Shi, Zhan, Yilin Shen, Hongxia Jin, and Xiaodan Zhu. 2022. “Improving Zero-Shot Phrase Grounding via Reasoning on External Knowledge and Spatial Relations”. Proceedings of the AAAI Conference on Artificial Intelligence 36 (2):2253-61. https://doi.org/10.1609/aaai.v36i2.20123.