ACL Findings2024
Unveiling the Power of Integration: Block Diagram Summarization through Local-Global Fusion
Shreyanshu Bhushan, Eun-Soo Jung, Minho Lee
Abstract
Block Diagrams play an essential role in visualizing the relationships between components or systems. Generating summaries of block diagrams is important for document understanding or question answering (QA) tasks by providing concise overviews of complex systems. However, it's a challenging task as it requires compressing complex relationships into informative descriptions. In this paper, we present "BlockNet", a fusion framework that summarizes block diagrams by integrating local and global information, catering to both English and Korean languages. Additionally, we introduce a new multilingual method to produce block diagram data, resulting in a high-quality dataset called "BD-EnKo". In BlockNet, we develop "BlockSplit", an Optical Character Recognition (OCR) based algorithm employing the divide-and-conquer principle for local information extraction. We train an OCR-free transformer architecture for global information extraction using BD-EnKo and public data. To assess the effectiveness of our model, we conduct thorough experiments on different datasets. The assessment shows that BlockNet surpasses all previous methods and models, including GPT-4V, for block diagram summarization. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Cited by top-tier papers2
Builds on11
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- ViLT: Vision-and-Language Transformer Without Convolution or Region SupervisionWonjae Kim, Bokyung Son, Ildoo KimICML 2021 · 2,258 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
Related papers
- BLOCSUM: Block Scope-based Source Code Summarization via Shared Block RepresentationYunSeok Choi, Hyojun Kim, Jee-Hyong LeeACL Findings 2023 · 2 citations
- Assist Non-native Viewers: Multimodal Cross-Lingual Summarization for How2 VideosNayu Liu, Kaiwen Wei, Xian Sun, Hongfeng Yu et al.EMNLP 2022 · 10 citations
- BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation PretrainingMinJun Kim, Seungwoo Song, Youhan Lee, Haneol Jang et al.AAAI 2024 · 10 citations
- ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart UnderstandingJovana Kondic, Pengyuan Li, Dhiraj Joshi, Isaac Sanchez et al.CVPR 2026 · 7 citations
- VTLayout: A Multi-Modal Approach for Video Text LayoutYuxuan Zhao, Jin Ma, Zhongang Qi, Zehua Xie et al.ACM MM 2023 · 1 citation
