Papers › Answering Questions about Data Visualizations using Efficient Bimodal Fusion

Answering Questions about Data Visualizations using Efficient Bimodal Fusion

5 Aug 2019arXiv:1908.01801archive 2025-07-28

Kushal Kafle, Robik Shrestha, Brian Price, Scott Cohen, Christopher Kanan

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 given question. Despite its simplicity, PReFIL greatly surpasses state-of-the art systems and human baselines on both the FigureQA and DVQA datasets. Additionally, we demonstrate that PReFIL can be used to reconstruct tables by asking a series of questions about a chart.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

kushalkafle/PREFIL officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Chart Question AnsweringOptical Character RecognitionOptical Character Recognition (OCR)Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering (VQA) DVQA test-familiar PReFIL (Oracle OCR) 1:1 Accuracy 96.37 #1 of 1 Archive leaderboard report
Visual Question Answering (VQA) FigureQA - test 1 PReFIL 1:1 Accuracy 94.88 #1 of 3 Archive leaderboard report
Visual Question Answering (VQA) PlotQA-D1 PReFIL 1:1 Accuracy 57.91 #3 of 4 Archive leaderboard report
Visual Question Answering (VQA) PlotQA-D2 PReFIL 1:1 Accuracy 10.37 #4 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections