The ACM Multimedia Grand Challenge 2011 in a Nutshell

The 2011 ACM Multimedia Grand Challenge proved to be the most competitive so far. This article provides a quick summary of the competition. More comprehensive coverage can be found in an IEEE Multimedia Magazine report.

When the ACM Multimedia Grand Challenge was started in 2009 it was a radical idea: instead of submitting conference papers on solutions to self-imposed problems, scientists from the multimedia community were encouraged to engage in problems formulated by industry sponsors, called the Grand Challenges. In continuation of what now has become a tradition, the 2011 Grand Challenge consisted of six challenges sponsored by five industry sponsors: HP, Yahoo, Technicolor, Nokia, and Huawei/3DLife. The 2011 challenges, of which some are likely to be continued in 2012 can be found at the original website. Read more

ACM Multimedia 2011

Introduction to ACM Multimedia 2011

We are delighted to report on behalf of the entire organizing committee that the 19th ACM International Conference on Multimedia ACM Multimedia 2011 (MM’11) was held between November 28th and December 1st, 2011, in Scottsdale, Arizona, USA, to great success.

ACM Multimedia (MM) is the flagship conference of the Special Interest Group on Multimedia (SIGMM), which profiles cutting-edge scientific developments and showcases innovative industrial multimedia technologies and applications. The conference aims to promote intellectual exchanges and interactions among scientists, engineers, students, multimedia users, and artists through various events, including keynote talks from leaders in the area, oral and poster sessions focused on research challenges and solutions, workshops in up-and-coming key areas of research, technical and industrial demonstrations of prototypes and commercial products, tutorials, research and industrial panels, doctoral symposium, mentoring events, scientific competitions (including an open source software and a multimedia grand challenge competition), and interactive art exhibits. Read more

Report from NOSSDAV 2012

Setting for NOSSDAV 2012

NOSSDAV 2012, the 22nd SIGMM Workshop on Network and Operating Systems Support for Digital Audio and Video, was be held in Toronto, Canada, on June 7-8 2012. As in previous years, the workshop will continue to focus on both established and emerging research topics, high-risk high-return ideas and proposals, and future research directions in multimedia networking and systems, in a single-track format that encourages active participation and discussions among academic and industry researchers and practitioners. Read more

Co-locating Multimedia System Events: MMSys and NOSSDAV

The 23rd International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV) will be co-located with the ACM Multimedia Systems (MMSys) Conference in Oslo, Norway at the end of February 2013. In a meeting of the organizers of both conferences in February, it was decided that co-locating the conferences would help focus the efforts of multimedia systems community into one week. Read more

SIGMM Education Column

Project work is an important component of any graduate-level Multimedia course. SIGMM Education Column of this issue highlights the types of projects that are offered by Prof. Tat-Seng Chua and Prof. Mohan Kankanhalli in their co-lectured course, CS5342 Multimedia Computing and Applications, at National University of Singapore.

In general, the project can of any one of these two types:

  1. Implementation Project:
    • In this type of project, students are required to search for recent multimedia related papers to pick one (or few) papers which need to be understood, analyzed, implemented (and hopefully improved).
    • To obtain the highest grade, students are expected to develop their own novel idea as an improvement/extension over the existing work.
    • The end result of this project is usually a proper, working prototype of the idea in the paper(s).
  2. Survey Paper Project:
    • Students choose a specific topic to do the survey in this kind of project.
    • The end result is generally a very technical survey paper like the ones appearing in ACM Computing Surveys journal.
    • For the highest grade, it is considered necessary to propose some novel algorithm/technique or do an implementation of several techniques for a proper comparison.

Other characteristics of the project work are:

  • Projects are usually flexible, carried through the term. But each project needs to have some theoretical/algorithmic component and an implementation part.
  • Typical projects attempt to improve some state-of-the-art technique or algorithm.
  • There are three stages of evaluation — initial proposal which is iteratively refined, interim report, final report + demo-with-presentation. The final presentation is open to all.
  • Many people use it to investigate some part of their thesis research work and others use it as an opportunity to investigate a totally new area.

