Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images

Abstract

We address a question answering task on real-world images that is set up as a Visual Turing Test. By combining latest advances in image representation and natural language processing, we propose Neural-Image-QA, an end-to-end formulation to this problem for which all parts are trained jointly. In contrast to previous efforts, we are facing a multi-modal problem where the language output (answer) is conditioned on visual and natural language input (image and question). Our approach Neural-Image-QA doubles the performance of the previous best approach on this problem. We provide additional insights into the problem by analyzing how much information is contained only in the language part for which we provide a new human baseline. To study human consensus, which is related to the ambiguities inherent in this challenging task, we propose two novel metrics and collect additional answers which extends the original DAQUAR dataset to DAQUAR-Consensus.

DOI: 10.1109/ICCV.2015.9

Extracted Key Phrases

14 Figures and Tables

Showing 1-10 of 37 references
Showing 1-10 of 125 extracted citations
050100201520162017
Citations per Year

165 Citations

Semantic Scholar estimates that this publication has received between 133 and 211 citations based on the available data.

See our FAQ for additional information.