인공지능 기반 문화예술 콘텐츠 창작 기술 분석 및 도구 설계

다국어 초록 (Multilingual Abstract)

This paper proposes an arts and culture content creation tool powered by artificial intelligence. With the recent advances in technologies including artificial intelligence, there are active research activities on creating art and culture contents. However, it is still difficult and cumbersome for those who are not familiar with programming and artificial intelligence. In order to deal with the content creation with new technologies, we analyze related creation tools, services and technologies that process with raw visual and audio data, generate new media contents and visualize intermediate results. We then extract key requirements for a future creation tool for creators who are not familiar with programming and artificial intelligence. We finally introduce an intuitive and integrated content creation tool for end-users. We hope that this tool will allow creators to intuitively and creatively generate new media arts and culture contents based on not only understanding given data but also adopting new technologies.

참고문헌 (Reference)

1 "tSNE Java Script demo"

2 A. Ramesh, "Zero-Shot Text-to-Image Generation"

3 J. Redmon, "YOLOv3: An Incremental Improvement"

4 J. Redmon, "YOLO9000: Better, Faster, Stronger" 6517-6525, 2017

5 A. S. Cowen, "What music makes us feel: At least 13 dimensions organize subjective experiences associated with music across different cultures" 117 (117): 1924-1934, 2020

6 L. Maaten, "Visualizing High-Dimensional Data Using t-SNE" 9 : 2579-2605, 2008

7 "The Next Rembrandt"

8 "Teachable Machine"

9 "T-SNE visualization"

10 C. Weng, "Photo Wake-Up: 3D Character Animation From a Single Photo"

11 Z. Cao, "OpenPose:Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields" 43 (43): 172-186, 2021

12 "Music visualization"

13 H. Dong, "MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment" 2018

14 Z. Wolkowicz, "Midivis: Visualizing Music Structure via Similarity Matrices" 53-56, 2009

15 "Magenta"

16 D. M. Blei, "Latent Dirichlet Allocation" 3 : 993-1022, 2003

17 C. Sievert, "LDAvis: A method for visualizing and interpreting topics" 63-70, 2014

18 T. Ishibashi, "Investigating audio data visualization for interactive sound recognition" Association for Computing Machinery 67-77,

19 A. Krizhevsky, "ImageNet classification with deep convolutional neural networks" Curran Associates Inc 1 : 1097-1105,

20 P. Isola, "Image-to-Image Translation with Conditional Adversarial Networks" 5967-5976, 2017

21 P. Isola, "Image-to-Image Translation with Conditional Adversarial Networks" 5967-5976, 2017

22 L. A. Gatys, "Image Style Transfer Using Convolutional Neural Networks" 2414-2423, 2016

23 M. Wattenberg, "How to Use t-SNE Effectively" 2016

24 "Google Arts & Culture"

25 "Deep dream generator"

26 K. He, "Deep Residual Learning for Image Recognition" 770-778, 2016

27 S. Minaee, "Deep Learning-based Text Classification: A Comprehensive Review" 54 (54): 2021

28 J. P. Briot, "Computational Synthesis and Creative Systems" Springer 2017

29 S. Hershey, "CNN architectures for large-scale audio classification" 131-135, 2017

30 "Autodraw"

31 Z. Kastrati, "A Deep Learning Sentiment Analyser for Social Media Comments in Low-Resource Languages" 10 (10): 1133