TY - GEN
T1 - SciCapenter
T2 - 2024 CHI Conference on Human Factors in Computing Sytems, CHI EA 2024
AU - Hsu, Ting Yao
AU - Huang, Chieh Yang
AU - Huang, Shih Hong
AU - Rossi, Ryan
AU - Kim, Sungchul
AU - Yu, Tong
AU - Giles, Clyde Lee
AU - Huang, Ting Hao Kenneth
N1 - Publisher Copyright:
© 2024 Association for Computing Machinery. All rights reserved.
PY - 2024/5/11
Y1 - 2024/5/11
N2 - Crafting effective captions for figures is important. Readers heavily depend on these captions to grasp the figure's message. However, despite a well-developed set of AI technologies for figures and captions, these have rarely been tested for usefulness in aiding caption writing. This paper introduces SciCapenter, an interactive system that puts together cutting-edge AI technologies for scientific figure captions to aid caption composition. SciCapenter generates a variety of captions for each figure in a scholarly article, providing scores and a comprehensive checklist to assess caption quality across multiple critical aspects, such as helpfulness, OCR mention, key takeaways, and visual properties reference. Users can directly edit captions in SciCapenter, resubmit for revised evaluations, and iteratively refine them. A user study with Ph.D. students indicates that SciCapenter significantly lowers the cognitive load of caption writing. Participants' feedback further offers valuable design insights for future systems aiming to enhance caption writing.
AB - Crafting effective captions for figures is important. Readers heavily depend on these captions to grasp the figure's message. However, despite a well-developed set of AI technologies for figures and captions, these have rarely been tested for usefulness in aiding caption writing. This paper introduces SciCapenter, an interactive system that puts together cutting-edge AI technologies for scientific figure captions to aid caption composition. SciCapenter generates a variety of captions for each figure in a scholarly article, providing scores and a comprehensive checklist to assess caption quality across multiple critical aspects, such as helpfulness, OCR mention, key takeaways, and visual properties reference. Users can directly edit captions in SciCapenter, resubmit for revised evaluations, and iteratively refine them. A user study with Ph.D. students indicates that SciCapenter significantly lowers the cognitive load of caption writing. Participants' feedback further offers valuable design insights for future systems aiming to enhance caption writing.
UR - http://www.scopus.com/inward/record.url?scp=85194133947&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85194133947&partnerID=8YFLogxK
U2 - 10.1145/3613905.3650738
DO - 10.1145/3613905.3650738
M3 - Conference contribution
AN - SCOPUS:85194133947
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI 2024 - Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Sytems
PB - Association for Computing Machinery
Y2 - 11 May 2024 through 16 May 2024
ER -