ArtECulture Benchmark
Explore score history ↗ArtECulture is a benchmark for culture-conditioned visual emotion understanding with 6,792 artworks and culture-specific labels across three cultures. It evaluates MLLMs on predicting cultural emotion perception and explaining rationale.
- Released
- 2026-08-04
- Institutions
- National University of Singapore · Southern University of Science and Technology · Nanyang Technological University
- Evaluates
- General AI, Multimodal
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
ArtECulture paper
No reported scores are on record for this benchmark yet.