Uni-MDTrack: Learning Decoupled Memory and Dynamic States for Parameter-Efficient Visual Tracking in All Modality

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cai, Wenrui, Lu, Zhenyi, Li, Yuzhe, Feng, Yongchao, Zhang, Jinqing, Liu, Qingjie, Wang, Yunhong
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.14452