| 研究実績の概要 |
During the last year of the project, we investigated the use of generative text-to-image representations for the analysis and understanding of art images. Building on top of the latest advancements on text-to-image generation, we used this technology to generate a synthetic dataset with controllable labels and learn artistic representations from it. As an outcome:
1. We published our findings at the ACM International Conference on Multimedia Retrieval 2023 in Greece, which is a top conference on the field of multimedia analysis.
2. I participated in a panel about DALL-E and art history at the Digital Art History Summer School 2022 in Spain.
3. I co-organized a tutorial about computer vision on art at the Digital Humanities 2022 conference in Tokyo. I also co-organized the Vision for Art workshop at the European Conference on Computer Vision 2022 in Israel.
4. I gave a keynote talk at the Computer Vision for Fashion, Art, and Design workshop at the Conference on Computer Vision and Patter Recognition 2022 in New Orleans, United States.
|
