Modeling Relationships in Referential Expressions with Compositional Modular Networks
Preprint
Abstract
People often refer to entities in an image in terms of their relationships with other entities. For example, "the black cat sitting under the table" refers to both a "black cat" entity and its relationship with another "table" entity. Understanding these relationships is essential for interpreting and grounding such natural language expressions. Most prior work focuses on either grounding entire referential expressions holistically to one region, or localizing relationships based on a fixed set of categories. In this paper we instead present a modular deep architecture capable of analyzing referential expressions into their component parts, identifying entities and relationships mentioned in the input expression and grounding them all in the scene. We call this approach Compositional Modular Networks (CMNs): a novel architecture that learns linguistic analysis and visual inference end-to-end. Our approach is built around two types of neural modules that inspect local regions and pairwise interactions between regions. We evaluate CMNs on multiple referential expression datasets, outperforming state-of-the-art approaches on all tasks.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image AnnotationsInternational Journal of Computer Vision, 2017
- Visual7W: Grounded Question Answering in Images2016
- Jointly Learning to Parse and Perceive: Connecting Natural Language to the Physical WorldTransactions of the Association for Computational Linguistics, 2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Fast and Accurate Shift-Reduce Constituent Parsing