# Alt-Text with Context: Improving Accessibility for Images on Twitter

arXiv: https://arxiv.org/abs/2305.14779 · HTML: https://mlsanity.com/paper/2305.14779/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [From Captions to Visual Concepts and Back](https://mlsanity.com/paper/1411.4952/) (2014)
- [Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements](https://mlsanity.com/paper/2010.04295/) (2020)
- [Learning to Generate Images with Perceptual Similarity Metrics](https://mlsanity.com/paper/1511.06409/) (2015)
- [Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures](https://mlsanity.com/paper/1601.03896/) (2016)
- [Assessing Demographic Bias in Named Entity Recognition](https://mlsanity.com/paper/2008.03415/) (2020)
- [Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics](https://mlsanity.com/paper/2205.10646/) (2022)
- [Concadia: Towards Image-Based Text Generation with a Purpose](https://mlsanity.com/paper/2104.08376/) (2021)
- [Computer Vision and Conflicting Values: Describing People with Automated Alt Text](https://mlsanity.com/paper/2105.12754/) (2021)
- [A Dataset of Alt Texts from HCI Publications: Analyses and Uses Towards Producing More Descriptive Alt Texts of Data Visualizations in Scientific Papers](https://mlsanity.com/paper/2209.13718/) (2022)

## Built on by (most cited first, 3 of 3)

- [Long-Form Answers to Visual Questions from Blind and Low Vision People](https://mlsanity.com/paper/2408.06303/) (2024)
- [MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation](https://mlsanity.com/paper/2510.00647/) (2025)
- [Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation](https://mlsanity.com/paper/2610.20335/) (2026)

## Abstract (arXiv)

In this work we present an approach for generating alternative text (or alt-text) descriptions for images shared on social media, specifically Twitter. More than just a special case of image captioning, alt-text is both more literally descriptive and context-specific. Also critically, images posted to Twitter are often accompanied by user-written text that despite not necessarily describing the image may provide useful context that if properly leveraged can be informative. We address this task with a multimodal model that conditions on both textual information from the associated social media post as well as visual signal from the image, and demonstrate that the utility of these two information sources stacks. We put forward a new dataset of 371k images paired with alt-text and tweets scraped from Twitter and evaluate on it across a variety of automated metrics as well as human evaluation. We show that our approach of conditioning on both tweet text and visual information significantly outperforms prior work, by more than 2x on BLEU@4.