TOMCCAP Special Issue on 20th Anniversary of ACM SIG Multimedia

Call for Papers

The premier ACM SIGMM International Conference on Multimedia (known as ACM Multimedia) is celebrating its 20th anniversary. It all started in Anaheim, California, August 1-6, 1993, when the general chair, J.J. Garcia-Luna-Aceves gathered multimedia-interested researchers together to discuss and present research on systems and networks that would process digital audio and digital video. From this moment, over the next 20 years, research in digital multimedia has gone viral and became an integral part of our IT life. At this point, it is hard to imagine not having Flickr, YouTube, Facebook, Skype, Sony Playstation, Microsoft Media Player, Netflix, InstaGram, Akamai Content Distribution Services, and other multimedia products as part of our lives. Read more

Open Source Column: Mozilla Popcorn

Mozilla Popcorn: Web Video Interaction Using Client-Side Javascript

Context and history

Popcorn is an HTML5 media project from Mozilla, the non-profit organization that makes the Firefox web browser. It makes media-oriented web development easy through shared development, open source libraries and tools.

Popcorn.js: a Javascript library for interactions between video and the web

Popcorn.js makes web media more connected by providing an event-driven API to hook <video> and <audio> content into the of the capibilities of the web platform (developer.mozilla.org). Prior to HTML5, web video lived exclusively inside browser plug-ins like Flash and VLC, which put it outside the reach of JavaScript, CSS, and other techniques for interacting with the rest of the surrounding HTML document. Popcorn.js turns media into fully-interactive JavaScript objects, so that media objects can both trigger and listen for events. It enables developers to cue events along a media timeline using a simple Javascript syntax:

var pop = Popcorn("#my-video");
pop.text({
start: 1.38,
end: 5.12,
text: "Hello World",
target: "my-div"
});
pop.play();

Live source available at http://jsfiddle.net/p8Kbs/80/. Additionally, media playback is accessible via popcorn.play(), popcorn.pause(), and popcorn.currentTime(seconds), which allows you to jump to any point in the timeline of the referenced media. As a nod toward the expectations of media producers and videographers, Popcorn.js also provides methods like popcorn.cue(), which simply ties actions to specific times. Aside from simple time-based triggers, you can use popcorn.listen(event,callback_function) to bind the callback function to a specified event. Built-in events are provided to handle typical HTML5 web video playback scenarios, such as “play,” “pause,” “loadstart,” “seeked,” “volumechange,” and so on. However, you can define custom events and trigger them directly by using popcorn.trigger(event[,data]), where the data parameter is an optional data object to send to listeners.

Extensibility

By design, Popcorn is extensible. Mozilla supports about 20 plugins that come packaged with the library, ranging from simple HTML element insertion, to complex data retrieval and aggregation. Examples include a subtitle plugin, a GoogleMaps plugin, a Twitter plugin, a Facebook plugin, and a JavaScript code plugin. If some desired functionality doesn’t yet exist in the library, Popcorn.js has a well-documented plugin architecture: http://popcornjs.org/popcorn-docs/addon-development/. Popcorn works best with HTML5 media, but also has wrappers for arbitary objects (through the “baseplayer”) and Flash players, like YouTube, Vimeo, Flowplayer, and Soundcloud. It’s easy to write a wrapper for any web-oriented video player. Popcorn also includes a set of parsers for reading common data files (SRT, TTML, XML, etc). Of course, as with other parts of Popcorn, it is easy to create a custom data parser. Tested thoroughly, Popcorn.js supports all modern browsers and IE8. Currently, it’s stable at version 1.2. You can download the Popcorn source or use a web-based build tool to wrap a custom, compressed version.

Potential Applications

Popcorn is in use by a range of publishers, service providers, creative coders and individuals to mash video with the rest of the web. RAMP, a content optimization company, uses an automated process to display time-coded metadata about significant people, places and things whenever they are mentioned in a video. Using Popcorn, RAMP can support a range of player types and contexts (web, mobile, headless) by developing against the common Popcorn API (http://www.ramp.com/solutions/optimized-video/metaplayer/popcorn/). The Dutch multimedia archive Beeld en Geluid has used Popcorn to create a “living archive,” connecting cultural archival material with a range of semantic metadata (http://www.openimages.eu/blog/2012/01/13/open-images-videos-enriched-with-open-data/). Popcorn has also been used to create hyperlinked transcripts that use text as an interface for traversing and editing long media assets (http://yoyodyne.cc/h/) Aside from scale applications, Popcorn is also supported by a burgeoning creative community (In fact, the project was started and is run by Brett Gaylor–a filmmaker!). For instance, documentary producer Kat Cizek uses Popcorn to create web based interactive films. In “1 Millionth Tower,” the web browser creates a navigable 3D space that simulates high rises in major cities around the world. Popcorn is used to turn the camera at key moments, spawn visual effects, and to download live weather data from web APIs. If it’s raining in Toronto, it’s also raining in virtual Toronto (http://highrise.nfb.ca/onemillionthtower/1mt_webgl.php).

