes different and more challenging: intelligibility requirement is being replaced by audio quality requirement. Users expect high quality, multi-channel, high dynamic-range audio experience over wireless and internet. Such a content-driven trend challenges researchers to provide better speech and audio coding/decoding schemes that not only provide high compression efficiency, but offer more enjoyable listening experience as well. Hence, cross-disciplinary research ranging from signal processing, machine learning, to psychoacoustics and auditory model is essential for developing successful next generation speech and audio coding.

All these factors together create the right moment for the AVCC workshop. The AVCC workshop provides a unique opportunity for people from both audio/speech and video backgrounds to hold joint discussions. It also provides an exciting forum for top researchers from both industry and academia to gather together and to share the latest research ideas and industry trends.

This workshop aims at high-quality original papers. Topics of interest include: advanced video coding technologies, including high efficiency video coding, scalable video coding, 3D video coding; speech, audio, image and video processing; detection of speech and audio signal in complex environments; statistical methods for speech and audio signal processing; low delay, interactive multimedia communications; error control and congestion control; error resilience coding and error concealment; complexity optimization, GPU and ASIC friendly design and implementation of speech, audio and video signal processing system.

The keynote speaker is Dr. John Apostolopoulos from Hewlett-Packard Laboratories. The title of his talk is “Future Multimedia Communications for Mobile Devices and Immersive Environments”.

Organizers:

Peng Yin, Dolby Laboratories Inc, USA

Yan Ye, InterDigital Communications Inc, USA

Pei-jung Chung, University of Edinburgh, UK

Zhiqiang Wu, Wright State University, USA

Streaming and Media Communications

Room: JH1.02 Date: 7/11/2011 Time: 9:00-18:00

Visual Content Identification and Search

Room: JH1.03 Date: 7/11/2011 Time: 9:00-18:00

Special Session: Multimedia Services and Technologies for E-health

Room: JH1.04 Date: 7/11/2011 Time: 9:00-18:00

It is our great pleasure to welcome you to the ICME 2011 Workshop on Multimedia Services and Technologies for E-health (MUST-EH). MUST-EH workshop was one of the first of its kind and aiming at a series of workshop in coming years. This workshop aimed to report on the recent advancement and developments in various aspects of multimedia applications in e-health such as health monitoring, ubiquitous health care, Adaptive exergames for health, QoS for health and so on.

The applications of multimedia services, tools and technologies revolutionize today’s healthcare system. These applications opened up on demand smart healthcare to innovative possibilities: healthcare professional can treat and monitor patient more effectively and efficiently as multimedia services and technologies facilitate medical multimedia data to be sent to clinic or travelling doctor’s locations from an ambulance or patient accident site; present multimedia service and technologies also enable remote consultations which result in reduced cost, accessing undeserved population and continuous quality care of patients.

The call for papers attracted 16 submissions from USA, Canada, Europe and different parts of Asia. The program committee accepted 9 papers that cover different aspect of multimedia services and tools in e-health. We hope that the proceedings will serve a useful reference for scientists, researchers and academics in the field of multimedia in e-health.

We would like to thank our program committee for their valuable support from their busy schedule. We also like to thank main workshop organizers for their kind follow up.

Organizers:

M. Shamim Hossain, King Saud University, KSU, KSA

Stefan Goebel, Technical University Darmstadt, Germany

Atif Alamri, King Saud University, KSU, KSA

Manzur Murshed, Monash University, Australia

Multimedia-Aware Networking

Room: JH1.05 Date: 7/11/2011 Time: 9:00-18:00

Latest advances in multimedia content encoding and representation, including HDTV, 3DTV, multi-view video and associated added-value interactive services, are offering to the end user a truly rich multimedia experience. At the same time advances in communications systems and network technologies give the ability to apply in-network processing techniques in order to take advantage of the available user and media contextual information for efficient, flexible and auto-configurable media transmission. On the other hand network-aware applications and cross-layer mechanisms are being developed in order to take advantage of network information and to adapt the media to the current network conditions, terminal capabilities, and user preferences.

