Skip to main content

Identifying Visible Actions in Lifestyle Vlogs

Author(s): Ignat, Oana; Burdick, Laura; Deng, Jia; Mihalcea, Rada

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1xf9p
Full metadata record
DC FieldValueLanguage
dc.contributor.authorIgnat, Oana-
dc.contributor.authorBurdick, Laura-
dc.contributor.authorDeng, Jia-
dc.contributor.authorMihalcea, Rada-
dc.date.accessioned2021-10-08T19:45:50Z-
dc.date.available2021-10-08T19:45:50Z-
dc.date.issued2019en_US
dc.identifier.citationIgnat, Oana, Laura Burdick, Jia Deng, and Rada Mihalcea. "Identifying Visible Actions in Lifestyle Vlogs." Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (2019): pp. 6406-6417. doi:10.18653/v1/P19-1643en_US
dc.identifier.urihttps://arxiv.org/pdf/1906.04236.pdf-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1xf9p-
dc.description.abstractWe consider the task of identifying human actions visible in online videos. We focus on the widely spread genre of lifestyle vlogs, which consist of videos of people performing actions while verbally describing them. Our goal is to identify if actions mentioned in the speech description of a video are visually present. We construct a dataset with crowdsourced manual annotations of visible actions, and introduce a multimodal algorithm that leverages information derived from visual and linguistic clues to automatically infer which actions are visible in a video.en_US
dc.format.extent6406 - 6417en_US
dc.language.isoen_USen_US
dc.relation.ispartofProceedings of the 57th Annual Meeting of the Association for Computational Linguisticsen_US
dc.rightsAuthor's manuscripten_US
dc.titleIdentifying Visible Actions in Lifestyle Vlogsen_US
dc.typeConference Articleen_US
dc.identifier.doi10.18653/v1/P19-1643-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
VisibleActionsLifestyleVlogs.pdf1.69 MBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.