Pang, B., Li, Y., Li, J., Li, M., Cao, H., & Lu, C. (2021). TDAF: Top-Down Attention Framework for Vision Tasks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2384-2392. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16339