Shi, Z., Y. Shen, H. Jin, and X. Zhu. “Improving Zero-Shot Phrase Grounding via Reasoning on External Knowledge and Spatial Relations”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 2, June 2022, pp. 2253-61, doi:10.1609/aaai.v36i2.20123.