CMFF-Face: Attention-Based Cross-Modal Feature Fusion for High-Quality Audio-Driven Talking Face Generation.

@inproceedings{zhao-2024-cmffface, author = {Guangzhe Zhao and Yanan Liu and Xueping Wang and Feihu Yan}, editor = {Cathal Gurrin and Rachada Kongkachandra and Klaus Sch\"{o}ffmann and Duc-Tien Dang-Nguyen and Luca Rossetto and Shin'ichi Satoh and Liting Zhou}, title = {{CMFF-Face: Attention-Based Cross-Modal Feature Fusion for High-Quality Audio-Driven Talking Face Generation}}, booktitle = {{Proceedings of the 2024 International Conference on Multimedia Retrieval, ICMR 2024, Phuket, Thailand, June 10-14, 2024}}, pages = {101--110}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3652583.3658055}, doi = {https://doi.org/10.1145/3652583.3658055} }