GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

Open Webpage

Ding Jia, Jianyuan Guo, Kai Han, Han Wu, Chao Zhang, Chang Xu, Xinghao Chen

Published: 01 Jan 2024, Last Modified: 28 Sept 2024ICML 2024EveryoneRevisionsBibTeXCC BY-SA 4.0