@inproceedings{he-etal-2026-beyond, title = "Beyond Referring Expressions: Scenario Comprehension Visual Grounding", author = "He, Ruozhen and Shah, Nisarg A and Dong, Qihua and Xiao, Zilin and Koo, Jaywon and Ordonez, Vicente", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.1788/", pages = "40742--40762", ISBN = "979-8-89176-459-0" }