Presentation Details
| AnnotateVid.Io: A platform for crowd-annotation of behavioral videos Mark Fisher. University of Kansas, Lawrence, KS, USA |
Abstract
AnnotateVid.io is a highly customizable web application where users create public or private video collections that can be annotated by other (public or invited) users with the aim to capture data related to behavior. It is “free as in beer” for academic accounts. Collection owners can customize the data intake questions they ask of their collection’s users for all individuals, videos, and behaviors featured in their collection(s). This allows for great flexibility in the types of videos and behaviors that can be annotated. During annotation, a user indicates when a behavior is begun, and then marks when that behavior is ended in the video. Data for the behaviors recorded per video and per collection as a whole are downloadable as well as filterable and sortable by each custom attribute in the video. These data could facilitate analyses of frequency, duration, success/failure rates, or even association of various behaviors with each other across time. Related example uses of AnnotateVid.io will be demonstrated, potentially including a collection of course lecture videos, a collection of human sport activity videos, and a collection of rattlesnake behavior videos.
No part of this publication may be reproduced, distributed, or transmitted in any form or by any means, including photocopying, recording, or other electronic or mechanical methods, without the prior written permission of the author.
No part of this publication may be reproduced, distributed, or transmitted in any form or by any means, including photocopying, recording, or other electronic or mechanical methods, without the prior written permission of the author.
Content Locked. Log into a registered attendee account to access this presentation.