Uncertainty-Aware Art-Historical Dating with Vision-Language Models

2026-08-19

AI Summary

研究通过将艺术品断代视为不确定性感知回归任务，使用视觉-语言模型处理博物馆数据集中的时间纠缠问题，揭示了模型中存在的时间信息及偏差。

Abstract

Museum and archival datasets do not mirror historical artistic production, but materialize the contingent histories of collecting, preservation, cataloging, and digitization. This has direct consequences for interpreting pretrained image representations: they may appear to encode historical time while actually encoding the institutional conditions under which objects become visible as data. We describe this phenomenon as temporal entanglement and investigate it by formulating artwork dating as an uncertainty-aware regression task over frozen image embeddings. We evaluate several pretrained vision models on a temporally controlled Wikidata corpus of artworks. Our results show that these models contain usable temporal information, with Vision-Language Models (VLMs) outperforming purely visual self-supervised baselines. However, a qualitative analysis indicates that this temporal knowledge is shaped by various biases.

Problem

• temporal entanglement
• uncertainty-aware regression
• pretrained vision models
• artwork dating

Innovation

• Uncertainty-Aware Regression
• Vision-Language Models
• Temporal Entanglement