EmoHuman: Fine-Grained Emotion-Controlled Talking Head Generation via Audio-Text Multimodal Detangling.

@inproceedings{dai-2025-emohuman, author = {Qifeng Dai and Huidong Feng and Wendi Cui and Xinqi Cai and Yinglin Zheng and Ming Zeng}, editor = {Zhongfei Zhang and Elisa Ricci and Yan Yan and Liqiang Nie and Vincent Oria and Lamberto Ballan}, title = {{EmoHuman: Fine-Grained Emotion-Controlled Talking Head Generation via Audio-Text Multimodal Detangling}}, booktitle = {{Proceedings of the 2025 International Conference on Multimedia Retrieval, ICMR 2025, Chicago, IL, USA, 30 June 2025 - 3 July 2025}}, pages = {145--154}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3731715.3733322}, doi = {https://doi.org/10.1145/3731715.3733322} }