Call for Paper
Topics Covered
There are multiple novel generative AI tools purporting creative expression such as Stable Diffusion, DALL-E, Imagen and Parti recently created within the Computer Vision and Machine Learning Communities and AI-powered Music Generation Technologies. However, the broader impact of these technologies, as well as ways to protect artists are not well-discussed in the computer vision community. We would like the community to study and address the broader impact of these technologies as well as Generative AI Art Galleries, AI Art exhibitions, Cultural centers adapting to Generative AI technologies, including but not limited to the CVPR Art Gallery.
We solicit paper submissions on the following general categories:
Problem statements, introducing new areas of research on the intersection of Social Responsibility and Creative AI research.
Retrospectives on past creative content generation research and its ethical consequences.
Generative AI Art Galleries, AI Art exhibitions, including but not limited to the CVPR Art Gallery, Music Festivals and how these technologies impact Artists, Illustrators and Content Creators.
Technical contributions on responsible practices for example in the context of algorithmic bias and fairness in creative applications of computer vision. This includes creation, and curation of creative datasets, quantifying and mitigating biases in generative artworks.
Artworks that focus on the role of AI within society and its effect on art.
Accessibility and Creative expression with Generative AI.
Some examples of topics within this domain:
Product of Image Generation and its impact on society.
Economic risk and impact of Generative AI on artists [8].
Artists vs AI Generators, what is the line that makes a piece artistic? [8]
Understanding bias and fairness in the context of image generation. Many contemporary artists have begun to engage with AI and ML. Some have done this for the visual aesthetics that the techniques begin to allow, others engage with them more critically in order to understand and reveal the algorithmic processes that are beginning to have great social and political power. These groups often notice the social dimension of the algorithms which can be overlooked by the computer science community. What biases does the choice of training set bring to the images that are created? In a domain of subjective evaluation, what biases does the researcher themselves bring to determining what algorithms are a success?
Better approaches for real-time interactive methods for design. Current image generation algorithms show its value in efficiently generating content with various styles. This capability combined with designers' creativity and understanding of human emotions can potentially induce a new form of design process, where designers interact with the algorithms in real-time, leading to more valuable design outcomes.
Artistic perspectives on existing technologies and tools. The interdisciplinary arts brings an alternative perspective to computer vision work that can help us see the field in terms of its broader social context. Artists are often among the first groups to explore unintended consequences of new technologies, and to challenge foundational assumptions of the fields with which they interact.
Risks of cultural appropriation. While ethical considerations for what concerns the work of a specific artist are starting to be discussed in depth, the aspect of broader cultural appropriation is still relatively unexplored. Fundamental challenges arise when trying to define ownership and copyrights in the context of Traditional Cultural Expression, where the intellectual contribution can't be attributed to a single individual, but results from, and often defines, the cultural evolution of specific groups of people.
Copyright, ownership, and licensing. Generating creative content through generative models involves using already existing content as input which serves as an example of the desired output. As a result, this raises questions about style origination and ownership. Generated content tends to carry some resemblance of the content used as examples in the generation process. Could these similarities be interpreted as an imitation of style or merely drawing inspiration from existing work, and where do we draw the line?
Considerations relating to dataset diversity. Fashion and Art are two ways in which we show ourselves to the world. They can also be understood as a form of expression and storytelling. They have proven over the years to be efficient in preservation and celebration of culture and history. Existing work on Fashion and Art synthesis in computer vision research have been only limited to the western forms. This comes as a result of lack of diversity in the available datasets which further perpetuates the danger of a single story and under-representation of non-western cultures and Art forms. We invite submissions that analyze the bias aspect of existing datasets as well as new diverse benchmarks for fashion and art (e.g. [5, 6]).
Computer vision applications in fashion [2] or other creative domains which consider the diversity of user preferences, needs and requirements, such as individual tastes, body types [3, 4], aesthetic needs, etc.
Computer vision applications in fashion or other creative domains which aim at reducing waste, and eco-friendly recommendations, such as suggesting minimal quantities of fashion items to build a minimalist wardrobe [2].
