Hung Le, Doyen Sahoo, Nancy F. Chen, Steven C. H. Hoi. Hierarchical multimodal attention for end-to-end audio-visual scene-aware dialogue response generation. Computer Speech & Language, 63:101095, 2020. [doi]
@article{LeSCH20,
title = {Hierarchical multimodal attention for end-to-end audio-visual scene-aware dialogue response generation},
author = {Hung Le and Doyen Sahoo and Nancy F. Chen and Steven C. H. Hoi},
year = {2020},
doi = {10.1016/j.csl.2020.101095},
url = {https://doi.org/10.1016/j.csl.2020.101095},
researchr = {https://researchr.org/publication/LeSCH20},
cites = {0},
citedby = {0},
journal = {Computer Speech & Language},
volume = {63},
pages = {101095},
}