Scribe Verification in Chinese manuscripts using Siamese, Triplet, and Vision Transformer Neural Networks
This addresses the problem of authenticating scribes in historical manuscripts for researchers and archivists, but it is incremental as it applies existing methods to a specific domain.
The paper tackled scribe verification in Chinese manuscripts by comparing deep metric learning models, finding that a MobileNetV3+ Custom Siamese model with contrastive loss achieved the best or second-best accuracy and AUC on two datasets.
The paper examines deep learning models for scribe verification in Chinese manuscripts. That is, to automatically determine whether two manuscript fragments were written by the same scribe using deep metric learning methods. Two datasets were used: the Tsinghua Bamboo Slips Dataset and a selected subset of the Multi-Attribute Chinese Calligraphy Dataset, focusing on the calligraphers with a large number of samples. Siamese and Triplet neural network architectures are implemented, including convolutional and Transformer-based models. The experimental results show that the MobileNetV3+ Custom Siamese model trained with contrastive loss achieves either the best or the second-best overall accuracy and area under the Receiver Operating Characteristic Curve on both datasets.