Community annotation and remix: a research platform and pilot deployment

  • Authors:

  • Ryan Shaw;Patrick Schmitz

  • Affiliations:

  • Yahoo! Research Berkeley, Berkeley, CA;Yahoo! Research Berkeley, Berkeley, CA

  • Venue:
  • Proceedings of the 1st ACM international workshop on Human-centered multimedia
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a platform for community-supported media annotation and remix, including a pilot deployment with a major film festival. The platform was well received by users as fun and easy to use. An analysis of the resulting data yielded insights into user behavior. Completed remixes exhibited a range of genres, with over a third showing thematic unity and a quarter showing some attempt at narrative. Remixes were often complex, using many short segments taken from various source media. Reuse of spoken and written language in source media, and the use of written language in user-defined overlay text segments proved to be essential for most users. We describe how community remix statistics can be leveraged for media summarization, browsing, and editing support. Further, the platform as a whole provides a solid base for a range of ongoing research into community annotation and remix including analysis of remix syntax, identification of reusable segments, media and segment tagging, structured annotation of media, collaborative media production, and hybrid content-based and community-in-the-loop approaches to understanding media semantics.