Category Archives: Conferences

Special session accepted for MMM conference 2017

The MPG group and some of our collaborators proposed a special session for the Multimedia Modeling Conference 2017 in Iceland. We can announce now, that our proposal got accepted. The special session will be an evolved version of CrowdMM — Crowdsourcing for Multimedia.


The session will focus on advancing the state of the art of best practices for the use of crowdsourcing in multimedia research. A wealth of topics will be addressed within the field of multimedia, cross-cutting all of the main conference areas. Contributions dealing with e.g. crowdsourcing-based identification and evaluation of multimedia QoE (Area: Multimedia HCI and QoE), visual and audio indexing via human computation or hybrid techniques (Area:  Multimedia Search and Recommendation) or also the use of crowdsourcing for analysing affect portrayed in or elicited by multimedia content. Specific the emerging areas Emotional and Social Signals in Multimedia such as User Intent and Affection will be welcomed, as long as they present a strong methodological focus on crowdsourcing. We will put emphasis on tackling the methodological challenges listed in the “topics” section below. Crowdsourcing cannot be considered as a mature technology for multimedia research if the results it produces are not repeatable. To take crowdsourcing to the next level, it is necessary to determine best practices for test and incentive schemes design, as well as robust data analysis and quality control techniques. On the longer term (beyond 2017), our goal is to generate guidelines and recommendations for the use of crowdsourcing in multimedia, possibly also involving standardization bodies. To do so, it is necessary to focus on crowdsourcing not only as a means for multimedia research, but also as an end.

The main proposers are:

Guillaume Gravier, IRISA, France,

Guillaume Gravier is a senior research scientist at Centre National pour la Recherche Scientifique (CNRS). Since 2002, he has been working at the IRISA lab, where he currently leads the multimedia group. With a background on statistical speech modeling, his research activities focus on multimedia analytics: multimodal content modeling, multimedia pattern mining, natural language processing and video hyperlinking, etc. Guillaume Gravier is president of the French-speaking Speech Communication Association and co-founded the ISCA SIG on Speech and Language in Multimedia (SLIM), which he has been chairing since 2013. He is a member of the board of the national ICT cluster Images et Réseaux and the technical representative of Inria in the PPP BDVA. Guillaume Gravier has also been involved in the organization of major conferences and of national and international evaluation benchmarks.

Mathias Lux, Klagenfurt University, Austria,

Mathias Lux is Associate Professor at the Institute for Information Technology (ITEC) at Klagenfurt University. He is working on user intentions in multimedia retrieval and production and emergent semantics in social multimedia computing. In his scientific career he has (co-) authored more than 80 scientific publications, has served in multiple program committees and as reviewer of international conferences, journals and magazines, and has organized multiple scientific events. Mathias Lux is also well known for the development of the award winning and popular open source tools Caliph & Emir and LIRE for multimedia information retrieval.

Michael Riegler, Simula, Norway,

Michael Riegler is a PhD student at Simula Research Laboratory. He received his master degree from the Klagenfurt University with distinction. His master thesis was about large scale content based image retrieval. He wrote it at the Technical University of Delft under the supervision of Martha Larson. He is a part of the EONS project at the Media Performance Group. His research interests are endoscopic video analysis and understanding, image processing, image retrieval, parallel processing, gamification and serious games, crowdsourcing, social computing and user intentions. Furthermore, he is involved in several initiatives like the MediaEval Benchmarking initiative for Multimedia Evaluation and he has (co-) authored more than 30 scientific publications.

Steering Committee:

Martha Larson, Delft University of Technology, Netherlands, and Radboud University Nijmegen, Netherlands

Judith Redi, Delft University of Technology, Netherlands

LCN 2015

Leaving the cold, dark Norwegian autumn behind, Bendik and me went to Clearwater Beach in Florida for a week in October (26th to 30th) to attend the 40th Annual IEEE Conference on Local Computer Networks (LCN2015) and present our paper, Latency and fairness trade-off for thin streams using redundant data bundling in TCP. From below 10 degrees centigrade and low air humidity to temperatures above 25 degrees centigrade and very high air humidity, the difference was quite noticeable.

