Back to Search
Start Over
CrePoster: Leveraging multi-level features for cultural relic poster generation via attention-based framework.
- Source :
-
Expert Systems with Applications . Jul2024, Vol. 245, pN.PAG-N.PAG. 1p. - Publication Year :
- 2024
-
Abstract
- Integrating multi-level features of cultural relics into aesthetic posters suitable for social sharing can enhance cultural value dissemination. However, this task meets two major challenges: (i) generating professional captions for cultural relics that encompass color, shape, form, and metaphor details; (i i) combining designers' expertise and cultural relics' unique aesthetic features to create visually appealing posters through layout, color, and font selection. Existing methods for poster generation primarily target merchandise or scientific publications. Constrained by product style or traditional design rules, which are unsuitable for cultural relics with multi-level aesthetic features. In this work, we propose CrePoster , an attention-based C ultural re lic Poster generation framework that incorporates multi-level feature extraction. Taking Chinese cultural relics as the case study, after the photos are uploaded, CrePoster leverages a large-scale pre-trained image segmentation network to obtain the critical object. Subsequently, a multi-level feature extraction-based caption generator is utilized to generate professional captions. Afterward, an attention-based dual-scale fusion network is employed to represent the aesthetic characters and guide the layout matching. Compared with existing methods, CrePoster can generate higher-quality captions and posters with more aesthetic value. • A novel problem of generating aesthetic cultural relic posters. • An attention-based dual-scale fusion network for aesthetic character representation. • Use the synergy between multi-level feature extraction and attention mechanism. [ABSTRACT FROM AUTHOR]
- Subjects :
- *POSTERS
*RELICS
*IMAGE segmentation
*CULTURAL values
*AESTHETICS
*FEATURE extraction
Subjects
Details
- Language :
- English
- ISSN :
- 09574174
- Volume :
- 245
- Database :
- Academic Search Index
- Journal :
- Expert Systems with Applications
- Publication Type :
- Academic Journal
- Accession number :
- 176152020
- Full Text :
- https://doi.org/10.1016/j.eswa.2024.123136