Li, X., Song, J., Gao, L., Liu, X., Huang, W., He, X., & Gan, C. (2019). Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 8658-8665. https://doi.org/10.1609/aaai.v33i01.33018658