There were a lot of interesting paper presentations, especially in the field of wireless sensor networks (WSNs). Being the 40th anniversary of the conference, however, the main keynote speaker was inventor of Ethernet and Internet pioneer Bob Metcalfe.

More about Bendik’s master thesis in this blog post: “Taming Redundant Data Bundling”. Bendik has also made a Linux implementation.

iAd’s workshop at Ullevaal: fra eliteidrett til folkehelse

MPG has been an integral part of the SFI iAd (center for research-based innovation “information access disruption”) for nearly 8 years now, and the iAd has provided a wealth of ideas, opportunities, and not the least, funding in this period. In the last NFR-sponsored year of iAd, we organized a workshop with participation of iAd participants, politicians, representatives of the research council, industry, sports and medicine on October 31 in Ullevaal stadium, home of the Norwegian national soccer team.

With some looks back onto the successes of the project, and demos of recent achievements, the workshop drew some attention, but at the core of the workshop topics was not the past but the future.

The iAd partners have established a cooperation that will continue beyond the end of NFR sponsoring for the iAd center, and aim at the use of Big Data to increase our understanding of illnesses and gain the ability to predict their development.

The event, and discussions of how the iAD technology is going to be used by the national soccer team, were covered by various media, some examples are shown here:

Note also that NFR has earlier published an article about the future vision of iAd participants on its pages.

Best Presentation Award @ NOSSDAV 2014

OLYMPUS DIGITAL CAMERAIn an earlier blogpost, we informed that the paper “Interactive Zoom and Panning from Live Panoramic Video” by Vamsidhar Reddy Gaddam, Ragnar Langseth, Sigurd Ljødal, Pierre Gurdjos, Vincent Charvillat, Carsten Griwodz and Pål Halvorsen was accepted at NOSSDAV 2013.

Even though his PC broke an hour before the session and the powerpoint slides had to be re-made, Vamsi gave a perfect presentation, and at the conference banquet, he received the BEST PRESENTATION AWARD.

Visit to Globecom

Globecom 2013 was arranged in Atlanta in December 2013, and I was invited by the Nesrine Changuel (Alcatel-Lucent Bell Labs) to give a keynote talk at the workshop that she co-organized. The workshops name was Control Techniques for Efficient Multimedia Delivery, and the organizers were Nesrine Changuel, Moncef Gabbouj (Tampere Univ. of Tech.), Michel Kieffer (CNRS-Supelec) and Bessem Sayadi (ALu Bell). I felt that the workshop was somewhat outside the scope of the main Globecom conference. Globecom appears like a good place to be for researchers who investigate the lower layers of wireless technology as well as industry who develops those networking technologies: a good place to meet and discuss, and for listening to good and relevant keynotes, especially also on the political aspects of future wireless developments. For people who are concerned with end-to-end transport, application questions or even complete systems, I found hardly any attractions.

Globecom is, however, the place where ComSoc official meetings are held. The meeting that I attended was the MMTC’s (multimedia technical committee), which provided the MMTC members with news from the main conferences and other services that MMTC members provide. Obviously, the development of MMTC’s conference involvement was discussed, but another point was the status and development of the MMTC E-letter and R-letter. The E-letter contains invited 2-4 page letters on a topic of particular interest that is published 6 times a year. You find more about it here. The R-letter is meant to point us to high-quality papers within the flood of papers that appear today. Being reviewed in the R-letter is a precondition for nomination to the best paper of the year in MMTC, and self-nomination is a possibility. So, this is a really important letter to pay attention to, and more information can be found here.

Of course, I discussed these letters in comparison to the SIGMM Records, which are meant to publish the announcements from the SIGMM chairs, summaries of PhD theses to put the spotlight on the most concise pieces of research that we have, and the stories behind the research through interviews. You can find the Records here. We agreed that there is no overlap between the agendas of these letters, and that we should cooperate more, by cross-announcing and cross-referencing.

Finally, on Friday, I got around to the workshop. A half-day workshop, it was meant to let us share research about efficient multimedia delivery, and “MPEG DASH” was clearly a big interest of the organisers. As mentioned, I was invited to give a keynote. I you want to take a look at my slides, you can find them here. It’s a bit of a pity that the workshop collides with Packet Video on the other side of the conference, but we still had quite a few interesting papers in Atlanta. You can see the program here.

