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...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Yao Meng, Haochen Sun, Wei Jiang
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	Nature Portfolio 2026-03-01
Serie:	Scientific Reports
Soggetti:	Text-guided segmentation Vision Mamba Large language models Interactive segmentation Cross-modal alignment
Accesso online:	https://doi.org/10.1038/s41598-026-43841-w
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!