BROWSE

Related Scientist

's photo.

수리 및 계산 과학 연구단
more info

ITEM VIEW & DOWNLOAD

Finding epic moments in live content through deep learning on collective decisions

Cited 0 time in webofscience Cited 0 time in scopus
4 Viewed 0 Downloaded
Title
Finding epic moments in live content through deep learning on collective decisions
Author(s)
Hyeonho Song; Park, Kunwoo; Meeyoung Cha
Publication Date
2021-08
Journal
EPJ DATA SCIENCE, v.10, no.1
Publisher
SPRINGER
Abstract
Live streaming services enable the audience to interact with one another and the streamer over live content. The surging popularity of live streaming platforms has created a competitive environment. To retain existing viewers and attract newcomers, streamers and fans often create a well-condensed summary of the streamed content. However, this process is manual and costly due to the length of online live streaming events. The current study identifies enjoyable moments in user-generated live video content by examining the audiences' collective evaluation of its epicness. We characterize what features "epic" moments and present a deep learning model to extract them based on analyzing two million user-recommended clips and the associated chat conversations. The evaluation shows that our data-driven approach can identify epic moments from user-generated streamed content that cover various contexts (e.g., victory, funny, awkward, embarrassing). Our user study further demonstrates that the proposed automatic model performs comparably to expert suggestions. We discuss implications of the collective decision-driven extraction in identifying diverse epic moments in a scalable way.
URI
https://pr.ibs.re.kr/handle/8788114/10414
DOI
10.1140/epjds/s13688-021-00295-6
ISSN
2193-1127
Appears in Collections:
Pioneer Research Center for Mathematical and Computational Sciences(수리 및 계산과학 연구단) > Data Science Group(데이터 사이언스 그룹) > 1. Journal Papers (저널논문)
Files in This Item:
There are no files associated with this item.

qrcode

  • facebook

    twitter

  • Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
해당 아이템을 이메일로 공유하기 원하시면 인증을 거치시기 바랍니다.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse