@inproceedings{wang-etal-2025-long, title = "From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding", author = "Wang, Xiangfeng and Li, Xiao and Wei, Yadong and Songxueyu and Song, Yang and Xiaxiaoqiang and Zeng, Fangrui and Chen, Zaiyi and Liuliu and Xu, Gu and Xu, Tong", editor = "Potdar, Saloni and Rojas-Barahona, Lina and Montella, Sebastien", booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track", month = nov, year = "2025", address = "Suzhou (China)", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.185/", pages = "2764--2781", ISBN = "979-8-89176-333-3" }