Dual-Layer Fusion Knowledge Reasoning with Enhanced Multi-modal Features
Most of the existing multi-modal knowledge reasoning methods use splicing or attention to directly fuse the multi-modal features extracted from the pre-trained model, often ignoring the heterogeneity and interaction complexity between different modes. Therefore, a two-layer fusion knowledge inferenc...
Збережено в:
| Автор: | |
|---|---|
| Формат: | Artigo |
| Мова: | Chinês |
| Опубліковано: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2025-02-01
|
| Серія: | Jisuanji kexue yu tansuo |
| Предмети: | |
| Онлайн доступ: | http://fcst.ceaj.org/fileup/1673-9418/PDF/2312065.pdf |
| Теги: |
Немає тегів, Будьте першим, хто поставить тег для цього запису!
|