DuwatBench: Bridging Language and Visual Heritage through an Arabic Calligraphy Benchmark for Multimodal Understanding
arXiv · · Significant research
Summary
MBZUAI researchers introduce DuwatBench, a new benchmark for multimodal understanding of Arabic calligraphy. The dataset contains 1,272 samples across six calligraphic styles with detailed annotations to evaluate visual-text alignment. Evaluation of 13 multimodal models reveals challenges in processing calligraphic variations and artistic distortions, highlighting the need for culturally grounded AI research.
Keywords
Arabic calligraphy · multimodal · benchmark · dataset · MBZUAI
Get the weekly digest
Top AI stories from the GCC region, every week.