Guardado en:
Detalles Bibliográficos
Autores principales: Long, Xiaosheng, Wang, Hanyu, Song, Zhentao, Luo, Kun, Liu, Hongde
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2509.15883
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918144344326144
author Long, Xiaosheng
Wang, Hanyu
Song, Zhentao
Luo, Kun
Liu, Hongde
author_facet Long, Xiaosheng
Wang, Hanyu
Song, Zhentao
Luo, Kun
Liu, Hongde
contents Recent retrieval-augmented image captioning methods incorporate external knowledge to compensate for the limitations in comprehending complex scenes. However, current approaches face challenges in relation modeling: (1) the representation of semantic prompts is too coarse-grained to capture fine-grained relationships; (2) these methods lack explicit modeling of image objects and their semantic relationships. To address these limitations, we propose RACap, a relation-aware retrieval-augmented model for image captioning, which not only mines structured relation semantics from retrieval captions, but also identifies heterogeneous objects from the image. RACap effectively retrieves structured relation features that contain heterogeneous visual information to enhance the semantic consistency and relational expressiveness. Experimental results show that RACap, with only 10.8M trainable parameters, achieves superior performance compared to previous lightweight captioning models.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15883
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning
Long, Xiaosheng
Wang, Hanyu
Song, Zhentao
Luo, Kun
Liu, Hongde
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent retrieval-augmented image captioning methods incorporate external knowledge to compensate for the limitations in comprehending complex scenes. However, current approaches face challenges in relation modeling: (1) the representation of semantic prompts is too coarse-grained to capture fine-grained relationships; (2) these methods lack explicit modeling of image objects and their semantic relationships. To address these limitations, we propose RACap, a relation-aware retrieval-augmented model for image captioning, which not only mines structured relation semantics from retrieval captions, but also identifies heterogeneous objects from the image. RACap effectively retrieves structured relation features that contain heterogeneous visual information to enhance the semantic consistency and relational expressiveness. Experimental results show that RACap, with only 10.8M trainable parameters, achieves superior performance compared to previous lightweight captioning models.
title RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.15883