PrincetonComputer SciencePIXL GroupPublications → [Ignat et al. 2019] Local Access
Identifying Visible Actions in Lifestyle Vlogs

Annual Meeting of the Association for Computational Linguistics (ACL), July 2019

Oana Ignat, Laura Burdick,
Jia Deng, Rada Mihalcea
Abstract

We 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. We demonstrate that our multimodal algorithm outperforms algorithms based only on one modality at a time.
Citation

Oana Ignat, Laura Burdick, Jia Deng, and Rada Mihalcea.
"Identifying Visible Actions in Lifestyle Vlogs."
Annual Meeting of the Association for Computational Linguistics (ACL), July 2019.

BibTeX

@inproceedings{Ignat:2019:IVA,
   author = "Oana Ignat and Laura Burdick and Jia Deng and Rada Mihalcea",
   title = "Identifying Visible Actions in Lifestyle Vlogs",
   booktitle = "Annual Meeting of the Association for Computational Linguistics (ACL)",
   year = "2019",
   month = jul
}