Exploring Visual Information Flows in Infographics

The ACM Conference on Human Factors in Computing Systems (Proceedings of CHI 2020)

Min Lu1    Chufeng Wang1    Joel Lanir2    Nanxuan Zhao3,4    Hanspeter Pfister3    Daniel Cohen-Or1,5    Hui Huang1*

1Shenzhen University    2University of Haifa    3Harvard University    4City University of Hong Kong    5Tel Aviv University

Figure 1. Examples from the analysis of our infographic repository, with the extracted visual information flows shown on the right of each infographic.
Figure 2. Infographics Model: (a) an infographic example. (b) separating the artistic decorations, the visual information flow of the infographic connects the visual groups of data elements in narrative order, hinted by explicit graphics (e.g., digits here) and implicit Gestalt principles.


Infographics are engaging visual representations that tell an informative story using a fusion of data and graphical elements. The large variety of infographic design poses a challenge for their high-level analysis. We use the concept of Visual Information Flow (VIF), which is the underlying semantic structure that links graphical elements to convey the information and story to the user. To explore VIF, we collected a repository of over 13K infographics. We use a deep neural network to identify visual elements related to information, agnostic to their various artistic appearances. We construct the VIF by automatically chaining these visual elements together based on Gestalt principles. Using this analysis, we characterize the VIF design space by a taxonomy of 12 different design patterns. Exploring in a real-world infographic dataset, we discuss the design space and potentials of VIF in light of this taxonomy.

Figure 3. VIF Construction Pipeline: using manually labeled infographics as training data, we use a deep neural network to detect visual data elements, leaving aside artistic elements. We run multiple passes to trace and score different information flows based on Gestalt principles, and then we pick the best one.

Figure 4. Output of Element Extraction: data elements are extracted at high precision (a, b), with (c) false positives, e.g., the home button, and (d) some misses, e.g., ‘$’ icon.
Figure 5. Flow Construction: Using the detected data elements, we first trace the flow backbone and then associate nearby elements into visual groups.

Figure 9. 12 VIF Design Patterns: six main patterns highlighted in t-SNE plot and six more patterns with variance in backbone and content placement.

Data & Code

Note that the DATA and CODE are free for Research and Education Use ONLY. 

Please cite our paper (add the bibtex below) if you use any part of our ALGORITHM, CODE, DATA or RESULTS in any publication.

Code: https://github.com/wangchufeng/Narrative-flow-web


We thank the reviewers for their valuable comments and Freepik, Shutterstock for high-quality infographic designs. This work is supported in parts by NSFC (61761146002, 61602310, 61802265), Guangdong Provincial Natural Science Foundation (2018A030310426), Shenzhen Innovation Program (JCYJ20170302154106666), LHTD (20170003), the National Engineering Laboratory for Big Data System Computing Technology, and the Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ).

title = {
Exploring Visual Information Flows in Infographics},
author = {Min Lu and Chufeng Wang and Joel Lanir and Nanxuan Zhao and Hanspeter Pfister and Daniel Cohen-Or and Hui Huang},
journal = {Proceedings of CHI},
pages = {1--12},  
year = {2020},

Downloads (faster for people in China)

Downloads (faster for people in other places)