MovieQA: Understanding Stories in Movies through Question-Answering
We introduce the MovieQA dataset which aims to evaluate automatic story comprehension from both video and text. The dataset consists of 14,944 questions about 408 movies with high semantic diversity. The questions range from simpler "Who" did "What" to "Whom", to "...
Main Authors: | , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | en_US |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2018
|
Online Access: | http://hdl.handle.net/1721.1/113894 https://orcid.org/0000-0003-4915-0256 |
_version_ | 1811076672600932352 |
---|---|
author | Tapaswi, Makarand Zhu, Yukun Stiefelhagen, Rainer Torralba, Antonio Urtasun, Raquel Fidler, Sanja |
author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Tapaswi, Makarand Zhu, Yukun Stiefelhagen, Rainer Torralba, Antonio Urtasun, Raquel Fidler, Sanja |
author_sort | Tapaswi, Makarand |
collection | MIT |
description | We introduce the MovieQA dataset which aims to evaluate automatic story comprehension from both video and text. The dataset consists of 14,944 questions about 408 movies with high semantic diversity. The questions range from simpler "Who" did "What" to "Whom", to "Why" and "How" certain events occurred. Each question comes with a set of five possible answers, a correct one and four deceiving answers provided by human annotators. Our dataset is unique in that it contains multiple sources of information - video clips, plots, subtitles, scripts, and DVS. We analyze our data through various statistics and methods. We further extend existing QA techniques to show that question-answering with such open-ended semantics is hard. We make this data set public along with an evaluation benchmark to encourage inspiring work in this challenging domain. Keywords: Motion pictures,
Visualization, Semantics, Voltage control, Cognition, Natural languages, Computer vision |
first_indexed | 2024-09-23T10:25:45Z |
format | Article |
id | mit-1721.1/113894 |
institution | Massachusetts Institute of Technology |
language | en_US |
last_indexed | 2024-09-23T10:25:45Z |
publishDate | 2018 |
publisher | Institute of Electrical and Electronics Engineers (IEEE) |
record_format | dspace |
spelling | mit-1721.1/1138942022-09-30T21:03:48Z MovieQA: Understanding Stories in Movies through Question-Answering Tapaswi, Makarand Zhu, Yukun Stiefelhagen, Rainer Torralba, Antonio Urtasun, Raquel Fidler, Sanja Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Torralba, Antonio We introduce the MovieQA dataset which aims to evaluate automatic story comprehension from both video and text. The dataset consists of 14,944 questions about 408 movies with high semantic diversity. The questions range from simpler "Who" did "What" to "Whom", to "Why" and "How" certain events occurred. Each question comes with a set of five possible answers, a correct one and four deceiving answers provided by human annotators. Our dataset is unique in that it contains multiple sources of information - video clips, plots, subtitles, scripts, and DVS. We analyze our data through various statistics and methods. We further extend existing QA techniques to show that question-answering with such open-ended semantics is hard. We make this data set public along with an evaluation benchmark to encourage inspiring work in this challenging domain. Keywords: Motion pictures, Visualization, Semantics, Voltage control, Cognition, Natural languages, Computer vision 2018-02-26T21:43:32Z 2018-02-26T21:43:32Z 2016-12 2016-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-4673-8851-1 http://hdl.handle.net/1721.1/113894 Tapaswi, Makarand, et al. "MovieQA: Understanding Stories in Movies through Question-Answering." 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27-30 June, 2016, Las Vegas, Nevada, IEEE, 2016, pp. 4631–40. https://orcid.org/0000-0003-4915-0256 en_US http://dx.doi.org/10.1109/CVPR.2016.501 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) arXiv |
spellingShingle | Tapaswi, Makarand Zhu, Yukun Stiefelhagen, Rainer Torralba, Antonio Urtasun, Raquel Fidler, Sanja MovieQA: Understanding Stories in Movies through Question-Answering |
title | MovieQA: Understanding Stories in Movies through Question-Answering |
title_full | MovieQA: Understanding Stories in Movies through Question-Answering |
title_fullStr | MovieQA: Understanding Stories in Movies through Question-Answering |
title_full_unstemmed | MovieQA: Understanding Stories in Movies through Question-Answering |
title_short | MovieQA: Understanding Stories in Movies through Question-Answering |
title_sort | movieqa understanding stories in movies through question answering |
url | http://hdl.handle.net/1721.1/113894 https://orcid.org/0000-0003-4915-0256 |
work_keys_str_mv | AT tapaswimakarand movieqaunderstandingstoriesinmoviesthroughquestionanswering AT zhuyukun movieqaunderstandingstoriesinmoviesthroughquestionanswering AT stiefelhagenrainer movieqaunderstandingstoriesinmoviesthroughquestionanswering AT torralbaantonio movieqaunderstandingstoriesinmoviesthroughquestionanswering AT urtasunraquel movieqaunderstandingstoriesinmoviesthroughquestionanswering AT fidlersanja movieqaunderstandingstoriesinmoviesthroughquestionanswering |