DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain
Recent advancements in Vision-Language Models (VLMs) have revolutionized general visual understanding. However, their application in the food domain remains constrained by benchmarks that rely on coarse-grained categories, single-view imagery, and inaccurate metadata. To bridge this gap, we introduce DiningBench, a hierarchical, multi-view benchmark designed to evaluate VLMs across three levels of cognitive complexity: Fine-Grained Classification, Nutrition Estimation, and Visual Question Answering. Unlike previous datasets, DiningBench comprises 3,021 distinct dishes with an average of 5.27 images per entry, incorporating fine-grained "hard" negatives from identical menus and rigorous, v...
| Authors | Song Jin, Juntian Zhang, Xun Zhang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 12 April 2026 |
| Last updated at source | 12 April 2026 |
Connected in the knowledge graph
- meituan/DiningBenchDataset · cited by
Models and datasets referencing this paper
- meituan/DiningBenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.