Speaking about: Interspeech and AVSP

Religieuse Researchers get hungry, even the ones that occupy themselves with speaking about speech. What better place to lure these hungry speech scientists than to Lyon? The self-proclaimed gastronomical capital of France, the country which even bolder labels itself with the finest cuisine in the world, seems to offer a new culinary delicacy on every corner. From foie gras to moules frites, from canard à l’orange to coq au vin, and from crème brûlée to mille-feuille, the French know how to fill a belly in style. Oh, they also do science. In 2013, Lyon hosted the 14th Annual Conference of the International Speech Communication Association, or Interspeech, for simplicity’s sake. Hundreds of keen minds centered on anything and everything speech-related descended upon the unsuspecting, reluctant speakers of English. With topics covering diverse areas such as automatic speech recognition, room acoustics, paralinguistics, and speech production and perception, the researchers soon became hungry for more than food. After five days packed with speech technology and speech processes, as well as scrumptious lunches and lavish dinners, many of the researchers found their appetites sated. Many, but not all.

AnnecyWith a dozen or so satellite workshops and conferences, the hungriest scientists set out to explore the culinary arts of nearby regions. In Annecy, the audio-visual enthusiasts congregated in a circle of tents and shacks to exchange ideas and findings on how sound and vision are combined in speech. It quickly became apparent that the self-proclaiming Lyonnaise might have more than mere words to add to a dish. Fortunately, with the nightly boules to waken spirits, the hollow feeling left by the sloppy spaghetti bolognese was nearly forgotten. The workshop was set nearby the blue waters of Lac D’Annecy, surrounded by spectacular mountains. Despite the recent fire, which was to blame for the missing conference rooms and the erected pavilions, the devoted bimodal speech researchers found the country-side atmosphere an excellent inspiration for their discourse. Among the topics on the agenda was a study on the perception of synchrony in conversational speech. The presenting researcher, whom hailed from Simula, was happy to inform the audience about the temporal integration of audio and video in a live teleconference. She was certainly not alone, the days were filled with new insights on these perceptual processes that most humans tend to take for granted. Indeed, the hungry researchers returned many spoken, and seen, words wiser.

Full paper on temporal integration in live speech.

ISM and PV 2013

Some of us, Håkon and Pål, went on a more or less voluntarily trip to the US west coast for a couple of conferences. IMG_3774The first stop was Anahaim (LA, CA) to attend the International Symposium on Multimeida. After far to many hours on a plane in Pål’s opinion (too few according to Haakon), we had three days to listen to talks. However, we did not only attend the conference to listen, we also had a paper entitled “Efficient Implementation and Processing of a Real-time Panorama Video Pipeline“. Håkon had a really good presentation and actually got a few questions. In general, there were some interesting talks, but the event failed to impress us this year.

Next, the trip went north. We drove from LA to San Jose with an aim to go to the Packet Video workshop organised at Cisco. This year, we were involved with the organisation of the technical program. The workshop venue was good, there were a lot of talks relevant to our own research in MPG and the keynotes were inspiring. Definitely a place to go back to.

ACM Multimedia Systems Conference 2013

At the end of Febrary 2013, more exactly from February 27 to March 2, we organized the ACM Multimedia Systems Conference (MMSys) in Oslo. This was the fourth conference of the MMSys series, and we had been hard at convincing the initiators of the conferences from the very first time MMSys was held in 2010. Oslo in winter seemed a bit hard to swallow for many people, given that it tends to be a bit snippy outside.

Alas, the weather in Scottsdale misbehaved in 2010, so Oslo looked less frightening, and our wish to host it in Oslo was heard. We set out to host another event where multimedia systems researchers could meet systems researchers from other specialties, and welcome them into the community.