This workshop solicits novel contributions and breaking results on all aspects of multimedia-aware networking. In particular, workshop papers should describe algorithms, issues and experiences related to content-aware networking and network-aware applications, future (media) Internet architectures, self-* and adaptivity, cross-layer design and optimization, applications, and interoperability. We are particularly interested in (but not limited to) areas such as

* Content aware networking and network aware application including content creation (coding (e.g., 2D/3D, SVC, HEVC), preparation, packaging), content delivery (transport, streaming, live, on-demand, real-time, download), content adaptation (server, in-network, client), content-aware and media-aware forwarding and routing, content consumption (widget), and context aware applications and networks.

* Future Internet architectures, in particular, content/media centric aspects, network/infrastructure management, network virtualization, and cross-layer design and optimization.

* Self-* and adaptivity in the area of self-organization, self-configuration, and self-healing.

* Interoperability (i.e., standardization) efforts related to high-efficiency video coding, 3D video coding, dynamic adaptive streaming over HTTP, and modern media transport.

The call for papers attracted 14 submissions (WoMANΥ11 only without special session) from Austria, Belgium, France, Germany, Greece, Italy, Romania, Taiwan, and United States of America. The program committee accepted eight papers covering a variety of topics, all in the context of multimedia-aware networking:

* Content-awareness and cross-layer optimizations for service and network providers;

* Performance evaluations of home gateways and interactive spherical videos;

* Enhancing legacy infrastructures with content-awareness;

* Scalable video coding packetization in peer-to-peer networks;

* Quality impact of media-aware network delivery;

* Home-gateway support and implementation of content-aware network nodes;

Furthermore, WoMANΥ11 hosts a special session on “Hot Topics in Multimedia Delivery (HotMD)” introduced elsewhere and Claude Perron (Vice President of Thomson Video Networks) provides a keynote in the area of multimedia-aware networking.

As workshop chairs, we would like to thank all people who have contributed to the success of this workshop: the authors, the invited speaker, the program committee members and all reviewers, and the members of the organizing committee of ICME 2011. The support of the workshop sponsors is also greatly acknowledged, in particular DOLBY (http://www.dolby.com/) and RADVISION (http://www.radvision.com/) for sponsoring the best paper award.

We sincerely hope that the carefully crafted technical program we have arranged for, the scientific discussions that the workshop will hopefully stimulate, and your additional activities in Barcelona, will make your participation worthwhile and a memorable experience.

Organizers:

Christian Timmerer, Alpen-Adria-Universitt Klagenfurt, Austria

Daniel Negru, LaBRI, France

Eugen Borcoci, UPB, Romania

George Xilouris, Demokritos, Greece

Hot Topics in Multimedia Delivery

Room: JH1.05 Date: 7/11/2011 Time: 13:30-15:30

Multimedia delivery platforms are evolving in several axes. From the transmission point of view, moving from purely broadcast based to hybrid broadcast-broadband and broadband networks, being of special interest the converged traditional use of media with mobile internet devices. Also, from point of view of content, moving from SD and HD images to 3D and multiview immersive experiences. From the user perspective where, user personalization and context are becoming more and more important as well as new enhanced ways of user interaction. And, finally, the convergence of media delivery and consumption with other technologies, as the ones of videogames, where real and virtual media are combined to provide a unique immersive user experience.

Multimedia content distribution has always been a fascinating and motivating topic to the multimedia research community. After years of active research and industrial efforts, it has reached a stage that “all of us can get our 15 minutes on YouTube”. However, there is still a long way towards the ultimate goal of anyone being able to consume multimedia content anytime, anywhere. As more right holders of professional multimedia content are ready to test water of new distribution methods, such as Internet video and IPTV; as the ever increasing capabilities of emerging devices, such as smartphones and tablets, enable new multimedia experiences on-the-go; as rapidly expanding cloud services start to offer greater assistance to multimedia distribution, we are now at a time when these are ample opportunities for the research of multimedia content distribution. Solving the real challenges towards the ultimate goal of multimedia content distribution is not only inspiring and exciting, but also bound to have significant and long lasting impact.

