DMCA
Crowdsourcing step-by-step information extraction to enhance existing how-to videos (2014)
Cached
Download Links
| Venue: | In CHI ’14 |
| Citations: | 10 - 4 self |
BibTeX
@INPROCEEDINGS{Kim14crowdsourcingstep-by-step,
author = {Juho Kim and Phu Nguyen and Sarah Weir and Philip J. Guo and Robert C. Miller and Krzysztof Z. Gajos},
title = {Crowdsourcing step-by-step information extraction to enhance existing how-to videos},
booktitle = {In CHI ’14},
year = {2014}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Millions of learners today use how-to videos to master new skills in a variety of domains. But browsing such videos is often tedious and inefficient because video player interfaces are not optimized for the unique step-by-step structure of such videos. This research aims to improve the learning experience of existing how-to videos with step-by-step annotations. We first performed a formative study to verify that annota tions are actually useful to learners. We created ToolScape, an interactive video player that displays step descriptions and intermediate result thumbnails in the video timeline. Learners in our study performed better and gained more self-efficacy using ToolScape versus a traditional video player. To add the needed step annotations to existing how-to videos at scale, we introduce a novel crowdsourcing workflow. It ex tracts step-by-step structure from an existing video, including step times, descriptions, and before and after images. We in troduce the Find-Verify-Expand design pattern for temporal and visual annotation, which applies clustering, text process ing, and visual analysis algorithms to merge crowd output. The workflow does not rely on domain-specific customiza tion, works on top of existing videos, and recruits untrained crowd workers. We evaluated the workflow with Mechanical Turk, using 75 cooking, makeup, and Photoshop videos on YouTube. Results show that our workflow can extract steps with a quality comparable to that of trained annotators across all three domains with 77 % precision and 81 % recall. Author Keywords Crowdsourcing; how-to videos; video annotation.
Keyphrases
how-to video step-by-step information extraction new skill step-by-step annotation crowd worker interactive video player video player interface domain-specific customiza tion text process ing annota tions needed step annotation visual analysis algorithm unique step-by-step structure crowd output author keywords crowdsourcing video timeline step description mechanical turk visual annotation trained annotator step-by-step structure learning experience find-verify-expand design pattern step time formative study traditional video player learner today intermediate result thumbnail video annotation
