BIC_S01: Scene-Level Video Materials for AI-Generated Style Analysis

Jinyu Kim's doctoral dissertation project provides scene-level video materials for a comparative analysis of original and AI-generated videos. The dataset includes RAW and PRE videos, prompt files, generation settings, and metadata for the 1948 Italian Neorealist film 'Bicycle Thieves'. The 111.4 MB collection was last updated on June 4, 2026.

Use Cases

• Comparative analysis of original and AI-generated video styles based on scene-level materials.
• Training or evaluating generative AI video models using standardized 720p, 24 fps, 8-second video clips.
• Studying the reconfiguration of Italian Neorealist film aesthetics through AI models based on the provided film metadata.

Strengths

• Includes both RAW generated videos and PRE videos standardized to 720p, 24 fps, and 8 seconds for consistent analysis.
• Provides associated metadata, prompt files, and generation settings, which likely aids in reproducibility.
• Released under a permissive CC-BY-4.0 license, facilitating open research use.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Audio is excluded from the analysis, limiting the dataset's scope for multimodal studies.

Provenance

Source

Part of a doctoral dissertation project by Jinyu Kim, shared via figshare.

Collection Method

Likely created by processing the film 'Bicycle Thieves' with generative AI video models.

Time Range

The source film is from 1948; the dataset creation date is not specified.

Freshness

Last updated 2026-06-04 21:03:54; freshness should be verified.