Text-to-Image Generation for Abstract Concepts
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (4) · 3360-3368
DOI: 10.1609/aaai.v38i4.28122 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Jiayi Liao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent years have witnessed the substantial progress of large-scale models across various domains, such as natural language processing and computer vision, facilitating the expression of concrete concepts. Unlike concrete concepts that are usually directly associated with physical objects, expressing abstract concepts through natural language requires considerable effort since they are characterized by intricate semantics and connotations. An alternative approach is to leverage images to convey rich visual information as a supplement. Nevertheless, existing Text-to-Image (T2I) models are primarily trained on concrete physical objects and often struggle to visualize abstract concepts. Inspired by the three-layer artwork theory that identifies critical factors, intent, object and form during artistic creation, we propose a framework of Text-to-Image generation for Abstract Concepts (TIAC). The abstract concept is clarified into a clear intent with a detailed definition to avoid ambiguity. LLMs then transform it into semantic-related physical objects, and the concept-dependent form is retrieved from an LLM-extracted form pattern set. Information from these three aspects will be integrated to generate prompts for T2I models via LLM. Evaluation results from human assessments and our newly designed metric concept score demonstrate the effectiveness of our framework in creating images that can sufficiently express abstract concepts.
Zitieren
APA
Liao, J., Chen, X., Fu, Q., Du, L., He, X., Wang, X., Han, S., & Zhang, D. (2024). Text-to-Image Generation for Abstract Concepts. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3360-3368. https://doi.org/10.1609/aaai.v38i4.28122
Vancouver
Liao J, Chen X, Fu Q, Du L, He X, Wang X, et al. Text-to-Image Generation for Abstract Concepts. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(4):3360-3368. doi:10.1609/aaai.v38i4.28122
BibTeX
@article{Liao2024,
author = {Liao, Jiayi and Chen, Xu and Fu, Qiang and Du, Lun and He, Xiangnan and Wang, Xiang and Han, Shi and Zhang, Dongmei},
title = {Text-to-Image Generation for Abstract Concepts},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {4},
pages = {3360--3368},
doi = {10.1609/aaai.v38i4.28122}
}
EUVIMED