EUVIMEDEUVIMED entdecken
Crossref

Theme-Aware Visual Attribute Reasoning for Image Aesthetics Assessment

Leida Li, Yipo Huang, Jinjian Wu, Yuzhe Yang, Yaqian Li, Yandong Guo, Guangming Shi

IEEE Transactions on Circuits and Systems for Video Technology · 2023-09 · 33 (9) · 4798-4811

DOI: 10.1109/tcsvt.2023.3249185 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-09. Verfasst von Leida Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 83-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: Key-Area Research and Development Program of Guangdong Province, National Natural Science Foundation of China, OPPO Research Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

People usually assess image aesthetics according to visual attributes, e.g., interesting content, good lighting and vivid color, etc. Further, the perception of visual attributes depends on the image theme. Therefore, the inherent relationship between visual attributes and image theme is crucial for image aesthetics assessment (IAA), which has not been comprehensively investigated. With this motivation, this paper presents a new IAA model based on Theme-Aware Visual Attribute Reasoning (TAVAR). The underlying idea is to simulate the process of human perception in image aesthetics by performing bilevel reasoning. Specifically, a visual attribute analysis network and a theme understanding network are first pre-trained to extract aesthetic attribute features and theme features, respectively. Then, the first level Attribute-Theme Graph (ATG) is built to investigate the coupling relationship between visual attributes and image theme. Further, a flexible aesthetics network is introduced to extract general aesthetic features, based on which we built the second level Attribute-Aesthetics Graph (AAG) to mine the relationship between theme-aware visual attributes and aesthetic features, producing the final aesthetic prediction. Extensive experiments on four public IAA databases demonstrate the superiority of the proposed TAVAR model over the state-of-the-arts. Furthermore, TAVAR features better explainability due to the use of visual attributes.

Förderung

  • Key-Area Research and Development Program of Guangdong Province
  • National Natural Science Foundation of China
  • OPPO Research Fund
  • Key Project of Shaanxi Provincial Department of Education

Zitieren

APA

Li, L., Huang, Y., Wu, J., Yang, Y., Li, Y., Guo, Y., & Shi, G. (2023). Theme-Aware Visual Attribute Reasoning for Image Aesthetics Assessment. IEEE Transactions on Circuits and Systems for Video Technology, 33(9), 4798-4811. https://doi.org/10.1109/tcsvt.2023.3249185

Vancouver

Li L, Huang Y, Wu J, Yang Y, Li Y, Guo Y, et al. Theme-Aware Visual Attribute Reasoning for Image Aesthetics Assessment. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(9):4798-4811. doi:10.1109/tcsvt.2023.3249185

BibTeX
@article{Li2023,
  author = {Li, Leida and Huang, Yipo and Wu, Jinjian and Yang, Yuzhe and Li, Yaqian and Guo, Yandong and Shi, Guangming},
  title = {Theme-Aware Visual Attribute Reasoning for Image Aesthetics Assessment},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {9},
  pages = {4798--4811},
  doi = {10.1109/tcsvt.2023.3249185}
}
Kostenlos starten →