MovieQA: Understanding Stories in Movies through Question-Answering
Name
Torralba_MovieQA.pdf
Size
2.42 MB
Format
Adobe PDF
Checksum (MD5)
d4cc77c0cea62d61e895a135a98fd136
Author(s)
Tapaswi, Makarand
Zhu, Yukun
Stiefelhagen, Rainer
Torralba, Antonio
Urtasun, Raquel
Fidler, Sanja
Date Issued
December 2016
Journal
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
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.
Version
Author's final manuscript
Abstract
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
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPR.2016.501
