Towards Multimodal Empathetic Response Generation: A Rich Text-Speech-Vision Avatar-based Benchmark.

@inproceedings{zhang-2025-towards, author = {Han Zhang and Zixiang Meng and Meng Luo and Hong Han and Lizi Liao and Erik Cambria and Hao Fei}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{Towards Multimodal Empathetic Response Generation: A Rich Text-Speech-Vision Avatar-based Benchmark}}, booktitle = {{Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025- 2 May 2025}}, pages = {2872--2881}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3696410.3714739}, doi = {https://doi.org/10.1145/3696410.3714739} }