SemanticMetadata.net

Report from the Open Source Track @ ACM MM

Within the open source track of the ACM Multimedia conference the SIGMM  (Special Interest Group on Multimedia of the ACM) wants to provide a platform on discussing tools and code free to use in research as well as industry project. As I already blogged I had a presentation on Lire there. However all other contributors were nearly as interesting, if not even more

Marco Lohse presented a Network-Integrated Multimedia Middleware (NMM), which was developed at Saarland University and is now available with dual licensing. He is also CEO of the company selling the non GPL license. The software is impressive and his demo was great. No surprise he won the prize of 700 $. (http://www.motama.com/nmm.html)

Yannick Alluse presented GpuCV, an extension of OpenCV towards CUDA and shader based computing. Important thing is that the library decides whether CPU, Shader or the GPU will be used for processing. (https://picoforge.int-evry.fr/cgi-bin/twiki/view/Gpucv/Web/)

Andreas Berger showed a framework for DVB-* transmission. It allows for inexpensive setup of for instance a DVB-T or DVB-H broadcasting service in labs or research projects. As its very generic one can compose the DVB stream fully free, so MHP, IP Data, EPG and so on are possible. (http://sourceforge.net/projects/fatcaps/)

Jose San Pedro Wandelmer from the University of Sheffield presented his project FOBS, which is actually a wrapper for ffmpeg for C++ and JMF. I already knew FOBS as I have used it several times, but meeting Jose and talking to him was great. (http://fobs.sourceforge.net/)

ACM Multimedia 2010 in Florence, IT

Although my boss Laszlo Böszörmenyi did a great job on presenting our bid for hosting ACM Multimedia 2010, we didn’t stand a chance against Florenze. Alberto del Bimbo and his group will host the ACM Multimedia in 2010. Although we are slightly sad because we thought we will get it for sure (we didn’t know our competitors), we are now quite relieved that (i) another one is doing the organizational work and (ii) we had a good opportunity to present our department & research groups within the ACM MM community. We’ll definitely be there in Florence and help the group of Alberto del Bimbo as good as we can.

First impressions of the ACM Multimedia 2008

Yesterday the ACM Multimedia 2008 started here in Vancouver. In contrast to last years conference it takes place in a luxury hotel, whereas many researchers have booked one of the surrounding less expensive hotels The conference started with a rather disappointing keynote. It did not meet my expectations in novelty and importance of topic. The best paper session however was better, especially the 4th presentation on the Flickr distance by a Microsoft guy

The program of the first two days was somewhat crowded. Short papers, represented by posters, where presented in a small romm in parallell to 3 parallel main sessions. So one has a tight schedule around here.

At the ACM business meeting we (the ITEC @ Klagenfurt University) placed our bid for hosting the conference in 2010. Although our presentation was great we have strong competitors from Firenze. Decision is made in the next few days, perhaps even this evening.

This was the first of three things I’m here for in Vancouver. Tomorrow, on the last day of the main conference I’m going to present LIRe in the open source track and on Friday I’m going to present the joint research work of Oge Marques and me. Stay tuned I’ll post the slides

Report from Triple-I (part II)

The rest of the Triple-I was straight forward for me. I did a lot of talking with old colleages and industry people interested in multimedia asset management. Looks like everybody collected a huge amount of digital photos and is now searching for means to organize them

Next years Triple-I will be somewhat different. Having found a call for a next year’s I-Know I think the Triple-I will go back to the original I-Know as it seems that especially the concept of the I-semantics didn’t work out. The next event of the Multimedia Metadata Community will be our 9th workshop  in Toulouse.

Report from the Triple-I

The first day here at the Triple-I was very successful: The KASW ’08 workshop went great, presentations were insightful and discussions were lively. My presentation was also great although I could have talked longer (the talk scheduled after mine did not take place due to visa issues). Highlights were definitely the overview of research on folksonomies of Andreas Hotho, Ralf Klamma’s summary of the finding of his group regarding online communites (see Flickr for a quote) and the position of Andrew Gordon regarding the blogosphere and common sense knowledge.

Today I already chaired the special session of the multimedia metadata community at the I-Media with three interesting presentations. Besides all the scientific stuff I had a lot of chats about industry needs, computer games on an academic level, my eee pc and my trip to the GC

Packing my Bag for the Triple-I

Tomorrow morning I’m on the road to go to Graz, where the Triple-I (former I-Know) takes place Wednesday to Friday. I’ll be there to visit and present at the KASW workshop and to chair the session of the multimedia metadata community. I’m looking forward to meet my colleages there. I-Know is always productive and good fun.

