@article{scheduledsamplinginvisionlanguage, title = {Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network}, author = {Yehao Li and Yingwei Pan and Ting Yao and Jingwen Chen and Tao Mei}, year = {2021}, eprint = {2101.11562}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2101.11562v1}, }