Classification of important segments in educational videos using multimodal features

Junaid Ahmed Ghauri; Sherzod Hakimov; Ralph Ewerth

doi:10.48550/arXiv.2010.13626

Details

Original language	English
Title of host publication	Proceeding of the CIKM 2020 Workshops
Subtitle of host publication	Proceedings of the CIKM 2020 Workshops co-located with 29th ACM International Conference on Information and Knowledge Management (CIKM 2020)
Number of pages	8
Publication status	Published - 2020
Externally published	Yes
Event	2020 International Conference on Information and Knowledge Management Workshops, CIKMW 2020 - Galway, Ireland Duration: 19 Oct 2020 → 23 Oct 2020

Publication series

Name	CEUR Workshop Proceedings
Publisher	CEUR Workshop Proceedings
Volume	2699
ISSN (Print)	1613-0073

Abstract

Videos are a commonly-used type of content in learning during Web search. Many e-learning platforms provide quality content, but sometimes educational videos are long and cover many topics. Humans are good in extracting important sections from videos, but it remains a significant challenge for computers. In this paper, we address the problem of assigning importance scores to video segments, that is how much information they contain with respect to the overall topic of an educational video. We present an annotation tool and a new dataset of annotated educational videos collected from popular online learning platforms. Moreover, we propose a multimodal neural architecture that utilizes state-of-the-art audio, visual and textual features. Our experiments investigate the impact of visual and temporal information, as well as the combination of multimodal features on importance prediction.

Keywords

Deep learning, E-learning, Educational videos, Importance prediction, MOOC, Video analysis, Video summarization

ASJC Scopus subject areas

Computer Science(all)
General Computer Science

Cite this

Classification of important segments in educational videos using multimodal features. / Ghauri, Junaid Ahmed; Hakimov, Sherzod; Ewerth, Ralph.
Proceeding of the CIKM 2020 Workshops: Proceedings of the CIKM 2020 Workshops co-located with 29th ACM International Conference on Information and Knowledge Management (CIKM 2020). 2020. (CEUR Workshop Proceedings; Vol. 2699).

Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review

Ghauri, JA, Hakimov, S & Ewerth, R 2020, Classification of important segments in educational videos using multimodal features. in Proceeding of the CIKM 2020 Workshops: Proceedings of the CIKM 2020 Workshops co-located with 29th ACM International Conference on Information and Knowledge Management (CIKM 2020). CEUR Workshop Proceedings, vol. 2699, 2020 International Conference on Information and Knowledge Management Workshops, CIKMW 2020, Galway, Ireland, 19 Oct 2020. https://doi.org/10.48550/arXiv.2010.13626

Ghauri, J. A., Hakimov, S., & Ewerth, R. (2020). Classification of important segments in educational videos using multimodal features. In Proceeding of the CIKM 2020 Workshops: Proceedings of the CIKM 2020 Workshops co-located with 29th ACM International Conference on Information and Knowledge Management (CIKM 2020) (CEUR Workshop Proceedings; Vol. 2699). https://doi.org/10.48550/arXiv.2010.13626

Ghauri JA, Hakimov S, Ewerth R. Classification of important segments in educational videos using multimodal features. In Proceeding of the CIKM 2020 Workshops: Proceedings of the CIKM 2020 Workshops co-located with 29th ACM International Conference on Information and Knowledge Management (CIKM 2020). 2020. (CEUR Workshop Proceedings). doi: 10.48550/arXiv.2010.13626

Ghauri, Junaid Ahmed ; Hakimov, Sherzod ; Ewerth, Ralph. / Classification of important segments in educational videos using multimodal features. Proceeding of the CIKM 2020 Workshops: Proceedings of the CIKM 2020 Workshops co-located with 29th ACM International Conference on Information and Knowledge Management (CIKM 2020). 2020. (CEUR Workshop Proceedings).

Download

@inproceedings{77883d78945346eebcbbd9029bbdc435,

title = "Classification of important segments in educational videos using multimodal features",

abstract = "Videos are a commonly-used type of content in learning during Web search. Many e-learning platforms provide quality content, but sometimes educational videos are long and cover many topics. Humans are good in extracting important sections from videos, but it remains a significant challenge for computers. In this paper, we address the problem of assigning importance scores to video segments, that is how much information they contain with respect to the overall topic of an educational video. We present an annotation tool and a new dataset of annotated educational videos collected from popular online learning platforms. Moreover, we propose a multimodal neural architecture that utilizes state-of-the-art audio, visual and textual features. Our experiments investigate the impact of visual and temporal information, as well as the combination of multimodal features on importance prediction.",

keywords = "Deep learning, E-learning, Educational videos, Importance prediction, MOOC, Video analysis, Video summarization",

author = "Ghauri, {Junaid Ahmed} and Sherzod Hakimov and Ralph Ewerth",

note = "Publisher Copyright: {\textcopyright} 2020 CEUR-WS. All rights reserved. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 2020 International Conference on Information and Knowledge Management Workshops, CIKMW 2020 ; Conference date: 19-10-2020 Through 23-10-2020",

year = "2020",

doi = "10.48550/arXiv.2010.13626",

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR Workshop Proceedings",

booktitle = "Proceeding of the CIKM 2020 Workshops",

}

Download

TY - GEN

T1 - Classification of important segments in educational videos using multimodal features

AU - Ghauri, Junaid Ahmed

AU - Hakimov, Sherzod

AU - Ewerth, Ralph

PY - 2020

Y1 - 2020

N2 - Videos are a commonly-used type of content in learning during Web search. Many e-learning platforms provide quality content, but sometimes educational videos are long and cover many topics. Humans are good in extracting important sections from videos, but it remains a significant challenge for computers. In this paper, we address the problem of assigning importance scores to video segments, that is how much information they contain with respect to the overall topic of an educational video. We present an annotation tool and a new dataset of annotated educational videos collected from popular online learning platforms. Moreover, we propose a multimodal neural architecture that utilizes state-of-the-art audio, visual and textual features. Our experiments investigate the impact of visual and temporal information, as well as the combination of multimodal features on importance prediction.

AB - Videos are a commonly-used type of content in learning during Web search. Many e-learning platforms provide quality content, but sometimes educational videos are long and cover many topics. Humans are good in extracting important sections from videos, but it remains a significant challenge for computers. In this paper, we address the problem of assigning importance scores to video segments, that is how much information they contain with respect to the overall topic of an educational video. We present an annotation tool and a new dataset of annotated educational videos collected from popular online learning platforms. Moreover, we propose a multimodal neural architecture that utilizes state-of-the-art audio, visual and textual features. Our experiments investigate the impact of visual and temporal information, as well as the combination of multimodal features on importance prediction.

KW - Deep learning

KW - E-learning

KW - Educational videos

KW - Importance prediction

KW - MOOC

KW - Video analysis

KW - Video summarization

UR - http://www.scopus.com/inward/record.url?scp=85097538318&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2010.13626

DO - 10.48550/arXiv.2010.13626

M3 - Conference contribution

AN - SCOPUS:85097538318

T3 - CEUR Workshop Proceedings

BT - Proceeding of the CIKM 2020 Workshops

T2 - 2020 International Conference on Information and Knowledge Management Workshops, CIKMW 2020

Y2 - 19 October 2020 through 23 October 2020

ER -

Research@Leibniz University