[1]
Islam, M.M. et al. 2023. PATRON: Perspective-Aware Multitask Model for Referring Expression Grounding Using Embodied Multimodal Cues. Proceedings of the AAAI Conference on Artificial Intelligence. 37, 1 (Jun. 2023), 971–979. DOI:https://doi.org/10.1609/aaai.v37i1.25177.