Organizers:

Cheng Huang, Microsoft Research, USA

Yong Liu, Polytechnic Institute of NYU, USA

Francesc Pinyol Margalef, La Salle - Universitat Ramon Llull, Spain

Gabriel Fernàndez Ubiergo, La Salle - Universitat Ramon Llull, Spain

Alejandro López González, La Salle - Universitat Ramon Llull, Spain

Interactive Ambient Intelligent Multimedia Environments

Room: JH1.07 Date: 7/11/2011 Time: 9:00-12:30

Interactive Ambient Intelligence Multimedia Environments (AIME) has the vision of enhancing our everyday environment and our interaction with its objects by sensing, computing, and communication capabilities. Major characteristics of such environments are the increasing number of intelligent devices (ubiquity), their complexity, and their integration into the background (transparency). As pervasive devices grow in complexity and sophistication, they become harder and harder to use, particularly because of their tiny display screens and limited interfaces. At the same time, devices will disappear or blend into the background and will be invisible to the user. However, because of this transparency, users fail to develop an adequate mental concept for AIME and its interaction concept. The reasons for this are the integration of the infrastructure into the background and the missing or invisible user interfaces.

To overcome these challenges, new interaction models are required. How can one interact with tiny devices that do not provide their own user interfaces? Or how to find and access devices that are invisible to the user? How to access physical devices in an unfamiliar environment without having knowledge about the technical infrastructure such as device’s physical address or IP address? Identifying and activating the right device or service from a huge amount of existing devices to perform a specific task is a challenge for users of these environments.

Some researchers have suggested fully automated and intelligent interaction to overcome the above-mentioned challenges. However, when analyzing implicit interaction approaches, some other challenges come up. Major challenges are lack of control and over-automation. Several works have reported already that people do not accept a full-adaptive and over-automated environment. Instead, users prefer to always be in control. Therefore, concepts for natural interaction are needed that allow implicit interaction while avoiding loss of control and over-automation. In such environments, multimedia play two key roles: they support new ways of interaction that apply to multiple human senses, and they diffuse the presentation of content in the environment of the user.

Facing these challenges is a community-spanning effort, necessitating the pooling of resources and experiences of different research groups. The aim of this workshop thus is to provide a link (1) between different AIME research groups and (2) between the academic communities and industry groups that work in the AIME area. These different groups will come together to foster the developments of highly intuitive, multimedia supported interaction solutions for AIME. To reflect this, we will invite a keynote speaker from the industry, promote the workshop among industry participants, and help to set up cooperation between the industry and academic groups.

Organizers:

Ali A. Nazari Shirehjini

Xenophon Zabulis

Sahin Albayrak

Content Protection & Forensics

Room: JH1.02 Date: 7/15/2011 Time: 9:00-18:00

Advances in Automated Multimedia Surveillance for Public Safety

Room: JH1.03 Date: 7/15/2011 Time: 9:00-18:00

It is our great pleasure to welcome you to the 1st IEEE International Workshop on Advances in Automated Multimedia Surveillance for Public Safety (AAMS-PS 2011) in conjunction with IEEE International Conference on Multimedia and Expo (ICME 2011). Unlike other workshops on surveillance, this special workshop aims to report on the recent developments in various aspects of automated multimedia surveillance, including the state-of-the-art techniques, methodologies and systems for protecting people and ensuring their safety through effective surveillance.

Automated multimedia surveillance systems utilize different tools and techniques in capturing, processing and analyzing multimedia data coming from heterogeneous sensors. These systems are often designed to support (semi-) automatic decision making, such as generating an alarm in response to a surveillance event, as well as to provide useful information to human decision makers for ensuring public safety. Many researchers in industry and academia are working on various aspects of automated surveillance - automatic analysis of media streams, real-time processing, event detection, system architecture, quality evaluation and so on, while some argue on the level of automation to be exercised in such systems. Therefore, AAMS-PS 2011 aims to cover a broad spectrum of research aspects in automated multimedia surveillance that is often multidisciplinary in nature.

