@inproceedings{ding-etal-2024-learn, title = "Can We Learn Question, Answer, and Distractors All from an Image? A New Task for Multiple-choice Visual Question Answering", author = "Ding, Wenjian and Zhang, Yao and Wang, Jun and Jatowt, Adam and Yang, Zhenglu", editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.lrec-main.254/", pages = "2852--2863" }