# Detecting People in Artwork with CNNs

arXiv: https://arxiv.org/abs/1610.08871 · HTML: https://mlsanity.com/paper/1610.08871/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2016.

## Built on by (most cited first, 25 of 25)

- [Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes](https://mlsanity.com/paper/2303.02760/) (2023)
- [Understanding and Creating Art with AI: Review and Outlook](https://mlsanity.com/paper/2102.09109/) (2021)
- [Adaptive Length Image Tokenization via Recurrent Allocation](https://mlsanity.com/paper/2411.02393/) (2024)
- [Robustness of SAM: Segment Anything Under Corruptions and Beyond](https://mlsanity.com/paper/2306.07713/) (2023)
- [Improving Object Detection in Art Images Using Only Style Transfer](https://mlsanity.com/paper/2102.06529/) (2021)
- [DEArt: Dataset of European Art](https://mlsanity.com/paper/2211.01226/) (2022)
- [Semi-supervised Human Pose Estimation in Art-historical Images](https://mlsanity.com/paper/2207.02976/) (2022)
- [Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History](https://mlsanity.com/paper/2301.05124/) (2023)
- [SniffyArt: The Dataset of Smelling Persons](https://mlsanity.com/paper/2311.11888/) (2023)
- [A deep learning approach to clustering visual arts](https://mlsanity.com/paper/2106.06234/) (2021)
- [Algorithmic Ways of Seeing: Using Object Detection to Facilitate Art Exploration](https://mlsanity.com/paper/2403.19174/) (2024)
- [Seeing Faces in Things: A Model and Dataset for Pareidolia](https://mlsanity.com/paper/2409.16143/) (2024)
- [Transfer Learning for Olfactory Object Detection](https://mlsanity.com/paper/2301.09906/) (2023)
- [Object Retrieval and Localization in Large Art Collections using Deep Multi-Style Feature Fusion and Iterative Voting](https://mlsanity.com/paper/2107.06935/) (2021)
- [Context-Infused Visual Grounding for Art](https://mlsanity.com/paper/2410.12369/) (2024)
- [Stylistic Multi-Task Analysis of Ukiyo-e Woodblock Prints](https://mlsanity.com/paper/2410.12379/) (2024)
- [No Annotations for Object Detection in Art through Stable Diffusion](https://mlsanity.com/paper/2412.06286/) (2024)
- [Smelly, dense, and spreaded: The Object Detection for Olfactory References (ODOR) dataset](https://mlsanity.com/paper/2507.08384/) (2025)
- [Quantitative analysis of visual representation of sign elements in COVID-19 context](https://mlsanity.com/paper/2112.08219/) (2021)
- [Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey](https://mlsanity.com/paper/2412.01450/) (2024)
- [Gesture Classification in Artworks Using Contextual Image Features](https://mlsanity.com/paper/2412.03456/) (2024)
- [Analysis of the use of color and its emotional relationship in visual creations based on experiences during the context of the COVID-19 pandemic](https://mlsanity.com/paper/2203.13770/) (2022)
- [Improving Performance of Object Detection using the Mechanisms of Visual Recognition in Humans](https://mlsanity.com/paper/2301.09667/) (2023)
- [BOOST: Out-of-Distribution-Informed Adaptive Sampling for Bias Mitigation in Stylistic Convolutional Neural Networks](https://mlsanity.com/paper/2507.07134/) (2025)
- [Data Augmentation via Latent Diffusion Models for Detecting Smell-Related Objects in Historical Artworks](https://mlsanity.com/paper/2509.14755/) (2025)

## Abstract (arXiv)

CNNs have massively improved performance in object detection in photographs. However research into object detection in artwork remains limited. We show state-of-the-art performance on a challenging dataset, People-Art, which contains people from photos, cartoons and 41 different artwork movements. We achieve this high performance by fine-tuning a CNN for this task, thus also demonstrating that training CNNs on photos results in overfitting for photos: only the first three or four layers transfer from photos to artwork. Although the CNN's performance is the highest yet, it remains less than 60% AP, suggesting further work is needed for the cross-depiction problem. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-46604-057