@article{unicodervlauniversalencoderforvision, title = {Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training}, author = {Gen Li and Nan Duan and Yuejian Fang and Ming Gong and Daxin Jiang and Ming Zhou}, year = {2019}, eprint = {1908.06066}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1908.06066v3}, }