Popcorn Maker

A key goal of the Popcorn project is to enable more connected web video on a mass scale, and to open creative possibilities to individual media-makers. Popcorn Maker is a user-facing web application used to create interactive media. It requires no code knowledge. Users pick a video from YouTube or the wider web, open the media object in a prepared HTML template, customize the project, and publish. Popcorn Maker can be used to create pop-up videos, multimedia reports, guided web tours and more. Project composition happens live in the browser. Users can drag and drop events onto a timeline interface, position objects on the page, and watch a live preview of the project be constructed. Popcorn Maker projects are entirely human-readable HTML, CSS and Javascript. For the time being, Popcorn Maker does not support media editing and sequencing. Users must come prepared with an edited video file. For this reason, Popcorn Maker is not a web-based video editor–rather, it’s a video-based web editor. We may revisit this decision later when web browsers handle media playback and synchronization more precisely. Like the rest of the Popcorn project, Popcorn Maker is 100% free and open source. Developers of time-based multimedia apps are encouraged to build on the Butter SDK (source code available at http://github.com/mozilla/butter) and contribute back to the project. At the time of this writing, Popcorn Maker is in active development at version 0.5, and is scheduled for a 1.0 release in late 2012. http://mozillapopcorn.org.

Credits

The Popcorn project and its constituents are lovingly crafted by Ben Moskowitz, Bobby Richter, Brett Gaylor, David Seifried, Christopher De Cairos, Matthew Schranz, Jon Buckley, Scott Downe, Mohammed Buttu, Kate Hudson, David Humphrey, Jeremy Banks, Brian Chirls, James Burke, Robert Stanica, Anna Sobiepanek, Rick Waldron, Nick Cammarata, Daniel Hodgin, Daniel Brooks, Boaz Sender, Dan Ventura, Brad Chen, Minoo Ziaei, Cesar Gomes, Steven Weerdenburg, Cole Gillespie, and Nick Doiron.

MPEG Column: 100th MPEG Meeting

MPEG news: a report from the 100th meeting, Geneva, CH

The official press release is available here and I’d like to highlight two topics from MPEGs’ 100th meetingĀ in Geneva, Switzerland:

  • MP100E“: MPEG celebrates its 100th meeting
  • Systems news: ISOBMFF 4th edition, MDS social metadata, DASH conformance/refsw et al.
  • WebVC and ARAF goes CD
  • HEVC preliminary subjective test results publicly available Read more

Video Browser Showdown

The Video Browser Showdown (VBS) is a live video browsing competition where international researchers, working in the field of interactive video search, evaluate and demonstrate the efficiency of their tools in presence of the audience. The aim of the VBS is to evaluate video browsing tools for efficiency at known-item search (KIS) tasks with a well-defined data set in direct comparison to other tools. For each task the moderator presents a target clip on a shared screen that is visible to all participants. The participants use their own systems to perform an interactive search in the specified video file taken from a common data set and try to find the desired segment as fast as possible. Found segments are submitted to a server that is responsible for three tasks: (1) checking whether the submitted segment is correct, (2) measuring the task solve time and (3) computing scores for all teams and tasks. The performance of participating tools is evaluated in terms of successful submissions and search time. Read more

ACM International Conference on Multimedia 2009

On behalf of the entire Organizing Committee, we wish to report to you that the seventeen ACM International Conference on Multimedia (ACM Multimedia 2009), was held October 19-22, 2009 at the Beijing Hotel in Beijing, China.

