@inproceedings{ijcai2024p68, title = {CoAtFormer: Vision Transformer with Composite Attention}, author = {Chang, Zhiyong and Yin, Mingjun and Wang, Yan}, booktitle = {Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, {IJCAI-24}}, publisher = {International Joint Conferences on Artificial Intelligence Organization}, editor = {Kate Larson}, pages = {614--622}, year = {2024}, month = {8}, note = {Main Track}, doi = {10.24963/ijcai.2024/68}, url = {https://doi.org/10.24963/ijcai.2024/68}, }