Interactive text-guided image segmentation via vision Mamba and large language models

Abstract This paper proposes an H-type Bidirectional Alignment Network for text-guided image segmentation, enabling efficient and accurate cross-modal feature fusion. For visual encoding, a 12-layer Vision Mamba with four stages is adopted. It captures long-range dependencies via a Selective State S...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Yao Meng, Haochen Sun, Wei Jiang
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Nature Portfolio 2026-03-01
Edice:	Scientific Reports
Témata:	Text-guided segmentation Vision Mamba Large language models Interactive segmentation Cross-modal alignment
On-line přístup:	https://doi.org/10.1038/s41598-026-43841-w
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!