FULL PDF
Abstract
We present a web application that facilitates multimodal search within institutional image collections using current-generation machine learning models like CLIP. Further, we discuss image retrieval as a combined computer vision/human-computer interaction problem, and propose that the standardization of feature extraction is one of the main problems that digital art history faces today.
DOI: https://doi.org/10.11588/dahj.2023.9.91295
AuthorS
Fabian Offert
is Assistant Professor for the History and Theory of the Digital Humanities in the Department of Germanic and Slavic Studies at the University of California, Santa Barbara. His research and teaching focuses on the visual digital humanities, with a special interest in the epistemology and aesthetics of computer vision and machine learning. At UCSB, he is affiliated with the Media Arts and Technology program, the Comparative Literature program, and the Center for Responsible Machine Learning. He is also principal investigator of the UCHRI multi campus research group “Critical Machine Learning Studies” (2021-23), and the international research project “AI Forensics” (2022-25), funded by the VW foundation.
Peter Bell
studied Art History, Economics, and Visual Arts at Marburg University. He was Research Associate in the DFG SFB 600 research cluster at Trier University, (PhD 2011), Postdoctoral Researcher at Heidelberg University, Research Associate at the Prometheus Image Archive at Cologne University, as well as group leader at the Heidelberg Academy of Sciences and Humanities. From 2017-2021 he was Assistant Professor in Digital Humanities at the University of Erlangen-Nürnberg (FAU) and is now professor of Art History and Digital Humanities at Philipps University Marburg. He was also Principal Investigator of the DFG SPP 2172 “The Digital Image” and is speaker of the Digital Art History working group.