Despite the fact that it was the first edition, the AAMS-PS 2011 workshop attracted a good number of submissions, a total of 25 submissions (none as invited) from Spain, Italy, Belgium, Saudi Arabia, China, Korea, Singapore, Canada, UAE, Bosnia and Herzegovina, and USA. The program committee consisting of experienced researchers has accepted 10 papers for oral and 5 papers for poster presentation. The selected papers cover different aspects of automated multimedia surveillance including fast video search and indexing, multi-object tracking, queuing models, QoS, decision support system, anonymity, middleware, and social networking based surveillance.

We would like to thank all the organizing committee and TPC members for their hard work in advertising the workshop, reviewing the papers and providing valuable suggestions. We hope that the outcome of this workshop proceeding will serve as a valuable reference for researchers and developers in the area of multimedia surveillance. Finally, we would like to thank the authors and the keynote speaker for providing the content of the program, and to Abdulmotaleb El Saddik and Xian-Sheng Hua for helping us in realizing this event.

Organizers:

Mohan S. Kankanhalli, National University of Singapore, Singapore

Pradeep K. Atrey, University of Winnipeg, Canada

M. Anwar Hossain, King Saud University, Riyadh, KSA

Advances in Music Information Research

Room: JH1.04 Date: 7/15/2011 Time: 9:00-18:00

Music information research has been a fast growing scientific field during the past decade. In traditional content-based MIR, music-related information is extracted from the audio signal using signal processing techniques. These methods, however, cannot capture semantic information that is not encoded in the audio signal, but nonetheless essential to many consumers, e.g., the meaning of the lyrics of a song or the political motivation or background of a singer.

In recent years, the emergence of various Web 2.0 platforms and services dedicated to the music and audio domain, like last.fm, MusicBrainz, or echonest, has provided novel and powerful, albeit noisy, sources for high level, semantic information on music artists, albums, songs, and others. The abundance of such information provided by the power of the crowd can therefore contribute to music information research and development considerably. On the other hand, the wealth of newly available, semantically meaningful information offered on Web 2.0 platforms also poses new challenges, e.g., dealing with the huge amount and the noisiness of this kind of data, various user biases, hacking, or the cold start problem.

Another recent trend, not at last addressable to platforms like Apple's iPhone or Google's Android, are intelligent user interfaces to access the large amounts of music available on today's mobile music players. Mobile devices that offer high speed Web access allow for even more music to be consumed via Web services. Dealing with these vast amounts of music requires intelligent services on mobile devices that provide, for example, personalized and context-aware music recommendations. The current emergence and confluence of these challenges make this an interesting field for researchers and industry practitioners alike.

Addressing these challenges, the 2011 edition of the AdMIRe workshop series served as a forum for presenting cutting edge research and discussing emerging trends in the fields covered. The workshop brought together researchers and developers from music and audio, multimedia, Web mining, and recommender systems communities.

In its third successful year, the workshop has established itself as a truly international venue with 18 high-quality submissions by authors from 12 countries.

Keeping an acceptance rate similar to previous years' editions, finally 10 papers have been selected as the result of a rigorous reviewing process.

The included topics span a wide field, such as mobile music computing and browsing, similarity measurement, tag and text analysis, music ontology design, and social studies. Several papers further present improvements in content-based music information research, more precisely, in chord estimation, signal-based genre classification, and content-based music retrieval.

We would like to thank all authors, participants, and presenters for their high-quality submissions and presentations as well as for their interesting discussions that made AdMIRe an outstanding event. Special thanks go to all members of the program committee and all reviewers for ensuring the high scientific quality of the workshop program.

The AdMIRe 2011 workshop was supported by the Austrian National Science Fund (FWF) under project numbers L511-N15 and P22856-N23, by the Department of Computational Perception at the Johannes Kepler University Linz, by the Linzer Hochschulfonds, by Barcelona Music & Audio Technology (BMAT), and by the organizers of the IEEE International Conference on Multimedia and Expo 2011.

