Chart question answering (CQA) is a newly proposed visual question answering (VQA) task where an algorithm must answer questions about data visualizations, e.g. bar charts, pie charts, and line graphs. CQA requires capabilities that natural-image VQA algorithms lack: fine-grained measurements, optical character recognition, and handling out-of-vocabulary words in both questions and answers. Without modifications, state-of-the-art VQA algorithms perform poorly on this task. Here, we propose a novel CQA algorithm called parallel recurrent fusion of image and language (PReFIL). PReFIL first learns bimodal embeddings by fusing question and image features and then intelligently aggregates these learned embeddings to answer the givenmore »
Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
-
-
At the historic Shelter Island Conference on the Foundations of Quantum Mechanics in 1947, Willis Lamb reported an unexpected feature in the fine structure of atomic hydrogen: a separation of the 2S1/2 and 2P1/2 states1. The observation of this separation, now known as the Lamb shift, marked an important event in the evolution of modern physics, inspiring others to develop the theory of quantum electrodynamics2–5. Quantum electrodynamics also describes antimatter, but it has only recently become possible to synthesize and trap atomic antimatter to probe its structure. Mirroring the historical development of quantum atomic physics in the twentieth century, modernmore »
Full Text Available