Improved Image Caption Rating - Datasets, Game, and Model.

Autor:	Scott AT; Department of Computer Science, San Francisco State University, San Francisco, CA, USA., Narins LD; Department of Computer Science, San Francisco State University, San Francisco, CA, USA., Kulkarni A; Department of Computer Science, San Francisco State University, San Francisco, CA, USA., Castanon M; Department of Computer Science, San Francisco State University, San Francisco, CA, USA., Kao B; Department of Computer Science, San Francisco State University, San Francisco, CA, USA., Ihorn S; Department of Psychology, San Francisco State University, San Francisco, CA, USA., Siu YT; Department of Special Education, San Francisco State University, San Francisco, CA, USA., Yoon I; Department of Computer Science, San Francisco State University, San Francisco, CA, USA.
Jazyk:	angličtina
Zdroj:	Extended abstracts on Human factors in computing systems. CHI Conference [Ext Abstr Hum Factors Computing Syst] 2023 Apr; Vol. 2023. Date of Electronic Publication: 2023 Apr 19.
DOI:	10.1145/3544549.3585632
Abstrakt:	How well a caption fits an image can be difficult to assess due to the subjective nature of caption quality. What is a good caption? We investigate this problem by focusing on image-caption ratings and by generating high quality datasets from human feedback with gamification. We validate the datasets by showing a higher level of inter-rater agreement, and by using them to train custom machine learning models to predict new ratings. Our approach outperforms previous metrics - the resulting datasets are more easily learned and are of higher quality than other currently available datasets for image-caption rating.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu