Yixuan He, Xing Xu 0001, Xin Liu, Weihua Ou, Huimin Lu. Multimodal Transformer Networks with Latent Interaction for Audio-Visual Event Localization. In 2021 IEEE International Conference on Multimedia and Expo, ICME 2021, Shenzhen, China, July 5-9, 2021. pages 1-6, IEEE, 2021. [doi]
@inproceedings{He0LOL21,
title = {Multimodal Transformer Networks with Latent Interaction for Audio-Visual Event Localization},
author = {Yixuan He and Xing Xu 0001 and Xin Liu and Weihua Ou and Huimin Lu},
year = {2021},
doi = {10.1109/ICME51207.2021.9428081},
url = {https://doi.org/10.1109/ICME51207.2021.9428081},
researchr = {https://researchr.org/publication/He0LOL21},
cites = {0},
citedby = {0},
pages = {1-6},
booktitle = {2021 IEEE International Conference on Multimedia and Expo, ICME 2021, Shenzhen, China, July 5-9, 2021},
publisher = {IEEE},
isbn = {978-1-6654-3864-3},
}