README.md

videoqa-stan

Source code for Video Question Answering via Hierarchical Spatio-Temporal Attention Networks based on arctic-captions and arctic-capgen-vid.

Dependencies

To run this code you will need:

• Python 2.7
• Theano
• NLTK and WordNet Synsets

Reference

"Video Question Answering via Hierarchical Spatio-Temporal Attention Networks."
Zhou Zhao, Qifan Yang*, Deng Cai, Xiaofei He, Yueting Zhuang. To appear IJCAI 2017.

License

The code is released under a revised (3-clause) BSD License.