ML2MG-VLCR: A Multimodal LLM Guided Zero-shot Method for Visio-linguistic Compositional Reasoning with Autoregressive Generative Language Model.

@inproceedings{gong-2024-ml2mgvlcr, author = {Ziyu Gong and Chengcheng Mai and Yihua Huang}, 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 = {{ML2MG-VLCR: A Multimodal LLM Guided Zero-shot Method for Visio-linguistic Compositional Reasoning with Autoregressive Generative Language Model}}, booktitle = {{Proceedings of the 2024 International Conference on Multimedia Retrieval, ICMR 2024, Phuket, Thailand, June 10-14, 2024}}, pages = {842--850}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3652583.3658016}, doi = {https://doi.org/10.1145/3652583.3658016} }