Scalable algorithms for scholarly figure mining and semantics

Choudhury, Sagnik Ray; Wang, Shuting; Giles, C. Lee

doi:10.1145/2928294.2928305

Cited by 18 publications

(29 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While we did not directly compare our text role classifier with other approaches, we obtain a F1-score of 98%. This result is higher than the 92% F1-score reported by Choudhury et al [CWG16] using different features and a smaller data set (165 charts, 4,363 boxes). Our mark type classification approach exhibits superior performance to ReVision's classifier (F1-scores 94% vs. 80%) on their corpus.…”

Section: Discussioncontrasting

confidence: 68%

See 1 more Smart Citation

Reverse‐Engineering Visualizations: Recovering Visual Encodings from Chart Images

Poco

Heer

2017

Computer Graphics Forum

156

145

View full text Add to dashboard Cite

We investigate how to automatically recover visual encodings from a chart image, primarily using inferred text elements. We contribute an end‐to‐end pipeline which takes a bitmap image as input and returns a visual encoding specification as output. We present a text analysis pipeline which detects text elements in a chart, classifies their role (e.g., chart title, x‐axis label, y‐axis title, etc.), and recovers the text content using optical character recognition. We also train a Convolutional Neural Network for mark type classification. Using the identified text elements and graphical mark type, we can then infer the encoding specification of an input chart image. We evaluate our techniques on three chart corpora: a set of automatically labeled charts generated using Vega, charts from the Quartz news website, and charts extracted from academic papers. We demonstrate accurate automatic inference of text elements, mark types, and chart specifications across a variety of input chart types.

show abstract

Section: Discussioncontrasting

confidence: 68%

“…In DiagramFlyer, Chen et al [CCA15] use feature vectors based only on text bounding boxes. Choudhury et al [CWG16] use text bounding boxes and also text content. We follow a similar approach, but do not incorporate text content, as it may propagate OCR errors.…”

Section: Miles/gallon Vs Horsepowermentioning

confidence: 99%

Reverse‐Engineering Visualizations: Recovering Visual Encodings from Chart Images

Poco

Heer

2017

Computer Graphics Forum

156

145

View full text Add to dashboard Cite

show abstract

“…Thus, we discuss feature engineering and feature learning approaches used to extract visualization features. [11], [47], [54], [66] element positions or regions [44], [46], [53], [54], [67] element styles [46] parameters [1], [2] communicative signals [68] design rules [30], [36] statistical models [3], [66], [69], [70] statistics [31], [32], [64], [71], [72] one-hot vector [73] Feature Learning convolutional neural network [12], [13], [40], [44], [50], [53], [69], [74]- [77], [77]- [87] autoencoder [6], [77] autoencoder [9], [88] embedding models [3], [73] autoencoder [89]…”

Section: Representationmentioning

confidence: 99%

“…For our discussion, we classify existing approaches according to the feature space, including graphics, program, text, and underlying data (Table 1). It should be noted that some papers use multiple features for different tasks [44], [53] or use hybrids by feature fusion for improving performances [54], [66], [69]. In the following text, we describe each category in detail.…”

Section: Feature Engineering and Feature Learningmentioning

confidence: 99%

AI4VIS: Survey on Artificial Intelligence Approaches for Data Visualization

Wang

Shu

et al. 2021

Preprint

View full text Add to dashboard Cite

Visualizations themselves have become a data format. Akin to other data formats such as text and images, visualizations are increasingly created, stored, shared, and (re-)used with artificial intelligence (AI) techniques. In this survey, we probe the underlying vision of formalizing visualizations as an emerging data format and review the recent advance in applying AI techniques to visualization data. We define visualization data as the digital representations of visualizations in computers and focus on visualizations in information visualization and visual analytic. We build our survey upon a corpus spanning ten different fields in computer science with an eye toward identifying important common interests. Our resulting taxonomy is organized around WHAT is visualization data and its representation, WHY and HOW to apply AI to visualization data. We highlight a set of common tasks that researchers apply to the visualization data and present a detailed discussion of AI approaches developed to accomplish those tasks. Drawing upon our literature review, we discuss several important research questions surrounding the management and exploitation of visualization data, as well as the role of AI in support of those processes. We make the list of surveyed papers and related material available online at ai4vis.github.io.

show abstract

“…It usually combines text detection, optical character recognition (OCR), keypoint analysis, and other advanced computer vision methods [ 41 ]. Neural networks have shown surprising performance at this task [ 42 , 43 ]. Depending on the type of graph, specialized data extraction techniques exist (e.g., bar charts or pie charts use different methods; see [ 44 ]).…”

Section: Literature Reviewmentioning

confidence: 99%

Graphical integrity issues in open access publications: Detection and patterns of proportional ink violations

2021

View full text Add to dashboard Cite

Academic graphs are essential for communicating complex scientific ideas and results. To ensure that these graphs truthfully reflect underlying data and relationships, visualization researchers have proposed several principles to guide the graph creation process. However, the extent of violations of these principles in academic publications is unknown. In this work, we develop a deep learning-based method to accurately measure violations of the proportional ink principle (AUC = 0.917), which states that the size of shaded areas in graphs should be consistent with their corresponding quantities. We apply our method to analyze a large sample of bar charts contained in 300K figures from open access publications. Our results estimate that 5% of bar charts contain proportional ink violations. Further analysis reveals that these graphical integrity issues are significantly more prevalent in some research fields, such as psychology and computer science, and some regions of the globe. Additionally, we find no temporal and seniority trends in violations. Finally, apart from openly releasing our large annotated dataset and method, we discuss how computational research integrity could be part of peer-review and the publication processes.

show abstract

Scalable algorithms for scholarly figure mining and semantics

Cited by 18 publications

References 12 publications

Reverse‐Engineering Visualizations: Recovering Visual Encodings from Chart Images

Reverse‐Engineering Visualizations: Recovering Visual Encodings from Chart Images

AI4VIS: Survey on Artificial Intelligence Approaches for Data Visualization

Graphical integrity issues in open access publications: Detection and patterns of proportional ink violations

Contact Info

Product

Resources

About