Active capture: automatic direction for automatic movies

Authors:
Marc Davis;Jeffrey Heer;Ana Ramirez
Affiliations:
University of California, Berkeley, Berkeley, CA;University of California, Berkeley, Berkeley, CA;University of California, Berkeley, Berkeley, CA
Venue:
MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Year:
2003

Citing 5
Cited 3

Designing annotation before it's needed

MULTIMEDIA '01 Proceedings of the ninth ACM international conference on Multimedia
Editing out Video Editing

IEEE MultiMedia
Active capture: automatic direction for automatic movies

MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Active capture: integrating human-computer interaction and computer vision/audition to automate media capture

ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 1
Documenting life: videography and common sense

ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 1

Active capture: automatic direction for automatic movies

MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Presiding over accidents: system direction of human action

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
DemoCut: generating concise instructional videos for physical demonstrations

Proceedings of the 26th annual ACM symposium on User interface software and technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Active Capture demonstration is part of a new computational media production paradigm that transforms media production from a manual mechanical process into an automated computational one that can produce mass customized and personalized media integrating video of non-actors. Active Capture leverages media production knowledge, computer vision and audition, and user interaction design to automate direction and cinematography and thus enables the automatic production of annotated, high quality, reusable media assets. The implemented system automates the process of capturing a non-actor performing two simple reusable actions ("screaming" and "turning her head to look at the camera") and automatically integrates those shots into various commercials and movie trailers.