On April 12th, 2024, Top Computer Science Journal ACM Computing Surveys (CSUR for short) has unveiled study titled " From Detection to Application: Recent Advances in Understanding Scientific Tables and Figures." This systematic and comprehensive literature review, borne out of a year-long intensive endeavor (Submitted on March 14th, 2023, accepted on April 2nd, 2024), introduces the research framework and the whole pipeline for understanding tables and figures in academic papers, including detection, structural analysis, interpretation, and application. 

Notably, ACM Computing Surveys is prestigious and peer-reviewed quarterly scientific journal published by the Association for Computing Machinery (ACM). The journal was established in 1969, it has received great attention and unanimous recognition from the world's top scholars and enjoys outstanding influence in the international academic community. According to the Journal Citation Reports, CSUR has a 2022 impact factor of 16.6, ranking third among the 111 journals in the field of computer science theory and methods that participated in the ranking.
 

DIS faculty Dr. Haihua Chen as the second author, collaborated with a dedicated team of researchers, including Miss. Jiani Huang (master student), Dr. Fengchang Yu (Postdoctoral researcher), and Dr. Wei Lu (Professor) from School of Information Management at Wuhan University. Together, this team has dedicated time and energy into unraveling the complexities of understanding, analyzing, and applications of scientific ta

bles and figures. 

This survey delivered a thorough analysis of benchmark datasets, recent techniques, and their pros and cons. Additionally, a quantitative analysis of the effectiveness of different models on popular benchmarks is presented. It further outlines several important applications that exploit the semantics of scientific tables and figures. The survey also highlights the challenges and some potential directions for future research.

In the words of Dr. Chen himself, “We believe this is the first comprehensive survey in understanding scientific tables and figures that covers the landscape from detection to application. We hope this survey will serve as a hands-on reference for a better understanding of the current research development on scientific tables and figures and assist readers in advancing this field.”

In the aftermath of this milestone publication, the research team has recently submitted another paper titled “DIG: Complex Layout Document Image Generation with Authentic-looking Text for Enhancing Layout Analysis” to ACM Multimedia 2024, the worldwide premier multimedia conference.

Link to the paper: https://dl.acm.org/doi/10.1145/3657285
Link to the journal: https://dl.acm.org/journal/csur

Published May 17th, 2024