@article{devicedepthandvisualconceptsaware, title = {DEVICE: DEpth and VIsual ConcEpts Aware Transformer for TextCaps}, author = {Dongsheng Xu and Qingbao Huang and Feng Shuang and Yi Cai}, year = {2023}, eprint = {2302.01540}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2302.01540v3}, }