SIGMM Strategic Retreat Executive Summary

ACM SIG Multimedia Strategic Retreat

(Friday October 31 - Saturday November 1, 2003)

Executive Summary

The ACM Special Interest Group on Multimedia (SIGMM) was created ten years ago. Since that time, researchers have solved a number of important problems related to media processing, multimedia databases, and distributed multimedia applications. Discussions at the annual SIGMM conference ACM Multimedia 2001 (MM'01) in Ottawa, Canada suggested it was time for senior members of the research community to meet and discuss the future of multimedia research. Some members of the community believed that multimedia research was addressing narrow topics with limited impact rather than addressing major problems that will have wider impact on technology for real and emerging applications.

A strategic retreat was organized as part of MM'03 to assess the current state of multimedia research and suggest directions for future research. Twenty-six researchers from academia and industry participated in the retreat organized by Professors Lawrence A. Rowe and Ramesh Jain who are the past and current SIGMM Chairs. Each participant was invited to write a short position paper briefly responding to questions about past research successes, future research directions, and the current state of SIGMM. These position papers were distributed to attendees before the retreat.

Multimedia research successes and failures were discussed during the retreat after which three grand challenges were identified that researchers should attempt to solve.

  • Authoring complex multimedia titles should be as easy as using a word processor to produce a document or drawing program to produce a diagram. These titles might be, for example, interactive material for teaching and learning, networked multiple player games, personal titles created to document a trip or event, or a multimedia document derived from archived material or material captured from a live event. Authors might be novices or experts and titles might be simple or complex but the tools used to produce content should enable the creation of high quality titles and experiences.
  • Interactions with remote people and environments should be nearly the same experience as interactions with local people and environments. Distributed collaboration and interactive, immersive 3D environments will have a significant impact on communication in the future. Just as the rapid decline in the cost of RAM memory in the 1980's lead to widespread adoption of graphical user interfaces, the forthcoming decline in the cost of communication will enable applications and interfaces that will lead to significant changes in our lives.
  • Capturing, storing, finding, and using digital media should be an everyday occurrence in our computing environment. The development of digital cameras and the emergence of cellphones with built-in cameras are adding to the already significant information glut. People want to use this material, but it is nearly impossible given the problem of storing, searching, and accessing this material.

Research over the past several decades has focused on the "nuts & bolts" infrastructure required by distributed multimedia applications. Now is the time to raise expectations for the development of tools and applications that incorporate new media types, multiple media and context, and intelligent systems to solve important problems and produce high quality user experiences. Important elements will include innovative user interfaces, automation, and intelligent agents that will assist the user.