DAD’s Arthur Flexer presented our work on discovering semantic pathways through Belvedere’s fine arts collection at the “Machine Learning for Media Discovery Workshop” (18th of July 2020) of the “International Conference on Machine Learning”. The conference was supposed to happen in Vienna, Austria, but due to COVID-19 went fully virtual. You can see Arthur present his poster in a dedicated Zoom room below.
While a virtual workshop is not able to replace the experience and liveliness of a physical scientific meeting, it still allowed us to get an increasing degree of public exposure for our work in progress, which is the purpose of our Liminal Spaces.
Citation: Flexer A.: Discovering X Degrees of Keyword Separation in a Fine Arts Collection, in Proceedings of the 37th International Conference on Machine Learning, Machine Learning for Media Discovery Workshop, Vienna, Austria, PMLR 108, 2020.
The DUST AND DATA team evaluated their progress and current status in a one week workshop at Drosendorf (Lower Austria). We also planned the second year of the project including concrete next steps for our three Case Studies: the Glyptothek of the Academy of Fine Arts Vienna, the Volkskundemuseum Wien and the Belvedere.
DAD´s Arthur Flexer gave a semi-virtual lecture on “Discovering X Degrees of Keyword Separation in a Fine Arts Collection” at the Austrian Research Institute for Artificial Intelligence (OFAI, 24.6.2020). The presented work is inspired by the project ‘X Degrees of Separation‘ by ‘Google Arts and Culture’, which explores the “hidden paths through culture” by analyzing visual features of artworks to find pathways between any two artifacts through a chain of artworks. In his work, Arthur Flexer is more interested in finding pathways of the semantic meaning of works of art rather than just their visual features. Therefore he used word embedding [Mikolov et al 2013], which encodes semantic similarities between words by modelling the context to their neighboring words in a large training text corpus. This is used to embed keywords of Belvedere´s online fine arts collection and obtain pathways through the resulting semantic space.
The above exemplary result starts with a sculpture with keywords ‘Resurrection’ and ‘Christ’ where the painting in the end position has keywords around the topic of ‘Death’ and ‘Martyrdom’. The second artwork in the pathway is a relief showing ‘Christ’, while the third is a painting tagged with ‘Death’ and ‘Skeleton’, hence already semantically closer to the topics of ‘Martyrdom’, ‘Suffering’ and ‘Death’ of the end artwork. In fourth position is an etching with the only keyword ‘Vulture’, which is semantically close to ‘Angel’, ‘Air’ and ‘Death’ of the ending artwork.
In the ensuing discussion of results it was found remarkable how machine learning via word embedding replicates existing biases and prejudice in the society. In the above query with the word “Homosexuality” the most similar word out of 22 million terms in the word embedding model is “Paedophilia”, one of the worst prejudice against homosexual people. The word embedding model has been trained on the Wikipedia and Common Crawl corpus [Mikolov et al 2018], which helps explaining the replication of very common and persisting prejudice in our society.
OFAI´s Brigitte Krenn found it interesting how the very reglemented and almost scientific language in Belvedere’s keywords (stemming from the Iconclass project) is contrasted with everyday language via usage of word embedding. As can be seen above, the most similar keywords to “Homosexuality” are “Rape”, “Religion”, “Violence” and “Islam” (all translated from German). This is of course a direct result of the biases inherent to the word embedding model. DAD’s Alexander Martos called this phenomenon “re-socialising of arts via natural language processing” or rather “re-a-socialising” since it uncovers asocial societal tendencies and (re-?) introduces them to the world of fine arts.
Automatic colorization of black and white photographs has recently been enabled by advances in machine learning (see [Zhang et al 2016] for the methods we used for the following results). Basically deep neural networks are shown millions of black and white photographs and their color versions to learn a mapping from black and white to color. After successful training, it is possible to colorize black and white photos which the machine learning algorithm has never seen before. Online services like ALGORITHMIA enable everyone to test and use this technique by simply uploading their images.
One focus for DUST AND DATA is the Glyptothek of the Academy of Fine Arts, Vienna, which is a collection of plaster casts dating back to the late 17th century. Its main task was to serve as study material for Academy students, but it also became publicly accessible as a museum. The collection contains copies of a canon of world renown sculptures, ranging from plaster casts of Egyptian originals to copies of Greek and Roman, medieval, renaissance and historism statues. Thanks to German archaeologist Vinzenz Brinkmann, it is now an established fact that classic statues from e.g. Greek antiquity were originally painted in bright colors.
