A Pooling Approach to Modelling Spatial Relations for Image Retrieval and Annotation

Abstract

Over the last two decades we have witnessed strong progress on modeling visual object classes, scenes and attributes that have significantly contributed to automated image understanding. On the other hand, surprisingly little progress has been made on incorporating a spatial representation and reasoning in the inference process. In this work, we propose a pooling interpretation of spatial relations and show how it improves image retrieval and annotations tasks involving spatial language. Due to the complexity of the spatial language, we argue for a learning-based approach that acquires a representation of spatial relations by learning parameters of the pooling operator. We show improvements on previous work on two datasets and two different tasks as well as provide additional insights on a new dataset with an explicit focus on spatial relations.

References in corpus (3)

• Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
• Explain Images with Multimodal Recurrent Neural Networks
• A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input

Cited by in corpus (5)

• A simple neural network module for relational reasoning
• Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
• Hard to Cheat: A Turing Test based on Answering Questions about Images
• Inferring spatial relations from textual descriptions of images
• Contextual Media Retrieval Using Natural Language Queries