SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Liangtao, Liu, Ting, Hu, Xiantao, Hu, Yue, Yin, Quanjun, Hong, Richang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!