As for DUST AND DATA, all we are given are black and white photos of plaster casts from the Glyptothek. These are digital photo copies of analog plaster copies of statues. Is this sufficient to obtain any kind of meaningful result when trying to automatically colorize classic statues?
The automatic colorization of our dying warrior did not quite succeed, but is has many interesting features nevertheless. E.g. the algorithm did correctly “understand” that the statue is held by a real person, hence the colorization to skin tones of the person’s arm and dark color of the trousers. As for the statue, it is rendered in a light brown color, probably imitating the color of statues it has seen during training of the machine learning system. But what about the arm bottom left in the picture? It has almost a lifelike skin tone. And even more astonishing, the red bloodlike colorization of the amputed arm stump!
The Glyptothek also has a copy of Michelangelo’s David, or at least its head. The colorization above does provide a skinlike pink tone for the face and even blond hair.
Applying the colorization to the full David statue gives a lifelike pinkish skin tone, at least much more so than for the dying warrior above. The fact that Michelangelo’s David is such a realistic sculpture probably made it possible to trick the algorithm into treating the photo of David as the photo of a real naked person.
So can we use machine learning to automatically colorize photos of plaster casts from the Glyptothek? This would require training an algorithm with thousands of color restorations of antique statues (see photo of the Trojan archer above) to have any chance of success. But application of state-of-the-art colorization algorithms already now provides interesting results by exposing some of the biases and failures of their machine learning machinery.
The accessibility of vast amounts of text in digital form has enabled humanities to add ‘distant reading’ of thousands of books by algorithms as a new research tool to its repertoire of methods. This ‘distant reading’ of course has to be complemented with traditional ‘close reading’ of individual books. See e.g. [Jänicke et al 2015] for a survey and discussion of challenges.
We are currently working on applying machine learning as a distant reading tool to the journal Österreichische Zeitschrift für Volkskunde (OEZV) of the Austrian Museum of Folk Life and Folk Art. The OEZV has been published almost continuously since 1895 and we are able to use the result of an ‘Optical Character Recognition’ (OCR) scan of the entire publication history for our analysis. One of our interests is how the discourse and corresponding topics have changed over the years of its publication.
We applied topic modelling via Latent Dirichlet Allocation (LDA) for this analysis. Topic modelling tries to model latent topics in large amounts of text. Its basic entitity are documents which are modelled as probability distributions over word occurences. The assumption is that documents contain text about different topics which manifests itself in usage of different words. These latent topics are then also modelled as probability distributions over word occurences, since different topics will use different words related to their different content. LDA then finds a probability distribution of topics across documents, trying to optimize separation of documents over topics. The assumption here is that different documents contain information about rather different (and few) topics, but of course overlaps are allowed.
Usually a document is one article in a journal or newspaper, but for OEZV we have no access to article boundaries, therefore our basic entity are individual pages (more than 34000 for all years of OEZV together). Since we are interested in topic evolution over time, we aggregated all pages per year into overall documents. Using the LDA visualization package pyLDAvis, we modelled all OEZV volumes as distributions over 30 topics.
In this visualization, every topic is represented as a sphere in the left part of the figure. Clicking on one of the spheres (no. 17 in our picture), the right part of the figure shows a distribution of words which are prevalent for this topic. Some of the words have a religious meaning like ‘apostel’, ‘christusfigur’, ‘passionsspiele’ or ‘gründonnerstag’. Others are more about dancing like ‘tänzer’, ‘bandltanz’ or ‘getanzt’, which might lead to the conclusion that this topic is about religion and certain folkroristic rituals aorund it. It has to be said that such topics are often hard to interpret and maybe 30 topics for the entire OEZV collection is a too coarse resolution.
Every year of OEZV is now a distribution over 30 topics, i.e. a vector of probabilities of size 30. We can use this representation to compute how similar annual volumes of OEZV are in their distribution across topics. In the figure above both axes are the years of publication, from 1895 in the bottom left corner to 2018 bottom right and top left. One coloured cell in this figure represents the similarity of these years (inverted distance between probability vectors), with dark blue being very similar, bright yellow not similar and green in-between. Therefore the main diagonal is dark blue, since OEZV from one year is of course very similar to itself. The most interesting patterns are the larger dark blue rectangles along the main diagonal, indicating a number of consecutive years which are all similar to each other. This is most evident for the years 1940 to 1944, which is highlighted with a red ring around it. This time span coincides with Austria being part of Nazi Germany’s Third Reich, hence it is expected that the discourse in OEZV might be very different from all other years of its publication.
