# videoqa

**Repository Path**: Chris_Ch0u/videoqa

## Basic Information

- **Project Name**: videoqa
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2018-08-23
- **Last Updated**: 2020-12-18

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

#+OPTION: ^:nil
* Open-Ended Video-QA

** [[http://ieeexplore.ieee.org/document/8017608][Unifying the Video and Question Attentions for Open-Ended Video Question Answering]]

*** Dataset
- [[./dataset/file_map.tsv][file_map]]: contains the urls of the videos
- [[./dataset/QA.tsv][QA]]: contains the question-answer pairs
- [[./dataset/split][Split]]: contains the dataset split in the paper

If you use the dataset, please cite our paper 

@article{xue2017unifying,

  title={Unifying the Video and Question Attentions for Open-Ended Video Question Answering},

  author={Xue, Hongyang and Zhao, Zhou and Cai, Deng},

  journal={IEEE Transactions on Image Processing},

  year={2017},

  publisher={IEEE}

}

*** Code
**** contains the methods in the paper

*** Dependency
- [[https://github.com/Theano][Theano]]
- [[https://github.com/mila-udem/blocks][Blocks]]
- Python >= 3.4

*** Example

[[./examples/117791.gif]] 
- Question: What is a boy combing his hair with?
- Groundtruth: with his fingers
- Prediction: with his hands

[[./examples/076306.gif]]
- Question: What runs up a fence?
- Groundtruth: a cat
- Prediction: a cat

.[[/examples/112935.gif]]
- Question: What is a young girl in a car adjusting?
- Groundtruth: her dark glasses
- Prediction: her hair