| 💼 | https://tillmannohm.com |
| 🔬 | https://cudan.tlu.ee/team/tillmann |
| 🦤 | https://twitter.com/tillmannohm |
🖥 Demo: https://collection-space-navigator.github.io/CSN
📄 Paper (preprint): https://arxiv.org/abs/2305.06809
💾 Code: https://github.com/Collection-Space-Navigator/CSN
🌐 Website: https://collection-space-navigator.github.io
We are doing a conference! If you work with #cultural #text #linguistic #media #literature #film #art #audiovisual #DH etc data, take a look! Bonus: Tallinn Christmas market, northern lights (maybe) and 4 free practical skills workshops (yes incl R!) on the pre-conf day.
#CUDAN2023
The Cultural Data Analytics Conference 2023
❄️December 13-16, 2023❄️
Tallinn, Estonia
Abstract submissions by July 24: cudan.tlu.ee/conference
Ahh I've been so excited for this paper to come out for ages!! No affiliation, just think it's super cool:
"Collection Space Navigator" for exploring projections of visual art collections
Honestly, when I first saw this, it wasn't the art applications that intrigued me so much as the value it offers for understanding 'slices' through high-dimensional space.
Demo: https://collection-space-navigator.github.io/CSN/
Website: https://collection-space-navigator.github.io/
#machinelearning #dimensionalityreduction #arts #datavisualization
Collection Space Navigator: a powerful tool to explore and curate large collections of visual digital artifacts.
With configurable multidimensional filters and two-dimensional projections, users can easily analyze and understand complex data. Try out the functional showcase demo using classical Western art and see how the CSN can enhance your research: https://collection-space-navigator.github.io/
#datavisualization #digitization #opensource #digitalarthistory #datascience #dataviz
Introducing the Collection Space Navigator (CSN) – An Interactive Visualization Interface for Multidimensional Datasets
A browser-based tool that enables the exploration and curation of digital collections in the multidimensional space.
🖥 Demo: https://collection-space-navigator.github.io/CSN
📄 Paper (preprint): https://arxiv.org/abs/2305.06809
💾 Code: https://github.com/Collection-Space-Navigator/CSN
🌐 Website: https://collection-space-navigator.github.io
developed at CUDAN, Tallinn University by @tillmannohm, Mar Canet Sola, @andreskarjus and @schichmax
Read about our embedding technique:
https://arxiv.org/abs/2205.10271
Stay tuned for the Collection Space Navigator release and publication.
* attributed to George Box
#CollectionSpaceNavigator #CSN #curation #museum #visualization #collections #ai #wikiart #digitalhumanities #arthistory #UMAP #tSNE #research #complexity #deeplearning #embeddings #compression #science #dataanalytics #dataanalysis #aesthetics #curating #computervision
3/3
The quantification of visual aesthetics and complexity have a long history, the latter previously operationalized via the application of compression algorithms. Here we generalize and extend the compression approach beyond simple complexity measures to quantify algorithmic distance in historical and contemporary visual media. The proposed "ensemble" approach works by compressing a large number of transformed versions of a given input image, resulting in a vector of associated compression ratios. This approach is more efficient than other compression-based algorithmic distances, and is particularly suited for the quantitative analysis of visual artifacts, because human creative processes can be understood as algorithms in the broadest sense. Unlike comparable image embedding methods using machine learning, our approach is fully explainable through the transformations. We demonstrate that the method is cognitively plausible and fit for purpose by evaluating it against human complexity judgments, and on automated detection tasks of authorship and style. We show how the approach can be used to reveal and quantify trends in art historical data, both on the scale of centuries and in rapidly evolving contemporary NFT art markets. We further quantify temporal resemblance to disambiguate artists outside the documented mainstream from those who are deeply embedded in Zeitgeist. Finally, we note that compression ensembles constitute a quantitative representation of the concept of visual family resemblance, as distinct sets of dimensions correspond to shared visual characteristics otherwise hard to pin down. Our approach provides a new perspective for the study of visual art, algorithmic image analysis, and quantitative aesthetics more generally.
However, embedding the objects in a multi-dimensional vector space, and eventually reducing the dimensionality to 2 or 3 dimensions, can provide valuable insights into the patterns and similarities within these collections.
The figure below shows different projections of the high-dimensional embedding space generated by our Collection Space Navigator, a multidisciplinary research project at CUDAN, Tallinn University with Mar Canet Sola, @andreskarjus and @schichmax. 2/3
Harald Klinke
Daniel
Andres Karjus
Jane Adams