Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev, Cordelia Schmid. TubeDETR: Spatio-Temporal Video Grounding with Transformers. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. pages 16421-16432, IEEE, 2022. [doi]
@inproceedings{YangMSLS22,
title = {TubeDETR: Spatio-Temporal Video Grounding with Transformers},
author = {Antoine Yang and Antoine Miech and Josef Sivic and Ivan Laptev and Cordelia Schmid},
year = {2022},
doi = {10.1109/CVPR52688.2022.01595},
url = {https://doi.org/10.1109/CVPR52688.2022.01595},
researchr = {https://researchr.org/publication/YangMSLS22},
cites = {0},
citedby = {0},
pages = {16421-16432},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022},
publisher = {IEEE},
isbn = {978-1-6654-6946-3},
}