@inproceedings{ma-etal-2026-response, title = "Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding", author = "Ma, Ke and Tang, Jiaqi and Guo, Bin and Han, Xueting and Xu, Ruonan and He, Qingfeng and Wang, Ziheng and Wang, Xu and Chen, Qifeng and Yu, Zhiwen and Liu, Yunhao", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2042/", pages = "44139--44153", ISBN = "979-8-89176-390-6" }