Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation

TL;DR

Hanfu-Bench is a new multimodal dataset that advances cross-temporal cultural understanding and transcreation of traditional Chinese attire, highlighting challenges for vision-language models in capturing cultural and temporal nuances.

Contribution

Introduces Hanfu-Bench, a multimodal dataset with tasks on cultural visual understanding and transcreation, emphasizing temporal aspects of Chinese culture.

Findings

Closed VLMs match non-experts in understanding but lag behind humans by 10%.

Open VLMs perform worse than non-experts.

Best transcreation model achieves only 42% success rate.

Abstract

Culture is a rich and dynamic domain that evolves across both geography and time. However, existing studies on cultural understanding with vision-language models (VLMs) primarily emphasize geographic diversity, often overlooking the critical temporal dimensions. To bridge this gap, we introduce Hanfu-Bench, a novel, expert-curated multimodal dataset. Hanfu, a traditional garment spanning ancient Chinese dynasties, serves as a representative cultural heritage that reflects the profound temporal aspects of Chinese culture while remaining highly popular in Chinese contemporary society. Hanfu-Bench comprises two core tasks: cultural visual understanding and cultural image transcreation. The former task examines temporal-cultural feature recognition based on single- or multi-image inputs through multiple-choice visual question answering, while the latter focuses on transforming traditional attire into modern designs through cultural element inheritance and modern context adaptation. Our evaluation shows that closed VLMs perform comparably to non-experts on visual cutural understanding but fall short by 10% to human experts, while open VLMs lags further behind non-experts. For the transcreation task, multi-faceted human evaluation indicates that the best-performing model achieves a success rate of only 42%. Our benchmark provides an essential testbed, revealing significant challenges in this new direction of temporal cultural understanding and creative adaptation.