Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding
This work addresses the challenge of making VLMs more inclusive and effective for culturally specific content beyond English-based corpora, though it is incremental as it focuses on dataset creation rather than new model development.
The authors tackled the problem of vision-language models (VLMs) struggling with culturally rich art by creating the Pun Rebus Art Dataset, a multimodal dataset for Chinese pun rebus art understanding, and found that state-of-the-art VLMs perform poorly, often providing biased and hallucinated explanations with limited improvement from in-context learning.
Large vision-language models (VLMs) have demonstrated remarkable abilities in understanding everyday content. However, their performance in the domain of art, particularly culturally rich art forms, remains less explored. As a pearl of human wisdom and creativity, art encapsulates complex cultural narratives and symbolism. In this paper, we offer the Pun Rebus Art Dataset, a multimodal dataset for art understanding deeply rooted in traditional Chinese culture. We focus on three primary tasks: identifying salient visual elements, matching elements with their symbolic meanings, and explanations for the conveyed messages. Our evaluation reveals that state-of-the-art VLMs struggle with these tasks, often providing biased and hallucinated explanations and showing limited improvement through in-context learning. By releasing the Pun Rebus Art Dataset, we aim to facilitate the development of VLMs that can better understand and interpret culturally specific content, promoting greater inclusiveness beyond English-based corpora.