Zhiqi Li, Wenhai Wang, Hongyang Li, Enze Xie, Chonghao Sima, Tong Lu, Yu Qiao 0001, Jifeng Dai. BEVFormer: Learning Bird's-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers. 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 IX. Volume 13669 of Lecture Notes in Computer Science, pages 1-18, Springer, 2022. [doi]
@inproceedings{LiWLXSLQD22, title = {BEVFormer: Learning Bird's-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers}, author = {Zhiqi Li and Wenhai Wang and Hongyang Li and Enze Xie and Chonghao Sima and Tong Lu and Yu Qiao 0001 and Jifeng Dai}, year = {2022}, doi = {10.1007/978-3-031-20077-9_1}, url = {https://doi.org/10.1007/978-3-031-20077-9_1}, researchr = {https://researchr.org/publication/LiWLXSLQD22}, cites = {0}, citedby = {0}, pages = {1-18}, booktitle = {Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part IX}, editor = {Shai Avidan and Gabriel J. Brostow and Moustapha Cissé and Giovanni Maria Farinella and Tal Hassner}, volume = {13669}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, isbn = {978-3-031-20077-9}, }