Influence in fashion and artistic domain. Approaches that model influence between people, its impact on the fashion and creative domains, and how influence strength relates to other factors like cultural background, social and financial status [7].
Most datasets for creative arts and fashion have limited temporal coverage that tend to range from a few months to a couple of years. However, certain concepts like cultural appropriation and artwork attribution may span a time range of several years or decades which may create serious challenges in pinpointing the original creators. We invite contributions that address the short time span of the research data used in these studies and its implications for the developed models.
Artists retrospect of the trajectory of the Generative AI fields. Covering topics such as digital artwork forgery and how to tackle this problem? identifying and assessing algorithmic harms in Generative Art, such as stereotyping identities and cultural miss-representation.
Recapitulating colonial Western-centric views of the world because of its limited training data and modeling assumptions, GenAI caricatures and stereotypes representations of non-Western imagery that may have cultural significance. This process recapitulates the process of colonial acquisition of cultural artifacts for museums placed in Western contexts without history or explanation of how artifacts were acquired. At the same time, how can we avoid extractive data-collection processes to mitigate these kinds of harms? [9]
Arguments for and against AI Art as Theft arguments have been made both ways that the act of artistic expression inherently involves stealing (being inspired) and so there is no difference between human and AI generated artifacts. However, the sheer scale and speed of generative AI tools makes AI Art qualitatively different to human inspiration or copying. Numerous copyright lawsuits are now in the courts. How should the field orient itself toward this question?
References:
[1] W.-L. Hsiao and K. Grauman, “Creating capsule wardrobes from fashion images,” in CVPR, 2018
[2] B. Zhao, J. Feng, X. Wu, and S. Yan, “Memory-augmented attribute manipulation networks for interactive fashion search,” in CVPR, 2017.
[3] S. C. Hidayati, T. W. Goh, J. G. Chan, C. Hsu, J. See, W. Lai Kuan, K. Hua, Y. Tsao, and W. Cheng, “Dress with style: Learning style from joint deep embedding of clothing styles and body shapes,” IEEE Transactions on Multimedia, 2020.
[4] W-L. Hsiao and K. Grauman. "ViBE: Dressing for Diverse Body Shapes," in CVPR 2020
[5] H. Kataoka, Y. Satoh, K. Abe, M. Minoguchi, and A. Nakamura, “Ten-million-order human database for world-wide fashion culture analysis,” in CVPR Workshops, 2019.
[6] K. Matzen, K. Bala, and N. Snavely, “Streetstyle: Exploring world-wide clothing styles from millions of photos,” in arXiv, 2017.
[7] Z. Al-Halah and K. Grauman, “From Paris to Berlin: Discovering Fashion Style Influences Around the World,” in CVPR, 2020.
[8] H. Jiang, "AI Art and its Impact on Artists", in FAccT 2023.
[9] R. Qadri, "AI’s Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia", FAccT 2023.
Submission and Presentation Guidelines
We solicit short papers on developing and applying computer vision techniques that are valuable in the creative domains, with an emphasis on fashion, art and design. Accepted short papers will be linked online at the workshop webpage. The page limit is between two to four pages (including references). We encourage submission of work that has been previously published, and work in progress on relevant topics of the workshop. Accepted papers will be presented at the poster session. One paper will be awarded as the best paper. Manuscripts should follow the CVPR 2024 template and should be submitted through our CMT portal. We will provide CMT submission link soon.
Paper submission Link: https://cmt3.research.microsoft.com/EC3V2024
Note to Authors
For authors who want to submit their accepted work at this workshop to a different journal or conference, please check their double submission rules thoroughly. The four page limit should comply with the most common conferences on computer vision. However, the authors need to confirm this with the venue they intend to submit the paper to.
Please note that our workshop doesn't have a proceeding.
The review process is single-blind.
Authors can optionally submit supplemental materials for the paper via CMT.
For poster session, the poster dimension requirement is the same as the main conference.
Important Dates
Paper submission deadline: April 7 (11:59PM PST)
Notification to authors: April 15 (11:59PM PST)