@inproceedings{ni2021m,
author = {Ni, Minheng and Huang, Haoyang and Su, Lin and Cui, Edward and Bharti, Taroon and Wang, Lijuan and Gao, Jianfeng and Zhang, Dongdong and Duan, Nan},
title = {M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training},
booktitle = {CVPR 2021},
year = {2021},
month = {June},
abstract = {We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts expressed in different languages into a common semantic space. In addition, to explicitly encourage fine-grained alignment between images and non-English languages, we also propose Multimodal Code-switched Training (MCT) to combine monolingual pre-training and multimodal pre-training via a code-switch strategy. Experiments are performed on the multilingual image retrieval task across two benchmark datasets, including MSCOCO and Multi30K. M3P can achieve comparable results for English and new state-of-the-art results for non-English languages.},
url = {http://approjects.co.za/?big=en-us/research/publication/m3p-learning-universal-representations-via-multitask-multilingual-multimodal-pre-training/},
}