Nobukatsu Hojo, Saki Mizuno, Satoshi Kobashikawa, Ryo Masumura, Mana Ihori, Hiroshi Sato, Tomohiro Tanaka. Audio-Visual Praise Estimation for Conversational Video based on Synchronization-Guided Multimodal Transformer. In Naomi Harte, Julie Carson-Berndsen, Gareth Jones, editors, 24th Annual Conference of the International Speech Communication Association, Interspeech 2023, Dublin, Ireland, August 20-24, 2023. pages 2663-2667, ISCA, 2023. [doi]
@inproceedings{HojoMKMIST23,
title = {Audio-Visual Praise Estimation for Conversational Video based on Synchronization-Guided Multimodal Transformer},
author = {Nobukatsu Hojo and Saki Mizuno and Satoshi Kobashikawa and Ryo Masumura and Mana Ihori and Hiroshi Sato and Tomohiro Tanaka},
year = {2023},
doi = {10.21437/Interspeech.2023-1464},
url = {https://doi.org/10.21437/Interspeech.2023-1464},
researchr = {https://researchr.org/publication/HojoMKMIST23},
cites = {0},
citedby = {0},
pages = {2663-2667},
booktitle = {24th Annual Conference of the International Speech Communication Association, Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
editor = {Naomi Harte and Julie Carson-Berndsen and Gareth Jones},
publisher = {ISCA},
}