Report from the Games Convention :: Day 1

Today in the morning I came back from Leipzig, where I visited the Games Convention (GC). I was there to find find potential industry partners and people interested in cooperation with the university. Unfortunately at the Games Convention (GC) you need to have an appointment to meet someone as most interesting people are fully booked. However at some places I was lucky. I talked to a very helpful product manager of RTL-Games, a very interested technical account manager of Emergent Game Technologies and a PR assistant of NCSOFT. Also the sales manager of Techland was open to a short talk. Most negative experience was Crytek, where on the one hand someone had time to talk to me, but on the other expressed that they were only interested if I either came from a really big college with a lot of students or I had a lot of money to give them. Perhaps I just spoke to the wrong person … or they need the money for their development gear as Cryengine is known to take a lot of resources. For many of the approached companies the right people had no time, but people at the reception gave me contact information or took my business card to think about my efforts. All in all I am pleased with the first day leaving aside Crytek and Koch Media.

And now for the fun part: I played S.T.A.L.K.E.R. Clear Sky in the pre-release version and let it crash several times. The game looks just like the old S.T.A.L.K.E.R. – just a little better. I’m looking forward to the release. I played Rayman Raving Rabbids TV Party (Ubisoft) with my butt on the Wii with the creative director of the game throwing snowballs at me. That was real fun I also watched some Spore (EA) and tested it myself for the DS. I played the new Street Fighter 4 game (Capcom) and lost 2:0 in button smashing to a stranger. I tried the new Need for Speed Undercover and I was impressed by the visual damage the car took in crashes. My Audi look kaputt after my 5 minutes test. However behavior of the car is not changed by crashes, just the look of it. Another new racing game is MotorStorm: Pacific Rift. It’s interesting how the developers combined monster trucks and motor bikes in the same game, racing at the same time. Obviously motor bikes are more fun than monster trucks.

A special experience was to play a preview of Sonic Unleashed (Sega) on a HDTV plasma screen. With such a resolution the speed of Sonic is actually fun. Age of Conan was also here with a kind of LARP battle camp with computers inside. Interesting part was the option to play Conan with three TFTs: I call this “3D cave for the poor”. It should transports the feeling of “being inside” better than with a single screen. The feeling is somewhat limited, but its actually there. At EA I tried the preview of the new Harry Potter for the Wii and battled one EA merchandising guy with my wand. It’s now in the same class of games everyone does for the Wii: Instead of button smashing its more like controller swinging. It’s interesting how fast a new input concept can look old.

The new Call of Duty game and Fallout 3 where completely overloaded although only trade visitors were allowed, so I didn’t get a glimpse of those. However those “most prominent” 3D ego shooters where not the critical mass of the GC. Most people played Guitar Hero World Tour (Activision) featuring a band of 4 people with singing, drums, bass and lead guitar. There was a huge lot of sets on at least 4 locations within the GC. Never seen so great many people fooling around with plastic instruments. All in all I was impressed by the big fuss everyone is making about their own games. Most publishers obviously have enough money for PR.

Lire accepted for the Open Source Contest @ ACM MM

Although its quite some time ago that I got the acceptance mail I forgot to blog the good news: Lire (Lucene Image Retrieval) has been acccepted to be presented at the ACM Multimedia within the Open Source Contest track. As it is a contest I assume we have chances to win something?

WIAMIS 2008 talk: Video summarization through acceleration

With the contribution “Redundancy Removing by Adaptive Acceleration and Event Clustering for Video Summarization” Bernard Mérialdo presented a very interesting approach to video summarization. Beside other methods the video is accelerated. Based on the overall motion the actual amount of acceleration is adapted. Furthermore they apply hierarchical clustering on fixed size segments to select most important parts. Therefore the video is faster when not very much motion is going on and slower if fast motion is characteristics for a video segment. Nice added value was hat he described the RUSHES track of TRECVID and the evaluation process. Experts evaluate the accuracy of the summaries and weight them with extraction time and size of the summary.

Some thoughts on the WIAMIS keynote of H. Bischof

In the morning I was listenting to the talk of Horst Bischof on robust people detection in surveillance scenarios. In my opinion he gave a great talk: He manages to show the nature and results of their research and motivate the usefulness and significance of results based on context and related work. He points out what the achievements are and what hasn’t been touched by his research group and why. He also visualized his results using videos which was appreciated by the audience. If I findout where the videos can be found I’ll blog the link.