@inproceedings{song2022vidt,
    title={{ViDT}: An Efficient and Effective Fully Transformer-based Object Detector},
    author={Hwanjun Song and Deqing Sun and Sanghyuk Chun and Varun Jampani and Dongyoon Han and Byeongho Heo and Wonjae Kim and Ming-Hsuan Yang},
    year={2022},
    booktitle={International Conference on Learning Representations (ICLR)},
}