MovieQA: Understanding Stories in Movies through Question-Answering
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Video+Subtitles Question Answering | MovieQA (val) | Accuracy0.38 | 13 | |
| Textual Cloze | RecipeQA (test) | Accuracy26.89 | 9 | |
| Video Question Answering | MovieQA v1 (test) | Accuracy24.32 | 8 | |
| Video Question Answering | MovieQA v1 (val) | Accuracy34.2 | 8 | |
| Question Answering | MovieQA Plot Synopses 1.0 (test) | Accuracy56.7 | 7 | |
| Question Answering | MovieQA (val) | Accuracy34.2 | 7 | |
| Question Answering | MovieQA Plot Synopses 1.0 (val) | Accuracy56.7 | 6 | |
| Question Answering | MovieQA Subtitle 1.0 (val) | Accuracy38 | 5 | |
| Question Answering | MovieQA Script 1.0 (val) | Accuracy42.3 | 5 | |
| Question Answering | MovieQA DVS 1.0 (val) | Accuracy33 | 5 |