The General Chairs at the Conference Banquet (l.t.r. Alan Hanjalic, Yong Rui, Wen Gao)

ACM Multimedia is the premier annual event on multimedia research, technology and art. Since 1993, the conference has brought together researchers, practitioners and users from academia, industry, and government active in the broad field of multimedia in order to communicate the state-of-the-art in multimedia research, technology and art. In particular, the conference brings newest insights into the possibilities to explore and exploit old and new media (e.g., text, audio, visual, haptics), used in isolation or in a synergetic combination, in order to bring the technology facilitating the interaction and communication among humans, machines and data a significant step further.

SIG Multimedia Chair Klara Nahrstedt

Richness of new fundamental concepts, practical tools and controversial ideas that emerged from the worldwide multimedia community in the past year is reflected in a wide variety of elements of this year’s conference program. In addition to the oral and poster sessions presenting the full and short technical papers, respectively, the conference also features a plenary brave new topic session and two panel discussions bringing up the issues that are currently hot and controversial in the field of multimedia. Special role in the conference program has been reserved for the workshops held in conjunction with the main conference and meant to focus on specific multimedia-related topics, either to explore them more in depth or to promote them in the multimedia community. One key aspect of this conference that is different from most other academic conferences is its emphasis on systems and applications. To this end, the conference also includes technical demonstrations of research prototypes and systems, open source software competition, video demonstration of concepts and applications, as well as multimedia art sessions. Finally, by including the doctoral symposium and tutorials on various topics, the conference is also committed to inspire and educate junior scientists in the field and so strengthen and expand the multimedia research community for the years to come.

Recipient of the 2009 SIGMM Award for Outstanding Technical Contributions to Multimedia Computing, Communications and Applications, Lawrence A. Rowe

A highlight of ACM Multimedia 2009 was the Multimedia Grand Challenge, organized for the first time as a part of the conference program. The Multimedia Grand Challenge is a set of problems and issues from a number of industry leaders geared to engage the multimedia research community in solving relevant, interesting and challenging questions about the industry’s 2-5 year horizon for multimedia. Researchers were encouraged to submit working systems in response to the challenge to win the Grand Challenge competition. A large number of submissions were received for this first edition of the competition. The large number not only reveals the interest of the research community to address relevant real-life problems, but also reflects the high potential that we already have in the community to successfully address these problems.

Editor-in-Chief of ACM SIGMM’s TOMCCAP journal, Nicholas Georganas

The Content, Applications, Systems, and Human-Centered Multimedia tracks received 305 long paper submissions (138 in Content, 75 in Applications, 56 in Systems, and 36 in Human-Centered Multimedia). Each paper was reviewed by at least three qualified reviewers in a double-blind review process. The Program Committee met on June 28 2009 in New York to discuss the papers and make final selections for papers to be included as oral presentations in the conference program. This rigorous review process resulted in the acceptance of 50 long papers: 22 in the Content track, 12 in the Applications track, 10 in the Systems track, and 6 in the Human-Centered Multimedia track. This represents an acceptance rate of 16.4% percent.

The short paper program received 369 submissions. After a thorough review process, we accepted 103 papers resulting in an acceptance rate of 27.9% percent. These short papers will be presented during poster sessions at the conference. This year’s sixth version of the Interactive Art Program will consist of long and short papers in the dedicated multimedia art sessions.

Welcome to the Animation School of Beijing Film Academy, hosts of the Conference Reception

We would like to thank our supporters: Baidu, Beijing Film Academy, FXPAL, Google, HP Labs, Microsoft Research, National Natural Science Foundation of China, NEC Labs, Netease, Peking University, Star Software, and Tencent. Without their generous support, organizing this conference would have been difficult.

The ACM Multimedia 2009 conference is the result of a strong and dedicated effort by a large number of volunteers. We would like to express our deep gratitude to everyone on the Organizing Committee for making the conference happen, and to the Program Committee and external reviewers who diligently worked to review submissions and provide suggestions and feedback to authors that resulted in a high quality final program. We also thank the ACM Staff for their strategic and administrative support. Finally we would like to acknowledge ACM and thank the special interest group SIGMM for sponsoring this event.

We hope you enjoyed the conference.

Wen Gao, Peking University, China
Yong Rui, Microsoft, China
Alan Hanjalic, Delft University of Technology, The Netherlands
ACM Multimedia 2009 General Co-Chairs