@article{intel:/content/journals/10.1386/jsca_00075_1, author = "Eriksson, Maria and Skotare, Tomas and Snickars, Pelle", title = "Understanding Gardar Sahlberg with neural nets: On algorithmic reuse of the Swedish SF archive", journal= "Journal of Scandinavian Cinema", year = "2022", volume = "12", number = "3", pages = "225-247", doi = "https://doi.org/10.1386/jsca_00075_1", url = "https://intellectdiscover.com/content/journals/10.1386/jsca_00075_1", publisher = "Intellect", issn = "2042-7905", type = "Journal Article", keywords = "convolutional neural nets", keywords = "computational film studies", keywords = "AI", keywords = "archival reuse", keywords = "film archives", keywords = "Video Reuse Detector", abstract = "In this article, we re-trace the history of the Swedish SF archive and reflect on how this collection of historic newsreels has been reappropriated and remixed throughout more recent media history. In particular, we focus on the work of director and film historian Gardar Sahlberg, who made extensive use of the SF archive, first in a series of documentary films, then in a number of historical TV programmes. We are interested in how historic film footage travels and circulates through time, but foremost we explore how algorithms can help identify instances of audio-visual reuse in large datasets. Hence the article discusses algorithmic ways of examining archival film reuse, introducing a method for mapping video reuse with the help of artificial intelligence or more precisely machine learning that uses so-called convolutional neural nets. The article presents the Video Reuse Detector (VRD), a tool that uses machine learning to identify visual similarities within a given audio-visual database such as the SF archive.", }