Saved in:
Bibliographic Details
Main Authors: Liu, Tengfei, Hu, Yongli, Gao, Junbin, Sun, Yanfeng, Yin, Baocai
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.10105
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911955072057344
author Liu, Tengfei
Hu, Yongli
Gao, Junbin
Sun, Yanfeng
Yin, Baocai
author_facet Liu, Tengfei
Hu, Yongli
Gao, Junbin
Sun, Yanfeng
Yin, Baocai
contents Long Document Classification (LDC) has gained significant attention recently. However, multi-modal data in long documents such as texts and images are not being effectively utilized. Prior studies in this area have attempted to integrate texts and images in document-related tasks, but they have only focused on short text sequences and images of pages. How to classify long documents with hierarchical structure texts and embedding images is a new problem and faces multi-modal representation difficulties. In this paper, we propose a novel approach called Hierarchical Multi-modal Transformer (HMT) for cross-modal long document classification. The HMT conducts multi-modal feature interaction and fusion between images and texts in a hierarchical manner. Our approach uses a multi-modal transformer and a dynamic multi-scale multi-modal transformer to model the complex relationships between image features, and the section and sentence features. Furthermore, we introduce a new interaction strategy called the dynamic mask transfer module to integrate these two transformers by propagating features between them. To validate our approach, we conduct cross-modal LDC experiments on two newly created and two publicly available multi-modal long document datasets, and the results show that the proposed HMT outperforms state-of-the-art single-modality and multi-modality methods.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10105
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hierarchical Multi-modal Transformer for Cross-modal Long Document Classification
Liu, Tengfei
Hu, Yongli
Gao, Junbin
Sun, Yanfeng
Yin, Baocai
Computer Vision and Pattern Recognition
Artificial Intelligence
Long Document Classification (LDC) has gained significant attention recently. However, multi-modal data in long documents such as texts and images are not being effectively utilized. Prior studies in this area have attempted to integrate texts and images in document-related tasks, but they have only focused on short text sequences and images of pages. How to classify long documents with hierarchical structure texts and embedding images is a new problem and faces multi-modal representation difficulties. In this paper, we propose a novel approach called Hierarchical Multi-modal Transformer (HMT) for cross-modal long document classification. The HMT conducts multi-modal feature interaction and fusion between images and texts in a hierarchical manner. Our approach uses a multi-modal transformer and a dynamic multi-scale multi-modal transformer to model the complex relationships between image features, and the section and sentence features. Furthermore, we introduce a new interaction strategy called the dynamic mask transfer module to integrate these two transformers by propagating features between them. To validate our approach, we conduct cross-modal LDC experiments on two newly created and two publicly available multi-modal long document datasets, and the results show that the proposed HMT outperforms state-of-the-art single-modality and multi-modality methods.
title Hierarchical Multi-modal Transformer for Cross-modal Long Document Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2407.10105