FlintstonesSV++: Enhanced Visual Story Narration with Scene Graphs

FlintstonesSV++ is an enhanced version of a dataset for story narration using visual scene graphs. It was created by researchers from the Insight Research Ireland Center for Data Analytics at the University of Galway. The associated paper was accepted at the Text2Story Workshop, ECIR Conference 2025 in Lucca, Italy.

Use Cases

• Training models for visual story narration based on scene graph representations.
• Evaluating story generation systems that integrate visual and textual information.
• Researching the relationship between visual scene structure and narrative coherence.

Strengths

• Dataset is an enhanced version of an existing benchmark, suggesting iterative improvement.
• Associated with a peer-reviewed paper accepted at a 2025 academic workshop.

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

Insight Research Ireland Center for Data Analytics, University of Galway, Ireland.

Collection Method

Likely an enhancement of the original FlintstonesSV dataset, as described in the associated research paper.

Freshness

Last updated 2025-05-27 13:19:46; freshness should be verified.