@article{d83aa578b1ce410e9d41dd543f7dea92,
title = "Instruction-ViT: Multi-modal prompts for instruction learning in vision transformer",
keywords = "Instruction learning, Multi-modal information fusion, Multi-modal prompt, Vision transformer",
author = "Zhenxiang Xiao and Yuzhong Chen and Junjie Yao and Lu Zhang and Zhengliang Liu and Zihao Wu and Xiaowei Yu and Yi Pan and Lin Zhao and Chong Ma and Xinyu Liu and Wei Liu and Xiang Li and Yixuan Yuan and Dinggang Shen and Dajiang Zhu and Dezhong Yao and Tianming Liu and Xi Jiang",
note = "Publisher Copyright: {\textcopyright} 2023 Elsevier B.V.",
year = "2024",
month = apr,
doi = "10.1016/j.inffus.2023.102204",
language = "English",
volume = "104",
journal = "Information Fusion",
issn = "1566-2535",
}