# EXIF as Language: Learning Cross-Modal Associations Between Images and Camera Metadata

arXiv: https://arxiv.org/abs/2301.04647 · HTML: https://mlsanity.com/paper/2301.04647/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 86 references that are in the map.
- First posted on arXiv 11 Jan 2023.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [VirTex: Learning Visual Representations from Textual Annotations](https://mlsanity.com/paper/2006.06666/) (2020)
- [Audio-Visual Scene Analysis with Self-Supervised Multisensory Features](https://mlsanity.com/paper/1804.03641/) (2018)
- [YFCC100M: The New Data in Multimedia Research](https://mlsanity.com/paper/1503.01817/) (2015)
- [Learning Visual Features from Large Weakly Supervised Data](https://mlsanity.com/paper/1511.02251/) (2015)
- [Learning Rich Features for Image Manipulation Detection](https://mlsanity.com/paper/1805.04953/) (2018)
- [Fighting Fake News: Image Splice Detection via Learned Self-Consistency](https://mlsanity.com/paper/1805.04096/) (2018)
- [Learning Visual Representations with Caption Annotations](https://mlsanity.com/paper/2008.01392/) (2020)
- [Noiseprint: a CNN-based camera model fingerprint](https://mlsanity.com/paper/1808.08396/) (2018)
- [Learning Visual N-Grams from Web Data](https://mlsanity.com/paper/1612.09161/) (2016)

## Built on by (most cited first, 17 of 17)

- [Binding Touch to Everything: Learning Unified Multimodal Tactile Representations](https://mlsanity.com/paper/2401.18084/) (2024)
- [Pretrained Language Models as Visual Planners for Human Assistance](https://mlsanity.com/paper/2304.09179/) (2023)
- [Generating Visual Scenes from Touch](https://mlsanity.com/paper/2309.15117/) (2023)
- [RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings](https://mlsanity.com/paper/2502.19781/) (2025)
- [Iterated Learning Improves Compositionality in Large Vision-Language Models](https://mlsanity.com/paper/2404.02145/) (2024)
- [Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images](https://mlsanity.com/paper/2503.21003/) (2025)
- [Scale-adaptive UAV Geo-localization via Height-aware Partition Learning](https://mlsanity.com/paper/2412.11535/) (2024)
- [Bi-Level Optimization for Self-Supervised AI-Generated Face Detection](https://mlsanity.com/paper/2507.22824/) (2025)
- [Self-Supervised Learning for Detecting AI-Generated Faces as Anomalies](https://mlsanity.com/paper/2501.02207/) (2025)
- [FontGuard: A Robust Font Watermarking Approach Leveraging Deep Font Knowledge](https://mlsanity.com/paper/2504.03128/) (2025)
- [Processing and acquisition traces in visual encoders: What does CLIP know about your camera?](https://mlsanity.com/paper/2508.10637/) (2025)
- [RAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling](https://mlsanity.com/paper/2605.05941/) (2026)
- [CoAPT: Context Attribute words for Prompt Tuning](https://mlsanity.com/paper/2407.13808/) (2024)
- [Fine-grained Defocus Blur Control for Generative Image Models](https://mlsanity.com/paper/2510.06215/) (2025)
- [Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models](https://mlsanity.com/paper/2512.21337/) (2025)
- [PhotoHolmes: a Python library for forgery detection in digital images](https://mlsanity.com/paper/2412.14969/) (2024)
- [SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks](https://mlsanity.com/paper/2505.15628/) (2025)

## Abstract (arXiv)

We learn a visual representation that captures information about the camera that recorded a given photo. To do this, we train a multimodal embedding between image patches and the EXIF metadata that cameras automatically insert into image files. Our model represents this metadata by simply converting it to text and then processing it with a transformer. The features that we learn significantly outperform other self-supervised and supervised features on downstream image forensics and calibration tasks. In particular, we successfully localize spliced image regions "zero shot" by clustering the visual embeddings for all of the patches within an image.