Retrieval-Guided and Semantically Grounded Image Captioning for Open-Domain Scenes

Recent image captioning methods based on pre-trained vision–language models can generate fluent and coherent descriptions, yet they still struggle in open-domain scenes that contain long-tail concepts, uncommon object combinations, and ambiguous visual evidence. Two limitations are especially import...

Disgrifiad llawn

Manylion Llyfryddiaeth

Prif Awduron:	Shanshan Lin, Xiaoxuan Xie, Zexian Yang, Chao Chen
Fformat:	Artigo
Iaith:	Inglês
Cyhoeddwyd:	MDPI AG 2026-05-01
Cyfres:	Mathematics
Pynciau:	image captioning open-domain captioning retrieval augmentation visual prompting semantic grounding vision–language models
Mynediad Ar-lein:	https://www.mdpi.com/2227-7390/14/10/1667
Tagiau:	Ychwanegu Tag Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!