Title: @grahamFleshingOutBones2018 date: 2023-01-17 type: reference project:
[!info] - Cite Key: @grahamFleshingOutBones2018 - Link: Full Text PDF - Abstract: There is an active trade in human remains facilitated by social media sites. In this paper we ask: can machine learning detect visual signals in photographs indicating that the human remains depicted are for sale? Do such signals even exist? This paper describes an experiment in using Tensorflow and the Google Inception-v3 model against a corpus of publicly available photographs collected from Instagram. Previous examination of the associated metadata for these photos detected patterns in the connectivity and rhetoric surrounding this ‘bone trade’, including several instances where ‘for sale’ seemed to be implied, though not explicitly stated. The present study looks for signals in the visual rhetoric of the images as detected by the computer and how these signals may intersect with the other data present.
todo/refactor¶
Graham, S., & Huffer, D. (2018). Fleshing Out the Bones: Studying the Human Remains Trade with Tensorflow and Inception. Journal of Computer Applications in Archaeology, 1(1), 55–63. https://doi.org/10.5334/jcaa.8
Summary & Key Take Aways¶
Graham and Huffer argue that if we look at enough pictures 'distantly', by which they mean, getting the computer to look for signals of visual similarity in a corpus of images culled from Instagram, we might see emergent signals of 'tropes' that can be understood as signalling larger cultural issues at play with regard to how mostly white, western people regard the dead. To build this argument, they walk us through how computer vision works, and the nature (representativeness) of the corpus they build using automatic scrapers. They make this argument in order to set the stage for more complex studies anticipated in the future, but also to argue that there is something there in the bone trade worth studying.
Links¶
Annotations extracted; #todo/delete
Annotations¶
%% begin annotations %%
Imported on 2023-01-11 9:41 pm¶
Agree¶
[!quote|#5fb236] Highlight The modern online trade in anatomical, ethnographic and archaeological human remains, especially using social media and e-commerce platforms such as Instagram, Facebook, Etsy, Marktplaats, Amazon.com, etc., is becoming documented and exposed (e.g. Huxley & Finnegan 2004; Huffer & Chappell 2014; Halling & Seidemann 2016; Huffer et al. in press).
great stuff!
Page 1 [[2022-12-13#7:17 pm]]
Questions / confusion¶
[!quote|#ffd400] Note
Page 1 [[2022-12-14#12:39 pm]] machine vision ethics
Imported on 2023-01-11 9:45 pm¶
Agree¶
[!quote|#5fb236] Highlight Fleshing Out the Bones: Studying the Human Remains Trade with Tensorflow and Inception
Page 1 [[2023-01-11#9:45 pm]]
[!quote|#5fb236] Note
another really great piece of work lads!
Page 1 [[2023-01-11#9:45 pm]]
%% end annotations %%