Organizers:

Markus Schedl, Johannes Kepler University, Linz, Austria

Peter Knees, Johannes Kepler University, Linz, Austria

Oscar Celma, Barcelona Music and Audio Technologies, Barcelona,

Spain

Hot Topics in Multimedia

Room: JH1.05 Date: 7/15/2011 Time: 9:00-18:00

Special Session: Edutaiment

Room: JH1.05 Date: 7/15/2011 Time: 13:30-15:30

The appropriateness of the workshop in the program is to bring the best researchers in multimedia closer to one of the most important applications of their expertise: learning. At the same time, we expect that learning professionals come to see how multimedia can improve their learning methodologies.

Multimedia Productions in general and Games in particular, can be considered as interactive experiences that feature structured and complex activities. These can be used for solving problems and therefore for helping within the learning process. “Edutainment” is a transversal and strategic field that can be applied to different sectors and disciplines, providing with novel and innovative solutions.

The main aim of this workshop is to collect and disseminate the latest innovations in the field of applying multimedia technologies for learning and to create the synergies between the specialist in Multimedia and the specialist in Education to work together in this challenging field. To mention some, interesting ares of study include practical cases regarding the application of Multimedia in Education, Edutainment and Serious Games, Affective computing, Augmented, Virtual and Mixed Realities in Education, Interactive Arts in Education and Collaboration, competition and community Collaborative Environments and Learning, among many others.

As technology continues to permeate all areas of education the significance of multimedia is growing. Nowadays, the use of a Learning Management System is widespread in schools and universities. Also the use of simulations, videos, etc is becoming more and more important, and of course, distance programs are profiting from this technology and the number of students of open universities has increased steadily in the last 10 years. Education can be for multimedia what Medicine has been for Image Processing, a capital applications perfectly defined.

Entertainment implies a part of amusement plus some pleasure in the execution. A game provides with an interaction scheme and some sort of manipulative user interface for the generation of sensory feedback. It seems that educating through a medium that both serves for the purpose of learning and entertaining can be a pleasant, motivational and satisfying experience. And there are several real experiences that demonstrate that with clear facts and conclusions.

Organizers:

Dr. Maiga Chang,

Dr. Oscar Garcia-Panella,

Dr. Lluis Vicent-Safont

Dr. Olenka Bilash

Special Session: Human Factors in Multimedia

Room: JH1.05 Date: 7/15/2011 Time: 10:30-12:30

Chairman: David Fonseca

Organizers:

David Fonseca, La Salle

William A. Gruver, IEEE SMC Society

Anup Basu, Alberta

Chunrong Yuan, Tuebingen University

Marc Pifarre, La Salle

Eva Villegas, La Salle

Special Session: Multimodal Audio-based Multimedia Content Analysis

Room: JH1.05 Date: 7/15/2011 Time: 9:00-10:10

By definition, multimedia content is composed of multiple forms, including audio, video, text/ subtitles, and others. Traditionally, applications and algorithms that work with such content have considered only a single modality, allowing for example searching of textual tags, thereby ignoring any information available from others modalities. The limitations of this approach are obvious, and there is a recent trend towards multimodal processing, in which different content modalities complement each other, or are used for bootstrapping analysis of new modalities.

Audio is a prominent part of multimedia content, which is backed up by extensive research by the speech and music communities, although usually performed on audio-only systems. Utility of audio-only systems is often limited by the quality of the acoustic environment or the information contained therein, so they can benefit from a multimodal analysis of multimedia data, to enhance the resulting performance, robustness, and efficiency.

The main goal of the special session is to explore ways in which audio processing can be enhanced, bootstrapped, or facilitated by other available information modalities. We are interested not only in applications that show successful combinations of audio and other sources of information, but also on algorithms that effectively integrate them and leverage complementary information from each modality to obtain an enhanced result, in terms of degree of detail, coverage of the corpus, or other enabling factors.

The special session wants to provide a forum for publication of high-quality, novel research on multimedia applications and multimodal processing, with a special focus on the audio modality.

