arrow
Return

SALA: Semantic alignment and localization alignment for visual grounding

delete2025-08-18
delete0
PRE
AI
H
Hongbing Li
X
Xinran Wang
L
Linyi Yang
Q
Qi Li
B
Bo Xiao *
DOI:10.1016/j.neucom.2025.131265delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Combining semantic alignment and localization alignment (SALA) to solve two prevalent issues in visual grounding. • Semantic alignment captures consistent semantics across and within modalities through coarse-grained guidance. • Localization alignment enhances foreground while suppressing background through fine-grained supervision. • Experimental results demonstrate SALA’s superior grounding performance.
Keywords:
semantic alignment
localization alignment
visual grounding
multimodal learning
fine-grained supervision

Journal

Neurocomputing cover
Neurocomputing
IF:
6.5
Papers:
2.5W
Citations:
6.5W

Organization

No organization information available