https://github.com/AngusKung/MovieQA
Some experiments on MovieQA with Yuan-Ting Hsieh, En-Yu Fan and Jia-Cheng Huang in AMLDS
https://github.com/AngusKung/MovieQA
Last synced: 3 months ago
JSON representation
Some experiments on MovieQA with Yuan-Ting Hsieh, En-Yu Fan and Jia-Cheng Huang in AMLDS
- Host: GitHub
- URL: https://github.com/AngusKung/MovieQA
- Owner: AngusKung
- Created: 2016-05-19T09:18:57.000Z (about 10 years ago)
- Default Branch: master
- Last Pushed: 2016-06-22T16:04:17.000Z (almost 10 years ago)
- Last Synced: 2023-10-20T17:17:23.300Z (over 2 years ago)
- Language: Python
- Homepage:
- Size: 1.9 MB
- Stars: 5
- Watchers: 3
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG
Awesome Lists containing this project
- Awesome-Code - Some experiments on MovieQA with Hsieh,Tom and Huang in AMLDS
README
# MovieQA
MovieQA: Understanding Stories in Movies through Question-Answering
Makarand Tapaswi, Yukun Zhu, Rainer Stiefelhagen, Antonio Torralba, Raquel Urtasun, and Sanja Fidler
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, June 2016.
[Project page](http://movieqa.cs.toronto.edu) |
[arXiv preprint](http://arxiv.org/abs/1512.02902) |
[Read the paper](http://arxiv.org/abs/1512.02902) |
[Explore the data](http://movieqa.cs.toronto.edu/examples/)
----
### Benchmark Data
The data is made available in simple JSON / text files for easy access in any environment. We provide Python scripts to help you get started by providing simple data loaders.
To obtain access to the stories, and evaluate new approaches on the test data, please register at our [benchmark website](http://movieqa.cs.toronto.edu/).
### Python data loader
import MovieQA
mqa = MovieQA.DataLoader()
#### Explore
Movies are indexed using their corresponding IMDb keys. For example
mqa.pprint_movie(mqa.movies_map['tt0133093'])
QAs are stored as a standard Python list
mqa.pprint_qa(mqa.qa_list[0])
#### Use
To get train or test splits of the QA along with a particular story, use
story, qa = mqa.get_story_qa_data('train', 'plot')
Currently supported story forms are: plot, split plot
----
### Requirements
- numpy
- pysrt