@inproceedings{lei-etal-2018-tvqa, title = "{TVQA}: Localized, Compositional Video Question Answering", author = "Lei, Jie and Yu, Licheng and Bansal, Mohit and Berg, Tamara", editor = "Riloff, Ellen and Chiang, David and Hockenmaier, Julia and Tsujii, Jun{'}ichi", booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing", month = oct # "-" # nov, year = "2018", address = "Brussels, Belgium", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/D18-1167/", doi = "10.18653/v1/D18-1167", pages = "1369--1379" }