Islam, M. M., Gladstone, A., & Iqbal, T. (2023). PATRON: Perspective-Aware Multitask Model for Referring Expression Grounding Using Embodied Multimodal Cues. Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 971–979. https://doi.org/10.1609/aaai.v37i1.25177