Bin Huang, Xin Wang 0019, Hong Chen, Zihan Song, Wenwu Zhu 0001. VTimeLLM: Empower LLM to Grasp Video Moments. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. pages 14271-14280, IEEE, 2024. [doi]
@inproceedings{Huang0CS024,
title = {VTimeLLM: Empower LLM to Grasp Video Moments},
author = {Bin Huang and Xin Wang 0019 and Hong Chen and Zihan Song and Wenwu Zhu 0001},
year = {2024},
doi = {10.1109/CVPR52733.2024.01353},
url = {https://doi.org/10.1109/CVPR52733.2024.01353},
researchr = {https://researchr.org/publication/Huang0CS024},
cites = {0},
citedby = {0},
pages = {14271-14280},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024},
publisher = {IEEE},
isbn = {979-8-3503-5300-6},
}