Researchers have developed a novel framework to automatically estimate the perceived creativity of an image. This framework leverages psychological dimensions of creativity, specifically novelty, surprise, and arousal. By training machine learning models on data collected from human subjects via Amazon Mechanical Turk, the system can predict these creativity dimensions and then combine them to produce an overall image creativity score that statistically matches human ratings. AI
IMPACT This research could lead to automated tools for evaluating image creativity, benefiting content generation and curation platforms.
RANK_REASON Academic paper on a novel framework for estimating image creativity. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →