# CITE: A Corpus of Image-Text Discourse Relations

arXiv: https://arxiv.org/abs/1904.06286 · HTML: https://mlsanity.com/paper/1904.06286/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2019.

## Built on by (most cited first, 12 of 12)

- [Underspecification in Scene Description-to-Depiction Tasks](https://mlsanity.com/paper/2210.05815/) (2022)
- [ImageArg: A Multi-modal Tweet Dataset for Image Persuasiveness Mining](https://mlsanity.com/paper/2209.06416/) (2022)
- [Point-of-Interest Type Prediction using Text and Images](https://mlsanity.com/paper/2109.00602/) (2021)
- [Evaluating Document Coherence Modelling](https://mlsanity.com/paper/2103.10133/) (2021)
- [Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows](https://mlsanity.com/paper/2209.05840/) (2022)
- [Understanding Social Media Cross-Modality Discourse in Linguistic Space](https://mlsanity.com/paper/2302.13311/) (2023)
- [Cross-Modal Coherence for Text-to-Image Retrieval](https://mlsanity.com/paper/2109.11047/) (2021)
- [CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?](https://mlsanity.com/paper/2502.11300/) (2025)
- [RONA: Pragmatically Diverse Image Captioning with Coherence Relations](https://mlsanity.com/paper/2503.10997/) (2025)
- [AnANet: Modeling Association and Alignment for Cross-modal Correlation Classification](https://mlsanity.com/paper/2109.00693/) (2021)
- [Zero-shot Cross-Linguistic Learning of Event Semantics](https://mlsanity.com/paper/2207.02356/) (2022)
- [ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis](https://mlsanity.com/paper/2404.10141/) (2024)

## Abstract (arXiv)

This paper presents a novel crowd-sourced resource for multimodal discourse: our resource characterizes inferences in image-text contexts in the domain of cooking recipes in the form of coherence relations. Like previous corpora annotating discourse structure between text arguments, such as the Penn Discourse Treebank, our new corpus aids in establishing a better understanding of natural communication and common-sense reasoning, while our findings have implications for a wide range of applications, such as understanding and generation of multimodal documents.