Enhancing zero-shot scene recognition through semantic autoencoders and visual relation transfer
Abstract Zero-shot learning enables the recognition of images from unseen classes by leveraging auxiliary semantic information. Traditional methods typically learn either the relationship between the visual features and the semantic vectors or that between the seen and the unseen semantic vectors. H...
Uloženo v:
| Hlavní autoři: | , , , , |
|---|---|
| Médium: | Artigo |
| Jazyk: | Inglês |
| Vydáno: |
Nature Portfolio
2025-12-01
|
| Edice: | Scientific Reports |
| Témata: | |
| On-line přístup: | https://doi.org/10.1038/s41598-025-28158-4 |
| Tagy: |
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|