Mamba-VMR: Multimodal Query Augmentation via Generated Videos for Precise Temporal Grounding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Yunzhuo, Liu, Xinyue, Li, Yanyang, Wu, Nanding, Xu, Yifang, Zong, Linlin, Zhang, Xianchao, Liang, Wenxin
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.22121