ViInfographicVQA is a Vietnamese Visual Question Answering benchmark for infographic understanding. It likely contains data-rich visuals mixing text, charts, maps, and design elements. The dataset was created by duytranus and was last updated on November 14, 2025.
Use Cases
- Benchmark model performance on Vietnamese infographic understanding based on the described evaluation setting.
- Train models to read and synthesize information from layout-heavy visuals based on the described infographic content.
- Develop reasoning capabilities across multiple related infographics based on the described multi-image VQA setting.
Strengths
- Evaluates models on two distinct settings: single-image and multi-image VQA.
- Focuses on data-rich, layout-heavy visuals that mix text, charts, maps, and design elements.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
Provenance
- Source
- duytranus
- Freshness
- Last updated 2025-11-14 12:46:45