Visualsem: A High-quality Knowledge Graph For Vision And Language

Abstract

An exciting frontier in natural language understanding (NLU) and generation (NLG) calls for (vision-and-) language models that can efficiently access external structured knowledge repositories. However, many existing knowledge bases only cover limited domains, or suffer from noisy data, and most of all are typically hard to integrate into neural language pipelines. To fill this gap, we release VisualSem: a high-quality knowledge graph (KG) which includes nodes with multilingual glosses, multiple illustrative images, and visually relevant relations. We also release a neural multi-modal retrieval model that can use images or sentences as inputs and retrieves entities in the KG. This multi-modal retrieval model can be integrated into any (neural network) model pipeline. We encourage the research community to use VisualSem for data augmentation and/or as a source of grounding, among other possible uses. VisualSem as well as the multi-modal retrieval models are publicly available and can be

Stats

• citations24
• S2 citations—
• github stars89
• HF likes0
• heat score14.39
• arxiv keyalberts2020visualsem

Related papers

• Answering Visual-relational Queries In Web-extracted Knowledge Graphs (2017)0.00
• Cross-modal Retrieval For Knowledge-based Visual Question Answering (2024)7.81
• Remote Sensing Retrieval-augmented Generation: Bridging Remote Sensing Imagery And Comprehensive Knowledge With A Multi-modal Dataset And Retrieval-augmented Generation Model (2025)2.26
• REVEAL: Retrieval-augmented Visual-language Pre-training With Multi-source Multimodal Knowledge Memory (2022)13.65
• Multi-modal Retrieval Using Graph Neural Networks (2020)0.00
• OMGM: Orchestrate Multiple Granularities And Modalities For Efficient Multimodal Retrieval (2025)0.00
• Beyond Visual Semantics: Exploring The Role Of Scene Text In Image Understanding (2019)9.59
• Seeing Through Words: Controlling Visual Retrieval Quality With Language Models (2026)3.80