Temporal-Visual Semantic Alignment: A Unified Architecture for Transferring Spatial Priors from Vision Models to Zero-Shot Temporal Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Xiangkai, Zhang, Han, Li, Wenzhong, Lu, Sanglu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!