Micah Eckhardt, Rosalind W. Picard

Abstract

Labeling videos for affect content such as facial expression is tedious and time consuming. Researchers often spend significant amounts of time annotating experimental data, or simply lack the time required to label their data. For these reasons we have developed VidL, an open source video labeling system that is able to harness the distributed people-power of the internet. Through centralized management VidL can be used to manage data, custom label videos, manage workers, visualize labels, and review coders work. As an example, we recently labeled 700 short videos, approximately 60 hours of work, in 2 days using 20 labelers working from their own computers.