Rui Su, Qian Yu, Dong Xu 0001. STVGBert: A Visual-linguistic Transformer based Framework for Spatio-temporal Video Grounding. In 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021. pages 1513-1522, IEEE, 2021. [doi]
@inproceedings{SuY021,
title = {STVGBert: A Visual-linguistic Transformer based Framework for Spatio-temporal Video Grounding},
author = {Rui Su and Qian Yu and Dong Xu 0001},
year = {2021},
doi = {10.1109/ICCV48922.2021.00156},
url = {https://doi.org/10.1109/ICCV48922.2021.00156},
researchr = {https://researchr.org/publication/SuY021},
cites = {0},
citedby = {0},
pages = {1513-1522},
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},
}