L4C_S01: AI-Generated Video Style Analysis for The 400 Blows

A doctoral dissertation project provides scene-level video materials for a comparative analysis of original and AI-generated content. The 63.7 MB dataset includes RAW and PRE-processed videos, prompt files, generation settings, and metadata for the 1959 French New Wave film 'The 400 Blows'. It was authored by Jinyu Kim and last updated on figshare in June 2026.

Use Cases

• Comparative visual analysis of original vs. AI-generated film scenes based on the provided video pairs.
• Studying the reconfiguration of French New Wave film style through generative AI models.
• Analyzing the effect of standardized preprocessing (720p, 24 fps, 8 seconds) on video style analysis.
• Investigating the relationship between textual prompts, generation settings, and resulting video output.

Strengths

• Includes both RAW generated videos and standardized PRE-processed versions (720p, 24 fps, 8 seconds) for consistent analysis.
• Provides associated prompt files and generation settings, enabling reproducibility and parameter study.
• Clear provenance linking the scene (L4C_S01) to a specific, well-known film ('The 400 Blows', 1959).

Limitations

• Row count is unknown, which may limit suitability assessment for large-scale statistical analysis.
• Column-level documentation is absent; field semantics must be inferred after download.
• Audio is explicitly excluded from the analysis, limiting the scope to visual style.

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 film's release year, the source material is from 1959.

Freshness

Last updated 2026-06-04 20:59:46; freshness should be verified.

Geography

The source film is a French production.