The following publications are possibly variants of this publication:
- Dynamic Grained Encoder for Vision TransformersLin Song, Songyang Zhang, Songtao Liu, Zeming Li, Xuming He 0001, Hongbin Sun 0001, Jian Sun 0001, Nanning Zheng 0001. nips 2021: 5770-5783 [doi]
- Text Compression-Aided Transformer EncodingZuchao Li, Zhuosheng Zhang 0001, Hai Zhao, Rui Wang 0015, Kehai Chen, Masao Utiyama, Eiichiro Sumita. pami, 44(7):3840-3857, 2022. [doi]
- Conditional Positional Encodings for Vision TransformersXiangxiang Chu, Zhi Tian, Bo Zhang 0046, Xinlong Wang, Chunhua Shen. iclr 2023: [doi]
- Geometric Transformer with Interatomic Positional EncodingYusong Wang, Shaoning Li, Tong Wang, Bin Shao, Nanning Zheng 0001, Tie-Yan Liu. nips 2023: [doi]