Visual Semantic Parsing: From Images to Abstract Meaning Representation

TL;DR

This paper introduces a novel approach to visual scene understanding by converting images into Abstract Meaning Representation graphs, leveraging NLP techniques to capture high-level semantics and unify multiple descriptions.

Contribution

It adapts a text-based AMR parser for images, creating linguistically informed semantic graphs that go beyond traditional scene graphs, enabling richer scene understanding.

Findings

Successfully repurposed a text-to-AMR parser for images

Generated unified meta-AMR graphs from multiple descriptions

Demonstrated potential for improved scene understanding

Abstract

The success of scene graphs for visual scene understanding has brought attention to the benefits of abstracting a visual input (e.g., image) into a structured representation, where entities (people and objects) are nodes connected by edges specifying their relations. Building these representations, however, requires expensive manual annotation in the form of images paired with their scene graphs or frames. These formalisms remain limited in the nature of entities and relations they can capture. In this paper, we propose to leverage a widely-used meaning representation in the field of natural language processing, the Abstract Meaning Representation (AMR), to address these shortcomings. Compared to scene graphs, which largely emphasize spatial relationships, our visual AMR graphs are more linguistically informed, with a focus on higher-level semantic concepts extrapolated from visual input. Moreover, they allow us to generate meta-AMR graphs to unify information contained in multiple image descriptions under one representation. Through extensive experimentation and analysis, we demonstrate that we can re-purpose an existing text-to-AMR parser to parse images into AMRs. Our findings point to important future research directions for improved scene understanding.