Optimizing Discriminative Vision-Language Models for Efficient Multimodal Intent Recognition.

@inproceedings{song-2025-optimizing, author = {Jinwang Song and Zhongtian Hua and Hongying Zan and Yingjie Han and Min Peng}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{Optimizing Discriminative Vision-Language Models for Efficient Multimodal Intent Recognition}}, booktitle = {{Companion Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025 - 2 May 2025}}, pages = {3063--3067}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3701716.3718369}, doi = {https://doi.org/10.1145/3701716.3718369} }