Paper Info
Title
Synthetically Trained Icon Proposals for Parsing and Summarizing Infographics.
Abstract
Widely used in news, business, and educational media, infographics are handcrafted to effectively communicate messages about complex and often abstract topics including `ways to conserve the environmentu0027 and `understanding the financial crisisu0027. Composed of stylistically and semantically diverse visual and textual elements, infographics pose new challenges for computer vision. While automatic text extraction works well on infographics, computer vision approaches trained on natural images fail to identify the stand-alone visual elements in infographics, or `iconsu0027. To bridge this representation gap, we propose a synthetic data generation strategy: we augment background patches in infographics from our Visually29K dataset with Internet-scraped icons which we use as training data for an icon proposal mechanism. On a test set of 1K annotated infographics, icons are located with 38% precision and 34% recall (the best model trained with natural images achieves 14% precision and 7% recall). Combining our icon proposals with icon classification and text extraction, we present a multi-modal summarization application. Our application takes an infographic as input and automatically produces text tags and visual hashtags that are textually and visually representative of the infographicu0027s topics respectively.
Year
Venue
Field
2018
arXiv: Computer Vision and Pattern Recognition
Training set,Automatic summarization,Synthetic data generation,Icon,Infographic,Computer science,Natural language processing,Artificial intelligence,Parsing,Recall,Machine learning,Test set
DocType
Volume
Citations 
Journal
abs/1807.10441
1
PageRank 
References 
Authors
0.35
0
9
Name
Order
Citations
PageRank
Spandan Madan1282.05
Zoya Gavrilov228716.20
Matthew Tancik3144.75
Adrià Recasens4746.55
Kimberli Zhong510.69
Sami Alsheikh610.35
Hanspeter Pfister75933340.59
Aude Oliva85121298.19
Frédo Durand98625414.94