CiQi-VQA: Visual Question Answering on Chinese Porcelain Artifacts

A multimodal dataset for cultural reasoning on antique Chinese porcelains, created by SII-Monument-Valley. The dataset is part of the CiQi-Agent project, which aligns visual perception, tool-augmented reasoning, and cultural knowledge. It was last updated on April 1, 2026.

Use Cases

• Train multimodal agents for fine-grained visual perception of cultural artifacts based on the dataset's focus.
• Benchmark visual question answering systems on domain-specific cultural reasoning tasks.
• Ground AI models in cultural-heritage knowledge for antique connoisseurship applications.

Strengths

• Dataset is part of a published research project with a linked paper, suggesting academic rigor.
• Platform tags indicate specific domains like Chinese Art, Cultural Heritage, and Multimodal VQA.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

SII-Monument-Valley via Hugging Face.

Collection Method

Likely created for the CiQi-Agent research project, aligning vision, tools, and aesthetics.

Time Range

null

Freshness

Last updated 2026-04-01 09:18:49; freshness should be verified.

Geography

Focus on Chinese porcelains, suggesting a cultural and geographic focus on China.