Answering Visual-Relational Queries in Web-Extracted Knowledge Graphs
This addresses the challenge of integrating visual data into knowledge graphs for applications like semantic search and zero-shot learning, representing an incremental advancement in multi-modal AI.
The paper tackles the problem of answering visual-relational queries in knowledge graphs by introducing ImageGraph, a dataset with 1,330 relation types and 829,931 images, and proposes methods combining convolutional networks and knowledge graph embeddings to efficiently and accurately handle tasks like relation prediction and multi-relational image retrieval.
A visual-relational knowledge graph (KG) is a multi-relational graph whose entities are associated with images. We explore novel machine learning approaches for answering visual-relational queries in web-extracted knowledge graphs. To this end, we have created ImageGraph, a KG with 1,330 relation types, 14,870 entities, and 829,931 images crawled from the web. With visual-relational KGs such as ImageGraph one can introduce novel probabilistic query types in which images are treated as first-class citizens. Both the prediction of relations between unseen images as well as multi-relational image retrieval can be expressed with specific families of visual-relational queries. We introduce novel combinations of convolutional networks and knowledge graph embedding methods to answer such queries. We also explore a zero-shot learning scenario where an image of an entirely new entity is linked with multiple relations to entities of an existing KG. The resulting multi-relational grounding of unseen entity images into a knowledge graph serves as a semantic entity representation. We conduct experiments to demonstrate that the proposed methods can answer these visual-relational queries efficiently and accurately.