@inproceedings{chowdhury-etal-2025-towards, title = "Towards Multilingual spoken Visual Question Answering system using Cross-Attention", author = "Chowdhury, Amartya Roy and Rajkhowa, Tonmoy and Sharma, Sanjeev", editor = "Rambow, Owen and Wanner, Leo and Apidianaki, Marianna and Al-Khalifa, Hend and Eugenio, Barbara Di and Schockaert, Steven", booktitle = "Proceedings of the 31st International Conference on Computational Linguistics", month = jan, year = "2025", address = "Abu Dhabi, UAE", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2025.coling-main.615/", pages = "9165--9175" }