Understanding and Creating Art with AI: Review and Outlook

  title={Understanding and Creating Art with AI: Review and Outlook},
  author={Eva Cetinic and James She},
  journal={ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)},
  pages={1 - 22}
  • Eva Cetinic, James She
  • Published 18 February 2021
  • Art
  • ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)
Technologies related to artificial intelligence (AI) have a strong impact on the changes of research and creative practices in visual arts. The growing number of research initiatives and creative applications that emerge in the intersection of AI and art motivates us to examine and discuss the creative and explorative potentials of AI technologies in the context of art. This article provides an integrated review of two facets of AI and art: (1) AI is used for art analysis and employed on… 

Figures and Tables from this paper

Understanding Art with AI: Our Research Experience

This discussion paper outlines some research directions that are exploring to contribute to the challenge of understanding art with AI, primarily concerned with visual link retrieval, artwork clustering, integrating new features based on contextual information encoded in a knowledge graph, and implementing these methods on social robots to provide new engaging user interfaces.

The Creativity of Artificial Intelligence in Art

  • Ming-Chia Cheng
  • Art
    The 2021 Summit of the International Society for the Study of Information
  • 2022
: New technologies, especially in the field of artificial intelligence, are dynamic in transform-ing creative space. AI-enabled programs are rapidly contributing to areas such as architecture, music,

Graph Neural Networks for Knowledge Enhanced Visual Representation of Paintings

It is demonstrated that several GNN architectures can outperform strong CNN baselines in a range of fine art analysis tasks, such as style classification, artist attribution, creation period estimation, and tag prediction, while training them requires an order of magnitude less computational time and only a small amount of labeled data.

Who made the paintings: Artists or artificial intelligence? The effects of identity on liking and purchase intention

Investigating how people respond to and view AI-created artworks is becoming increasingly crucial as the technology’s current application spreads due to its affordability and accessibility. This

Is GPT-3 all you need for Visual Question Answering in Cultural Heritage?

This paper proposes a method for Visual Question Answering that allows to generate at runtime a description sheet that can be used for answering both visual and contextual questions about the artwork, avoiding completely the image and the annotation process.

AI in learning

  • H. Niemi
  • Computer Science
    Journal of Pacific Rim Psychology
  • 2021
The articles in this special issue evidence that agency, engagement, self-efficacy, and collaboration are needed in learning and working with intelligent tools and environments and that the teacher’s role in digital pedagogy primarily involves facilitating and coaching.

A Deep Learning-Based Programming and Creation Algorithm of NFT Artwork

  • T. Wang
  • Computer Science
    Mobile Information Systems
  • 2022
It is proved that the NFT artwork transmission programming algorithm based on artificial intelligence deep learning proposed in this paper can control the overall style of image generation according to the needs of the transmission, and the generated image features have good details and high visual quality.

A New City Map

—In this paper we seek to understand how street maps can be used for making efficient, tailored, abstract art. Often art pieces require a tradeoff between cost-effective automation and


  • Art
  • 2022
: What is the essential ingredient of creativity that only humans – and not machines – possess? Can artificial intelligence help refine the notion of creativity by reference to that essential

Proposals Generation for Weakly Supervised Object Detection in Artwork Images

Quantitative and qualitative analysis shows that bounding boxes generated from CAMs can compensate for the lack of manually annotated ground truth (GT) and that an object detector, trained with such pseudo-GT, surpasses end-to-end WSOD state-of-the-art methods on ArtDL 2.0 and IconArt.



Art, Creativity, and the Potential of Artificial Intelligence

An AI process developed for making art (AICAN), and the issues AI creativity raises for understanding art and artists in the 21st century are discussed, with advocate for a connection between machine creativity and art broadly defined as parallel to but not in conflict with human artists and their emotional and social intentions.

DeepArt: Learning Joint Representations of Visual Arts

This paper presents a unified framework, called DeepArt, to learn joint representations that can simultaneously capture contents and style of visual arts, and introduces Art500k, a large-scale visual arts dataset containing over 500,000 artworks.

Human ownership of artificial creativity

This Perspective seeks to provide an answer by systematically exploring the key issues in copyright law that arise at each phase of artificial creativity, from programming to deployment, and establishing four guiding actions for artists, programmers and end users that utilize AI as a tool such that they may be appropriately awarded the necessary proprietary rights.

Artificial Intelligence, Artists, and Art

The study found that human- created artworks and AI-created artworks were not judged to be equivalent in their artistic value, and knowing that a piece of art was created by AI did not influence participants’ evaluation of art pieces’ artistic value.

How to Read Paintings: Semantic Art Understanding with Multi-Modal Retrieval

SemArt is a collection of fine-art painting images in which each image is associated to a number of attributes and a textual artistic comment, such as those that appear in art catalogues or museum collections, and several models for encoding visual and textual artistic representations into a common semantic space are proposed.

Understanding Compositional Structures in Art Historical Images using Pose and Gaze Priors

The approach, inspired by Max Imdahl's pioneering work, focuses on two central themes of image composition: detection of action regions and action lines of the artwork; and pose-based segmentation of foreground and background.

Exploring the Representativity of Art Paintings

This study proposes a novel deep representation of art paintings, which is enhanced by style information through a weighted pooling feature fusion module, and proposes a graph-based learning method for representativity learning, which considers intra-category, and extra-category information.

Computational Analysis of Content in Fine Art Paintings

A deep learning algorithm that can detect content and discover co-occurring patterns of the content in fine art paintings and is automatically trained to discover the connective patterns reflecting artists’ creativity, which are latent in the large dataset of paintings.

AI-generated vs. Human Artworks. A Perception Bias Towards Artificial Intelligence?

A wide-scale experiment in which 565 participants are asked to evaluate paintings (which were created by humans or AI) on four dimensions: liking, perceived beauty, novelty, and meaning shows a negative bias of perception towards AI and a preference bias towards human systems.

Biases in Generative Art: A Causal Look from the Lens of Art History

This work investigates biases in the generative art AI pipeline right from those that can originate due to improper problem formulation to those related to algorithm design and discusses the socio-cultural impacts of these biases from the lens of art history.