FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Tianyu, Liu, Tengxuan, Han, Qinghao, Dai, Guohao, Yan, Shengen, Yang, Huazhong, Ning, Xuefei, Wang, Yu
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence 68T45, 68T50 I.2.7; I.2.10
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2501.01986