Yue et al. "Instruction-Augmented Multimodal Alignment for Image-Text and Element Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.
Markdown
[Yue et al. "Instruction-Augmented Multimodal Alignment for Image-Text and Element Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/yue2025cvprw-instructionaugmented/)
BibTeX
@inproceedings{yue2025cvprw-instructionaugmented,
title = {{Instruction-Augmented Multimodal Alignment for Image-Text and Element Matching}},
author = {Yue, Xinli and Sun, Jianhui and Lu, Junda and Yao, Liangchao and Xia, Fan and Wang, Tianyi and Rao, Fengyun and Lyu, Jing and Deng, Yuetang},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2025},
pages = {1379-1388},
url = {https://mlanthology.org/cvprw/2025/yue2025cvprw-instructionaugmented/}
}