From still to moving images and vice versa: Analysing technological cycles and the use of AI to study cinema history
From still to moving images and vice versa: Analysing technological cycles and the use of AI to study cinema history
Abstract
This article explores some possibilities that an artificial intelligence that retrieves objects offers to cinema historians by focusing on the deep exploration of the photogramme. Thus, it reflects on a technological cycle that begins when cinema put the instantaneous photograph into motion – a motion that hid the details that today are easily retrievable with the help of AI that needs to stop this motion to find them. Being able to identify similar objects in photogrammes of films that are part of a corpus, an object retrieval AI allows us to explore how elements from the mise-en-scène can transform the historical understanding of cinema. Our theoretical reflections are put into practice through the analysis of photogrammes containing wheels in a corpus of films conceived by members of the pioneer generation of cinema archivists in correspondence between Europe and Latin America, at the beginning of the 1950s. The ubiquity of wheels allows us to have a general perception of the kind of image that composes our corpus, while it also allows us to evaluate the possibilities and limitations of using an object retrieval AI for writing cinema history.
Citation
Copy Citation
BibTex
Except where otherwise noted, this item's license is described as Creative Commons Attribution Non Commercial No Derivatives 4.0 Generic
Keywords:
cinema historyimage retrievalactive learningphotogrammeaudiovisual archive corpus