Hosting MMSys was not the only thing that was to happen. MMSys has made its name as a place where multimedia systems researchers meet in a friendly atmosphere after hard competition for getting papers accepted. But there are also other events with a similar reputation, and the oldest one of them is NOSSDAV, the ACM workshop on networks and operating system support for digital audio and video. Having two such similar events, while travel funds are getting smaller and the community more international, has forced multimedia systems researchers to choose. At the end of MMSys 2012, the NOSSDAV and MMSys steering committees had agreed to arrange NOSSDAV at MMSys: to keep submission deadlines apart but combine the travels. And another workshop joined, the Mobile Video Workshop (MoVid), that had been connected to several larger conferences in the past.

So we had three different teams that worked on the scientific quality of these three events, under the premise that deadlines should be kept as far apart as possible; to really merge MMSys and NOSSDAV, and not cannibalize the one for the other. Finally, the paper deadline for MMSys was September 28, for MoVid, November 12 and for NOSSDAV, November 26. In addition to that, we organized also a special MMSys Session on 3D multimedia technologies, the Dataset Track was held once more, and also a call for demos was issued.

MMSys received 63 full paper submissions and accepted 15 out of this (that is the conference’s most competitive acceptance rate so far). Further 82 submissions were received for the various associated opportunities (NOSSDAV workshop, MoViD workshop, 3D technology and multimedia special session, dataset session, demo session). The proceedings are available from the ACM Digital Library, and the datasets can be accessed through They are hosted by an NSF hosting activity an the University of Massachusetts, Amherst, as well as the EU COST action Qualinet and will be available for at least 5 years. You can also listen to the speakers: videos are publicly available on YouTube.

The panel on WebRTC

The audience could enjoy one keynote speaker on each day of the conference: Aljosa Smolic from Disney Research Zurich, who attracted the largest crowd in the university’s largest auditorial, Rui Casais from Funcom, maker of massive multiplayer games Anarchy Online and Secret World, and Torgeir Hovden from ComoYo, who continued the MMSys “tradition” of keynotes on the hottest commercial topics in video-on-demand. The streaming community among the multimedia systems crowd was also served with the latest activities towards commercialized streaming by the panel on WebRTC/RTCWeb, where Michael Welzl hosted Harald Alvestrand (Google), Xavier Marjou (Orange), Christian Timmerer (University of Klagenfurt) and Max Mühlhäuser (TU Darmstadt).

In the breaks, we continued the successful tradition of an open poster session. Without any previous review, we invite every participant to put up a poster showing his or her own work. Although this remains uncatalogued on the MMSys web pages and in the ACM digital library, it provides people who attend to learn and network with an easier opportunity to discuss their own work with other attendees.

With three events happening in one place on three days, some preparations had to be made. Thanks to the University of Oslo, we could use nice rooms in the brand new computer science building for free, and arranged all talks, the reception, lunches, dinners, as well as demo and poster session there. Having all arrangements under a single roof was also welcome by visitors who are unused to the winterly conditions of Oslo.
We cooperated also with the local student organizations SIO and CYB and company Equippe AS, who provided catering and a variety of devices. Add to this the work that was done by the members of MPG and Simula sponsoring all remaining odd expenses, our only financial concern was to feed the participants well. Norway is not at all known for cheap eating, and participants would really have felt this if we hadn’t provided food for breaks, lunch and dinner. With the financial support of the Research Council of Norway, the Centre for Research-based Innovation iAd, FXPal, and of course all registration fees of the participants (from $200 to $450), we could do it.

ACM MMSys, NOSSDAV and MoVid in Oslo

The fourth ever ACM Multimedia Systems conference – or MMSys – was held in Oslo from February 27 to March 1, 2013. It was also the first time that MMSys hosted other events: an idea that had formed in the last years became reality, and NOSSDAV (the 23rd!) was arranged together with MMSys. Also the younger workshop, MoVid, joined the club.

We consider it a very successful event. More than 100 participants listened to the speakers of MMSys, NOSSDAV and MoVid and in particular the three keynotes by Aljosa Smolic (Disney Research), Rui Casais (Funcom) and Torgeir Hovden (ComoYo). If you are interested, you can also still watch most talks from MMSys and NOSSDAV. The are available from YouTube through the program pages here and here. The number of paying participants was increased by 10% from 2012.
Read more

« Older Entries