# Archival Faces: Detection of Faces in Digitized Historical Documents

arXiv: https://arxiv.org/abs/2504.00558 · HTML: https://mlsanity.com/paper/2504.00558/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 47 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 30 of 34)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Whole-Body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2007.11858/) (2020)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)
- [DSFD: Dual Shot Face Detector](https://mlsanity.com/paper/1810.10220/) (2018)
- [Sample and Computation Redistribution for Efficient Face Detection](https://mlsanity.com/paper/2105.04714/) (2021)
- [PyramidBox: A Context-assisted Single Shot Face Detector](https://mlsanity.com/paper/1803.07737/) (2018)
- [YOLO5Face: Why Reinventing a Face Detector](https://mlsanity.com/paper/2105.12931/) (2021)
- [SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation](https://mlsanity.com/paper/2308.11509/) (2023)
- [Towards Data-Efficient Detection Transformers](https://mlsanity.com/paper/2203.09507/) (2022)
- [TinaFace: Strong but Simple Baseline for Face Detection](https://mlsanity.com/paper/2011.13183/) (2020)
- [TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security](https://mlsanity.com/paper/2308.10133/) (2023)
- [Selective Refinement Network for High Performance Face Detection](https://mlsanity.com/paper/1809.02693/) (2018)
- [docExtractor: An off-the-shelf historical document element extraction](https://mlsanity.com/paper/2012.08191/) (2020)
- [YOLO-FaceV2: A Scale and Occlusion Aware Face Detector](https://mlsanity.com/paper/2208.02019/) (2022)
- [HORAE: an annotated dataset of books of hours](https://mlsanity.com/paper/2012.00351/) (2020)
- [MogFace: Towards a Deeper Appreciation on Face Detection](https://mlsanity.com/paper/2103.11139/) (2021)
- [Robust Face Detection via Learning Small Faces on Hard Images](https://mlsanity.com/paper/1811.11662/) (2018)

## Abstract (arXiv)

When digitizing historical archives, it is necessary to search for the faces of celebrities and ordinary people, especially in newspapers, link them to the surrounding text, and make them searchable. Existing face detectors on datasets of scanned historical documents fail remarkably -- current detection tools only achieve around 24% mAP at 50:90% IoU. This work compensates for this failure by introducing a new manually annotated domain-specific dataset in the style of the popular Wider Face dataset, containing 2.2k new images from digitized historical newspapers from the 19th to 20th century, with 11k new bounding-box annotations and associated facial landmarks. This dataset allows existing detectors to be retrained to bring their results closer to the standard in the field of face detection in the wild. We report several experimental results comparing different families of fine-tuned detectors against publicly available pre-trained face detectors and ablation studies of multiple detector sizes with comprehensive detection and landmark prediction performance results.