Organizers:

Xavier Anguera, Telefonica Research

Florian Metze, Carnegie Mellon University

Gerald Friedland, International Computer Science Institute

Special Session: Vision and Graphics Computing for Multimedia Communications

Room: JH1.05 Date: 7/15/2011 Time: 16:00-18:00

The explosion and far-reaching of internet multimedia, especially those with new and emerging new media types, such as various 3D visual entities including 3DTV, stereoscopic movies and sports, and PhotoSynth (i.e., 3D photo collections), calls for advanced multimedia communication systems to deliver the most compelling experiences to the end user. While signal processing based multimedia communication systems have been very successful in dealing with traditional multimedia, they are not sufficient in dealing with emerging new types of multimedia. Presumably, due to the rich and structured visual information, smart content analysis techniques from computer vision and visual synthesis techniques from computer graphics shall provide effective solutions for efficient visual communications of these new media. Furthermore an interactive 3D experience requires all the four steps of 3D acquisition, compression, transmission and visualization at the client side and these tasks must be considered together in order to fully exploit the potentiality of this new media.

This special session will explore how vision and graphics computing can be leveraged for advanced multimedia communications systems, both for traditional and emerging new media types. It will bring researchers from 3 different fields, i.e., computer vision, computer graphics, and multimedia communications together, and provide a forum to researchers to identify critical problems and proposed effective solutions in this emerging interdisciplinary area.

The special session will cover many different interesting topics in this rapidly growing field. These include visual and 3D data processing, management, summarization and analysis for various communication applications. All the steps required for a 3D interactive experience will also be covered: firstly the 3D reconstruction and acquisition of static and dynamic scenes; then compression algorithms for 3D and multi-view data; after that the transmission of this information, including error resilience and concealment techniques; and finally 3D data visualization and interaction, including augmented and virtual reality applications.

Concluding the aim of the special session is to show how vision and graphics computing provides key enabling technologies to effectively utilize the rich structured visual information behind new 3D entities in order to facilitate multimedia communications.

General Chairs

Gang Hua, IBM T. J. Watson Research Center

Pietro Zanuttigh, Department of Information Engineering, University of Padova,

Program Chair:

Philippos Mordohai, Stevens Institute of Technology

Hot Topics in 3D Multimedia

Room: JH1.08 Date: 7/15/2011 Time: 9:00-18:00

The second international workshop on Hot Topics in 3D Multimedia continues the mission of the first Hot3D workshop which was held in conjunction with ICME 2010 in Singapore during July 2010. The first Hot3D workshop was organized as a full‐day workshop aligned with other ICME workshops and activities. It has been a great success with outstanding contributions and very good attendance. The steering committee, consisting of Dinei Florencio, Murat Tekalp, Anthony Vetro, and Cha Zhang, at that time stated the Hot3D mission as follows:

“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 is now often tightly integrated with 3D environments, including 5.1 (and higher) and even 3D soundfield reproduction. Haptic systems 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 are 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.”

In 2011, Touradj Ebrahimi, Aljoscha Smolic, and Eckehard Steinbach took over the organization from the 2010 organizers. The technical program committee grew to 36 experts working in the area of 3D multimedia and the call for papers attracted a total of 27 submissions. Each paper received at least three reviews and finally, 12 high quality contributions were selected for inclusion in the workshop program, which corresponds to an acceptance rate of 44%.

The workshop will take place on Friday, July 15, 2011 in Barcelona in conjunction with ICME 2011. We are very happy that Tibor Balogh from Holografika has accepted our invitation to deliver the keynote talk at the workshop.

We would like to thank the Hot3D Steering Committee to entrust us with the organization of the second workshop and we hope that Hot3D will grow into a permanent venue for 3D multimedia researchers to meet and exchange ideas. We are excited to see that the workshop has attracted an excellent number of submissions and we are looking forward to an exciting and lively workshop.

Organizers:

Touradj Ebrahimi

Aljoscha Smolic

Eckehard Steinbach