ARS_S01: Original and AI-Generated Video Scenes for Style Analysis

Scene-level video materials from the 1929 Soviet montage film 'Arsenal' by Oleksandr Dovzhenko, used for comparative analysis of original and AI-generated content. The dataset includes raw and preprocessed videos, prompt files, generation settings, and metadata, totaling 59.2 MB. It was created by Jinyu Kim for a doctoral dissertation and last updated on June 4, 2026.

Use Cases

• Compare visual style between original and AI-generated videos based on the scene-level materials.
• Analyze the impact of generation settings on video output based on the provided configuration files.
• Study the reconfiguration of Soviet montage film style through generative AI based on the described comparative framework.

Strengths

• Includes both raw generated videos and preprocessed versions standardized to 720p, 24 fps, and 8 seconds.
• Contains associated prompt files and generation settings, providing context for the AI video creation process.
• Released under the CC-BY-4.0 license, allowing for open sharing and adaptation.

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 scope of multimodal study.

Provenance

Source

Part of a doctoral dissertation project by Jinyu Kim.

Collection Method

Likely generated using AI video models based on scenes from the specified film.

Time Range

Based on the 1929 film 'Arsenal'.

Freshness

Last updated 2026-06-04 21:02:15; freshness should be verified.