# MMCIG: Multimodal Cover Image Generation for Text-only Documents and Its Dataset Construction via Pseudo-labeling

arXiv: https://arxiv.org/abs/2508.17199 · HTML: https://mlsanity.com/paper/2508.17199/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 24 Aug 2025.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [AlignScore: Evaluating Factual Consistency with a Unified Alignment Function](https://mlsanity.com/paper/2305.16739/) (2023)
- [Multimodal Abstractive Summarization for How2 Videos](https://mlsanity.com/paper/1906.07901/) (2019)
- [SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data](https://mlsanity.com/paper/2403.06952/) (2024)
- [MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos](https://mlsanity.com/paper/2306.04216/) (2023)
- [Exploiting Pseudo Image Captions for Multimodal Summarization](https://mlsanity.com/paper/2305.05496/) (2023)
- [Questioning the Validity of Summarization Datasets and Improving Their Factual Consistency](https://mlsanity.com/paper/2210.17378/) (2022)
- [DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization](https://mlsanity.com/paper/2105.06441/) (2021)

## Abstract (arXiv)

In this study, we introduce a novel cover image generation task that produces both a concise summary and a visually corresponding image from a given text-only document. Because no existing datasets are available for this task, we propose a multimodal pseudo-labeling method to construct high-quality datasets at low cost. We first collect documents that contain multiple images with their captions, and their summaries by excluding factually inconsistent instances. Our approach selects one image from the multiple images accompanying the documents. Using the gold summary, we independently rank both the images and their captions. Then, we annotate a pseudo-label for an image when both the image and its corresponding caption are ranked first in their respective rankings. Finally, we remove documents that contain direct image references within texts. Experimental results demonstrate that the proposed multimodal pseudo-labeling method constructs more precise datasets and generates higher quality images than text- and image-only pseudo-labeling methods, which consider captions and images separately. We release our code at: https://github.com/HyeyeeonKim/MMCIG