Multi-Level Multimodal Transformer Network for Multimodal Recipe Comprehension.

@inproceedings{liu-2020-multilevel, author = {Ao Liu and Shuai Yuan and Chenbin Zhang and Congjian Luo and Yaqing Liao and Kun Bai and Zenglin Xu}, editor = {Jimmy Huang and Yi Chang and Xueqi Cheng and Jaap Kamps and Vanessa Murdock and Ji-Rong Wen and Yiqun Liu}, title = {{Multi-Level Multimodal Transformer Network for Multimodal Recipe Comprehension}}, booktitle = {{Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, SIGIR 2020, Virtual Event, China, July 25-30, 2020}}, pages = {1781--1784}, publisher = {ACM}, year = {2020}, url = {https://doi.org/10.1145/3397271.3401247}, doi = {https://doi.org/10.1145/3397271.3401247} }