Li Gao, Dong Nie, Bo Li, Xiaofeng Ren. Doubly-Fused ViT: Fuse Information from Vision Transformer Doubly with Local Representation. In Shai Avidan, Gabriel J. Brostow, Moustapha Cissé, Giovanni Maria Farinella, Tal Hassner, editors, Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXIII. Volume 13683 of Lecture Notes in Computer Science, pages 744-761, Springer, 2022. [doi]
@inproceedings{GaoNLR22,
title = {Doubly-Fused ViT: Fuse Information from Vision Transformer Doubly with Local Representation},
author = {Li Gao and Dong Nie and Bo Li and Xiaofeng Ren},
year = {2022},
doi = {10.1007/978-3-031-20050-2_43},
url = {https://doi.org/10.1007/978-3-031-20050-2_43},
researchr = {https://researchr.org/publication/GaoNLR22},
cites = {0},
citedby = {0},
pages = {744-761},
booktitle = {Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXIII},
editor = {Shai Avidan and Gabriel J. Brostow and Moustapha Cissé and Giovanni Maria Farinella and Tal Hassner},
volume = {13683},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-031-20050-2},
}