Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du 0001, Jiaqi Li, Zhi Gao, Qing Li 0003. [inline-graphic not available: see fulltext]VideoAgent: A Memory-Augmented Multimodal Agent for Video Understanding. In Ales Leonardis, Elisa Ricci 0001, Stefan Roth 0001, Olga Russakovsky, Torsten Sattler, Gül Varol, editors, Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part XXII. Volume 15080 of Lecture Notes in Computer Science, pages 75-92, Springer, 2024. [doi]
@inproceedings{FanMWDLGL24,
title = {[inline-graphic not available: see fulltext]VideoAgent: A Memory-Augmented Multimodal Agent for Video Understanding},
author = {Yue Fan and Xiaojian Ma and Rujie Wu and Yuntao Du 0001 and Jiaqi Li and Zhi Gao and Qing Li 0003},
year = {2024},
doi = {10.1007/978-3-031-72670-5_5},
url = {https://doi.org/10.1007/978-3-031-72670-5_5},
researchr = {https://researchr.org/publication/FanMWDLGL24},
cites = {0},
citedby = {0},
pages = {75-92},
booktitle = {Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part XXII},
editor = {Ales Leonardis and Elisa Ricci 0001 and Stefan Roth 0001 and Olga Russakovsky and Torsten Sattler and Gül Varol},
volume = {15080},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-031-72670-5},
}