However, looking directly at the results from the OCR scan for the years 1940 to 1944, we realize that all of it is some kind of pseudo-German nonsense language, e.g.: “Vrautbater fteßte eine Dteipe bon Dtätfelfragen, auf bie ber Vrautfüprer alg Veboßmäiptigter beg Vräutigamg bie paffenbe Slnimori finbett mufgte”. To understand what happened here we look directly at the PDF-files of the OEZV, showing one page for the year 1944 below. As you can see a special typeface called ‘Frakturschrift’ is being used, which was typical for Nazi Germany.
Compare this to a page from year 1895, where a more common typeface has been used, as in all years except 1940 to 1944.
Appearantly the OCR scan failed miserably on the ‘Frakturschrift’ typeface resulting in the years 1940 to 1944 using its “own” language, some kind of gibberish German. This of course has a very harmful impact on our machine learning approach, since the years 1940 to 1944 use completely different (non-sensical) words than all other years. As a result these years end up having very different distributions across words and topics. Hence the high similarity between years 1940 to 1944 turns out to not be a very significant result after all, but an artefact of the processing pipeline with the OCR mistake propagating through the whole system.
Nevertheless we find this result interesting, because the time when Austria was part of the Third Reich has always been a sort of blind spot for Austria’s society, taking decades to accept its own disreputable role in the horrific events during this historic time span, slowly emerging from “Hitler’s first victim” to perpetrator and culprit. It is therefore quite ironic that this blind spot reappears via distant reading of Austria’s main scientific journal on Austrian folk life and folk art …
Wohnzimmerexperimente hinter der viralen Firewall
COVID19 zwingt auch „Dust and Data“ auf Distanz und zur Änderung einiger Arbeitsweisen. Für ihre Forschungen zu neuen, AI-basierten Ausstellungsdisplays haben Sanja und Irina ihre modellbauerische Passion ins Wohnzimmer verfrachtet und dort einen Galerie-Parcours für einen intelligenten Mitbewohner errichtet: ihren Saugroboter „Dusty“. Getreu seinem dienenden Credo „Start cleaning“, begann dieser sogleich mit der autonomen Vermessung des angestaubten Kunstraumraums. Ob sich in seinem skulpturalen Trainingsset neben einer lurchaneignenden auch eine „ästhetische Erfahrung“ ausbildet, von deren Bewegungsmustern im musealen Raum wir lernen könnten, ist Gegenstand weiterer Beobachtungen.
Dusty’s Dada: the Making-Of
During our 2nd Critical Space with guest expert Bob Sturm (KTH Royal Institute of Technology, Stockholm, Sweden) we presented and discussed a first mock-up of our “GO CURATOR” idea.
Here you can see DAD team members setting up the physical model.
GO CURATOR analyses text describing paintings in museum collections. Topic modelling is used to represent the semantic content in these texts, thereby targeting the semantic meaning of the paintings themselves.
Result is a probabilistic distribution across topics for every painting. E.g. in the painting below, the topics “food”, “act”, “human” and “object” are present to an equal extent of 25%.
Curators or museum visitors can change the exhibition interactively by adjusting which topics should be present to what extent. GO CURATOR then automatically adjusts the choice of paintings and their exact hanging in the museum room.
Das Gespräch mit Alexander Martos und Niko Wahl über ihre Projekte am Volkskundemuseum Wien und das Sammeln und Kuratieren der Zukunft.
During the research visit of Bob Sturm we will discuss the frontiers of artificial creativity and its criticism in the context of DUST AND DATA. Bob Sturm will also give a public lecture about his work on using machine learning to compose Irish folk music. His talk will also feature live accordion playing.
“Folk the Algorithms” – Bob Sturm, KTH Royal Institute of Technology, Stockholm, Sweden
In this talk/musical performance, I will recount how a bit of Saturday morning humor turned into an ERC Consolidator Grant four years later. It’s a story of an engineer with an artistic bent meeting a machine learning algorithm through a blog. One part of the story involves the naive misappropriation of music data without consideration of its provenance and significance. Another part involves the serious contemplation of such transgressions, and then endeavors taken to redress them. A variety of interesting perspectives and questions have arisen out of this story, which will be subject to study in the project, Music at the Frontiers of Artificial Creativity and Criticism (MUSAiC, ERC-2019-COG No. 864189).
Time: Wednesday, 26th of February 2020, 6:30 p.m. sharp
Location: Oesterreichisches Forschungsinstitut fuer Artificial Intelligence, OFAI
Freyung 6, Stiege 6, Tuer 7, 1010 Wien