Enhancing vision–language contrastive representation learning using domain knowledge

Xiaoyang Wei

doi:10.1016/j.cviu.2025.104403

Enhancing vision–language contrastive representation learning using domain knowledge

2025-06-10

0

OA

AI

DOI：10.1016/j.cviu.2025.104403

Original

Original request for help

Save

Abstract

En 中文

• Rich semantics can be developed in representation learning by leveraging. • The inter-data relationships can be modeled using external knowledge. • Additional cross-modal alignment leads to better visual understanding. • Fine-grained inter-data similarity can serve as soft targets for cross-modal alignment.

Keywords:

Visual representation

Knowledge graph

Vision–language contrastive learning

Enhancing vision–language contrastive representation learning using domain knowledge

Abstract

Journal

Organization