VP-MEL: Visual Prompts Guided Multimodal Entity Linking

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Mi, Hongze, Li, Jinyuan, Zhang, Xuying, Cheng, Haoran, Wang, Jiahao, Sun, Di, Pan, Gang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916616612085760
author Mi, Hongze
Li, Jinyuan
Zhang, Xuying
Cheng, Haoran
Wang, Jiahao
Sun, Di
Pan, Gang
author_facet Mi, Hongze
Li, Jinyuan
Zhang, Xuying
Cheng, Haoran
Wang, Jiahao
Sun, Di
Pan, Gang
contents Multimodal entity linking (MEL), a task aimed at linking mentions within multimodal contexts to their corresponding entities in a knowledge base (KB), has attracted much attention due to its wide applications in recent years. However, existing MEL methods often rely on mention words as retrieval cues, which limits their ability to effectively utilize information from both images and text. This reliance causes MEL to struggle with accurately retrieving entities in certain scenarios, especially when the focus is on image objects or mention words are missing from the text. To solve these issues, we introduce a Visual Prompts guided Multimodal Entity Linking (VP-MEL) task. Given a text-image pair, VP-MEL aims to link a marked region (i.e., visual prompt) in an image to its corresponding entities in the knowledge base. To facilitate this task, we present a new dataset, VPWiki, specifically designed for VP-MEL. Furthermore, we propose a framework named IIER, which enhances visual feature extraction using visual prompts and leverages the pretrained Detective-VLM model to capture latent information. Experimental results on the VPWiki dataset demonstrate that IIER outperforms baseline methods across multiple benchmarks for the VP-MEL task.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06720
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VP-MEL: Visual Prompts Guided Multimodal Entity Linking
Mi, Hongze
Li, Jinyuan
Zhang, Xuying
Cheng, Haoran
Wang, Jiahao
Sun, Di
Pan, Gang
Computer Vision and Pattern Recognition
Computation and Language
Multimodal entity linking (MEL), a task aimed at linking mentions within multimodal contexts to their corresponding entities in a knowledge base (KB), has attracted much attention due to its wide applications in recent years. However, existing MEL methods often rely on mention words as retrieval cues, which limits their ability to effectively utilize information from both images and text. This reliance causes MEL to struggle with accurately retrieving entities in certain scenarios, especially when the focus is on image objects or mention words are missing from the text. To solve these issues, we introduce a Visual Prompts guided Multimodal Entity Linking (VP-MEL) task. Given a text-image pair, VP-MEL aims to link a marked region (i.e., visual prompt) in an image to its corresponding entities in the knowledge base. To facilitate this task, we present a new dataset, VPWiki, specifically designed for VP-MEL. Furthermore, we propose a framework named IIER, which enhances visual feature extraction using visual prompts and leverages the pretrained Detective-VLM model to capture latent information. Experimental results on the VPWiki dataset demonstrate that IIER outperforms baseline methods across multiple benchmarks for the VP-MEL task.
title VP-MEL: Visual Prompts Guided Multimodal Entity Linking
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2412.06720