Jiajun Deng, Zhengyuan Yang, Tianlang Chen, Wengang Zhou, Houqiang Li. TransVG: End-to-End Visual Grounding with Transformers. In 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021. pages 1749-1759, IEEE, 2021. [doi]
@inproceedings{DengYCZL21,
title = {TransVG: End-to-End Visual Grounding with Transformers},
author = {Jiajun Deng and Zhengyuan Yang and Tianlang Chen and Wengang Zhou and Houqiang Li},
year = {2021},
doi = {10.1109/ICCV48922.2021.00179},
url = {https://doi.org/10.1109/ICCV48922.2021.00179},
researchr = {https://researchr.org/publication/DengYCZL21},
cites = {0},
citedby = {0},
pages = {1749-1759},
booktitle = {2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021},
publisher = {IEEE},
isbn = {978-1-6654-2812-5},
}