Dong Xie, Linhu Liu, Shengjun Zhang, Jiang Tian. A Unified Multi-modal Structure for Retrieving Tracked Vehicles through Natural Language Descriptions. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Workshops, Vancouver, BC, Canada, June 17-24, 2023. pages 5419-5427, IEEE, 2023. [doi]
@inproceedings{XieLZT23,
title = {A Unified Multi-modal Structure for Retrieving Tracked Vehicles through Natural Language Descriptions},
author = {Dong Xie and Linhu Liu and Shengjun Zhang and Jiang Tian},
year = {2023},
doi = {10.1109/CVPRW59228.2023.00572},
url = {https://doi.org/10.1109/CVPRW59228.2023.00572},
researchr = {https://researchr.org/publication/XieLZT23},
cites = {0},
citedby = {0},
pages = {5419-5427},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Workshops, Vancouver, BC, Canada, June 17-24, 2023},
publisher = {IEEE},
isbn = {979-8-3503-0249-3},
}