RESUMO
In the realm of long document classification (LDC), previous research has predominantly focused on modeling unimodal texts, overlooking the potential of multi-modal documents incorporating images. To address this gap, we introduce an innovative approach for multi-modal long document classification based on the Hierarchical Prompt and Multi-modal Transformer (HPMT). The proposed HPMT method facilitates multi-modal interactions at both the section and sentence levels, enabling a comprehensive capture of hierarchical structural features and complex multi-modal associations of long documents. Specifically, a Multi-scale Multi-modal Transformer (MsMMT) is tailored to capture the multi-granularity correlations between sentences and images. This is achieved through the incorporation of multi-scale convolutional kernels on sentence features, enhancing the model's ability to discern intricate patterns. Furthermore, to facilitate cross-level information interaction and promote learning of specific features at different levels, we introduce a Hierarchical Prompt (HierPrompt) block. This block incorporates section-level prompts and sentence-level prompts, both derived from a global prompt via distinct projection networks. Extensive experiments are conducted on four challenging multi-modal long document datasets. The results conclusively demonstrate the superiority of our proposed method, showcasing its performance advantages over existing techniques.