Dare To Plagiarize? Plagiarized Painting Recognition And Retrieval

Abstract

Art plagiarism detection plays a crucial role in protecting artists' copyrights and intellectual property, yet it remains a challenging problem in forensic analysis. In this paper, we address the task of recognizing plagiarized paintings and explaining the detected plagarisms by retrieving visually similar authentic artworks. To support this study, we construct a dataset by collecting painting photos and synthesizing plagiarized versions using generative AI, tailored to specific artists' styles. We first establish a baseline approach using off-the-shelf features from the visual foundation model DINOv2 to retrieve the most similar images in the database and classify plagiarism based on a similarity threshold. Surprisingly, this non-learned method achieves a high recognition accuracy of 97.2% but suffers from low retrieval precision 29.0% average precision (AP). To improve retrieval quality, we finetune DINOv2 with a metric learning loss using positive and negative sample pairs sampled i

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhou2025dare

Related papers

• Visual Link Retrieval And Knowledge Discovery In Painting Datasets (2020)12.25
• Museum Painting Retrieval (2021)0.00
• Diffusion Art Or Digital Forgery? Investigating Data Replication In Diffusion Models (2022)15.75
• Leveraging Computer Vision Application In Visual Arts: A Case Study On The Use Of Residual Neural Network To Classify And Analyze Baroque Paintings (2022)3.58
• Deep Convolutional Embedding For Digitized Painting Clustering (2020)7.50
• Ai-based Copyright Detection Of An Image In A Video Using Degree Of Similarity And Image Hashing (2024)0.00
• A Deep Learning Approach To Clustering Visual Arts (2021)10.61
• Linking Art Through Human Poses (2019)10.74