@inproceedings{77573086d99443a1ae31b35c61a2cd89,
title = "A model-based approach to visual reasoning on CNLVR dataset",
abstract = "Visual Reasoning requires an understanding of complex compositional images and common-sense reasoning about sets of objects, quantities, comparisons, and spatial relationships. This paper presents a semantic parser that combines Computer Vision (CV), Natural Language Processing (NLP) and Knowledge Representation & Reasoning (KRR) to automatically solve visual reasoning problems from the Cornell Natural Language Visual Reasoning (CNLVR) dataset. Unlike the data-driven approaches applied to the same dataset, our system does not require any training but is guided by the knowledge base that is manually constructed. The system demonstrates robust overall performance which is also time and space efficient. Our system achieves 87.3% accuracy, which is 17.6% higher over the state-of-the-art method on raw image representations.",
author = "Shailaja Sampat and Joohyung Lee",
year = "2018",
language = "English (US)",
series = "Principles of Knowledge Representation and Reasoning: Proceedings of the 16th International Conference, KR 2018",
publisher = "AAAI press",
pages = "62--66",
editor = "Michael Thielscher and Francesca Toni and Frank Wolter",
booktitle = "Principles of Knowledge Representation and Reasoning",
note = "16th International Conference on the Principles of Knowledge Representation and Reasoning, KR 2018 ; Conference date: 30-10-2018 Through 02-11-2018",
}