Survey on Artificial Intelligence Approaches for Visualization Data

PhD Qualifying Examination


Title: "Survey on Artificial Intelligence Approaches for Visualization 
Data"

by

Mr. Aoyu WU


Abstract:

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. This survey probes the underlying vision of formalizing 
visualizations as an emerging data format and review the recent advance in 
applying AI techniques to visualization data. I define visualization data 
as the digital representations of visualizations in computers and focus on 
visualizations in information visualization (e.g., charts and 
infographics). To contextualize the research field, I first present a set 
of common tasks that researchers apply to the visualization data. Then, I 
formalize the concept of visualization data by providing a comprehensive 
overview of its content formats. Critically, I review the AI approaches, 
particularly the feature representations of visualization data. Drawing 
upon the literature review, I discuss several important research questions 
surrounding why visualization data poses distinct challenges from existing 
data formats such as images and text, and how to tailor deep-learning 
models to visualization data.


Date:			Friday, 28 May 2021

Time:                  	4:00pm - 6:00pm

Zoom meeting: 
https://hkust.zoom.us/j/97718879677?pwd=MEZ4MzUxS0pBOXJ4UStXRkM1bk5TUT09

Committee Members:	Prof. Huamin Qu (Supervisor)
 			Dr. Dan Xu (Chairperson)
 			Prof. Chiew-Lan Tai
 			Prof. Nevin Zhang


**** ALL are Welcome ****