Summary of Hierarchical Multi-modal Transformer For Cross-modal Long Document Classification, by Tengfei Liu et al.
Hierarchical Multi-modal Transformer for Cross-modal Long Document Classification
by Tengfei Liu, Yongli Hu, Junbin Gao, Yanfeng Sun, Baocai Yin
First submitted to arxiv on: 14 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach called Hierarchical Multi-modal Transformer (HMT) for cross-modal long document classification, which effectively utilizes both text and image features in documents with hierarchical structures. The HMT conducts multi-modal feature interaction and fusion between images and texts in a hierarchical manner using a multi-modal transformer and dynamic mask transfer module. Experimental results on four datasets show that the proposed approach outperforms state-of-the-art single-modality and multi-modality methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Long documents contain both text and image features, which can provide valuable information for classification tasks. However, current approaches only focus on short texts and images of pages. This paper aims to address this limitation by introducing a new method called Hierarchical Multi-modal Transformer (HMT) that combines text and image features in a hierarchical manner. The HMT uses a multi-modal transformer and dynamic mask transfer module to integrate the two modalities, allowing it to capture complex relationships between them. |
Keywords
» Artificial intelligence » Classification » Mask » Multi modal » Transformer
