@inproceedings{referringtransformeraonestepapproachto, title = {Referring Transformer: A One-step Approach to Multi-task Visual Grounding}, author = {Muchen Li and Leonid Sigal}, year = {2021}, booktitle = {NeurIPS 2021 12}, eprint = {2106.03089}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2106.03089v2}, }