Ankit P. Shah, Shijie Geng, Peng Gao, Anoop Cherian, Takaaki Hori, Tim K. Marks, Jonathan Le Roux, Chiori Hori. Audio-Visual Scene-Aware Dialog and Reasoning Using Audio-Visual Transformers with Joint Student-Teacher Learning. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022. pages 7732-7736, IEEE, 2022. [doi]
@inproceedings{ShahGGCHMRH22,
title = {Audio-Visual Scene-Aware Dialog and Reasoning Using Audio-Visual Transformers with Joint Student-Teacher Learning},
author = {Ankit P. Shah and Shijie Geng and Peng Gao and Anoop Cherian and Takaaki Hori and Tim K. Marks and Jonathan Le Roux and Chiori Hori},
year = {2022},
doi = {10.1109/ICASSP43922.2022.9746481},
url = {https://doi.org/10.1109/ICASSP43922.2022.9746481},
researchr = {https://researchr.org/publication/ShahGGCHMRH22},
cites = {0},
citedby = {0},
pages = {7732-7736},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022},
publisher = {IEEE},
isbn = {978-1-6654-0540-9},
}