mlsanityData to 7 Oct 2026

Level of agreement between emotions generated by Artificial Intelligence and human evaluation: a methodological proposal

arXiv 2410.08332 ↗First posted 10 Oct 2024cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Images are capable of conveying emotions, but emotional experience is highly subjective. Advances in artificial intelligence have enabled the generation of images based on emotional descriptions. However, the level of agreement between the generative images and human emotional responses has not yet been evaluated. To address this, 20 artistic landscapes were generated using StyleGAN2-ADA. Four variants evoking positive emotions (contentment, amusement) and negative emotions (fear, sadness) were created for each image, resulting in 80 pictures. An online questionnaire was designed using this material, in which 61 observers classified the generated images. Statistical analyses were performed on the collected data to determine the level of agreement among participants, between the observer's responses, and the AI-generated emotions. A generally good level of agreement was found, with better results for negative emotions. However, the study confirms the subjectivity inherent in emotional evaluation.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 41 of its 134 references that are in the map. First posted on arXiv 10 Oct 2024.

Builds on

41 of 134 references.

References · 41

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  4. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  5. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  6. 2016Pixel Recurrent Neural Networkscited by 814
  7. 2016Generative Adversarial Text to Image Synthesiscited by 735
  8. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  9. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  10. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  11. 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
  12. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 221
29 more
  1. 2015DRAW: A Recurrent Neural Network For Image Generationcited by 190
  2. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  3. 2015Generating Images from Captions with Attentioncited by 135
  4. 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
  5. 2021ArtEmis: Affective Language for Visual Artcited by 103
  6. 2017CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Normscited by 96
  7. 2019Learning to Paint With Model-based Deep Reinforcement Learningcited by 70
  8. 2016PixelVAE: A Latent Variable Model for Natural Imagescited by 69
  9. 2022A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advancescited by 59
  10. 2021Affective Image Content Analysis: Two Decades Review and New Perspectivescited by 47
  11. 2019Neural Painters: A learned differentiable constraint for generating brushstroke paintingscited by 28
  12. 2014Learning to Generate Chairs, Tables and Cars with Convolutional Networkscited by 26
  13. 2021Further Generalizations of the Jaccard Indexcited by 26
  14. 2016Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesiscited by 24
  15. 2020KaoKore: A Pre-modern Japanese Art Facial Expression Datasetcited by 18
  16. 2019PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regressioncited by 16
  17. 2019PixelVAE++: Improved PixelVAE with Discrete Priorcited by 15
  18. 2021GAN Computers Generate Arts? A Survey on Visual Arts, Music, and Literary Text Generation using Generative Adversarial Networkcited by 15
  19. 2020Sketch-to-Art: Synthesizing Stylized Art Images From Sketchescited by 10
  20. 2018Multitask Painting Categorization by Deep Multibranch Neural Networkcited by 8
  21. 2021Computational Emotion Analysis From Images: Recent Advances and Future Directionscited by 6
  22. 2022A Review on Text-Based Emotion Detection -- Techniques, Applications, Datasets, and Future Directionscited by 6
  23. 2014Supervised mid-level features for word image representationcited by 5
  24. 2017High-Level Concepts for Affective Understanding of Imagescited by 5
  25. 2022Unsupervised Hashing with Semantic Concept Miningcited by 5
  26. 2020Generative Adversarial Networks in Human Emotion Synthesis:A Reviewcited by 4
  27. 2020Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptationcited by 4
  28. 2019Modeling and Forecasting Art Movements with CGANscited by 2
  29. 2020Words as Art Materials: Generating Paintings with Sequential GANscited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025E-React: Towards Emotionally Controlled Synthesis of Human Reactionscited by 2