# DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents

arXiv: https://arxiv.org/abs/2306.06306 · HTML: https://mlsanity.com/paper/2306.06306/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 9 Jun 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training](https://mlsanity.com/paper/2005.00200/) (2020)
- [MERLOT: Multimodal Neural Script Knowledge Models](https://mlsanity.com/paper/2106.02636/) (2021)
- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound](https://mlsanity.com/paper/2201.02639/) (2022)
- [Visual News: Benchmark and Challenges in News Image Captioning](https://mlsanity.com/paper/2010.03743/) (2020)
- [VinVL: Revisiting Visual Representations in Vision-Language Models](https://mlsanity.com/paper/2101.00529/) (2021)
- [Unified Pretraining Framework for Document Understanding](https://mlsanity.com/paper/2204.10939/) (2022)
- [Good News, Everyone! Context driven entity-aware captioning for news images](https://mlsanity.com/paper/1904.01475/) (2019)
- [Transform and Tell: Entity-Aware News Image Captioning](https://mlsanity.com/paper/2004.08070/) (2020)
- [Instance-aware Image and Sentence Matching with Selective Multimodal LSTM](https://mlsanity.com/paper/1611.05588/) (2016)
- [Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking](https://mlsanity.com/paper/1908.04011/) (2019)

## Built on by (most cited first, 7 of 7)

- [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (2023)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning](https://mlsanity.com/paper/2311.10774/) (2023)
- [Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey](https://mlsanity.com/paper/2407.21794/) (2024)
- [Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps](https://mlsanity.com/paper/2307.05052/) (2023)
- [JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation](https://mlsanity.com/paper/2410.17250/) (2024)
- [Anticipating Driving Behavior through Deep Learning-Based Policy Prediction](https://mlsanity.com/paper/2307.11058/) (2023)

## Abstract (arXiv)

Vision-language pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-language pretraining models primarily focus on understanding single image associated with a single piece of text, they often ignore the alignment at the intra-document level, consisting of multiple sentences with multiple images. In this work, we propose DocumentCLIP, a salience-aware contrastive learning framework to enforce vision-language pretraining models to comprehend the interaction between images and longer text within documents. Our model is beneficial for the real-world multimodal document understanding like news article, magazines, product descriptions, which contain linguistically and visually richer content. To the best of our knowledge, we are the first to explore multimodal intra-document links by contrastive learning. In addition, we collect a large Wikipedia dataset for pretraining, which provides various topics and structures. Experiments show DocumentCLIP not only outperforms the state-of-the-art baselines in the supervised setting, but also achieves the best zero-shot performance in the wild after human evaluation. Our code is available at https://github.com/FuxiaoLiu/DocumentCLIP.