@article{institutionalbooksvisualelementsanopenso, title = {Institutional Books - Visual Elements: An open-source pipeline for extracting, classifying, deduplicating, and captioning visual elements from digital book collections}, author = {Jimmy Mendez and Matteo Cargnelutti and David Lowry-Duda and Catherine Brobston and Salwa Ismail and Greg Leppert and Amanda Watson and Jonathan Zittrain}, year = {2026}, eprint = {2608.18957}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.18957}, }