Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Explaining CLIP through Co-Creative Drawings and Interaction (2306.07429v1)

Published 12 Jun 2023 in cs.AI, cs.CV, and cs.CY

Abstract: This paper analyses a visual archive of drawings produced by an interactive robotic art installation where audience members narrated their dreams into a system powered by CLIPdraw deep learning (DL) model that interpreted and transformed their dreams into images. The resulting archive of prompt-image pairs were examined and clustered based on concept representation accuracy. As a result of the analysis, the paper proposes four groupings for describing and explaining CLIP-generated results: clear concept, text-to-text as image, indeterminacy and confusion, and lost in translation. This article offers a glimpse into a collection of dreams interpreted, mediated and given form by AI, showcasing oftentimes unexpected, visually compelling or, indeed, the dream-like output of the system, with the emphasis on processes and results of translations between languages, sign-systems and various modules of the installation. In the end, the paper argues that proposed clusters support better understanding of the neural model.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (12)
  1. Mar Canet Sola and Varvara Guljajeva “Dream Painter: Exploring creative possibilities of AI-aided speech-to-image synthesis in the interactive art context” In Proceedings of the ACM on Computer Graphics and Interactive Techniques 5.4 ACM New York, NY, USA, 2022, pp. 1–11
  2. Paul Cohen “Harold Cohen and AARON” In AI Magazine 37.4 AAAI, 2016, pp. 63–66 DOI: 10.1609/aimag.v37i4.2695
  3. Kevin Frans, Lisa Soros and Olaf Witkowski “Clipdraw: Exploring text-to-drawing synthesis through language-image encoders” In Advances in Neural Information Processing Systems 35, 2022, pp. 5207–5218
  4. Varvara Guljajeva “Synthetic Books” In 10th International Conference on Digital and Interactive Arts, 2021, pp. 1–7
  5. Varvara Guljajeva and Mar Canet Sola “Dream Painter: An Interactive Art Installation Bridging Audience Interaction, Robotics, and Creative AI” In Proceedings of the 30th ACM International Conference on Multimedia (MM ’22) Lisboa, Portugal: Association for Computing Machinery, 2022, pp. 7235–7236 DOI: 10.1145/3503161.3549976
  6. Aaron Hertzmann “Visual Indeterminacy in GAN Art” In Leonardo 53.4 MIT Press, 2020, pp. 424–428 DOI: 10.1162/leon˙a˙01930
  7. Roman Jakobson “On linguistic aspects of translation” In The Translation Studies Reader LondonNew York: Routledge, 2002
  8. Yuri M Lotman “Universe of the mind: A semiotic theory of culture” Indiana University Press, 1990, pp. 143
  9. “The Pleasure in Drawing” New York, NY: Fordham University Press, 2013
  10. “Learning Transferable Visual Models From Natural Language Supervision”, https://doi.org/10.48550/ARXIV.2103.00020, 2021
  11. “Investigating Explainability of Generative AI for Code through Scenario-Based Design” In 27th International Conference on Intelligent User Interfaces, IUI ’22 New York, NY, USA: Association for Computing Machinery, 2022, pp. 212–228 DOI: 10.1145/3490099.3511119
  12. “Tractatus Logico-Philosophicus” Originally published: London : Routledge & Kegan Paul, 1922. Includes index. Mineola, NY: Dover Publications, 1999
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Varvara Guljajeva (9 papers)
  2. Isaac Joseph Clarke (2 papers)
  3. Mar Canet Solà (4 papers)
Citations (3)

Summary

We haven't generated a summary for this paper yet.