dataforgoodfr/13_reveler_inegalites_cinema
Mar 2025 – Mar 2025
1 Month active
Languages Used
Python
Technical Skills
Computer VisionData ProcessingDeep LearningMachine LearningPyTorchPython
Julien-Commes
PROFILE
Julien-commes
Developed an end-to-end machine learning pipeline for the dataforgoodfr/13_reveler_inegalites_cinema repository, focused on analyzing movie trailers to detect and classify individuals within video frames. Leveraging Python, PyTorch, and YOLO, the pipeline automated frame extraction, face detection, filtering, classification, and clustering, with predictions stored directly on the output video to streamline auditing and validation. The workflow emphasized reproducibility and maintainability, featuring improved code comments and a clear structure. This solution reduced the need for manual review, accelerated data collection, and enabled scalable research into representation in cinema, providing a robust and extensible foundation for future video analysis tasks.
Overall Statistics
Feature vs Bugs
100%Features
Repository Contributions
1Total
Bugs
0
Commits
1
Features
1
Lines of code
1,076
Activity Months1
Your Network
12 peopleShared Repositories
12
Audrey DuranMember
FitzfoufouMember
Florian_YunMember
hadrien PoinseauxMember
ndretexMember
LudivineLacourMember
Nicolas RevelMember
Paul GabrielMember
lina kaciMember
Work History
March 2025
1 Commits • 1 Features
Mar 1, 2025March 2025 monthly summary for dataforgoodfr/13_reveler_inegalites_cinema: Delivered the V1 Trailer Analysis ML Pipeline, enabling end-to-end processing of movie trailers to detect and classify individuals, with predictions stored on the output video. This supports scalable research into representation and supports content indexing. Core achievements: implemented frame extraction, face detection, filtering, classification, and clustering; integrated storage of predictions; improved code comments for maintainability; established a reproducible ML pipeline workflow. No major bugs fixed this period. Business impact: reduces manual review, accelerates data collection, enabling data-driven insights into cinema representations; technical impact: robust end-to-end pipeline with extensible design.
1 Commits • 1 Features
Mar 1, 2025March 2025 monthly summary for dataforgoodfr/13_reveler_inegalites_cinema: Delivered the V1 Trailer Analysis ML Pipeline, enabling end-to-end processing of movie trailers to detect and classify individuals, with predictions stored on the output video. This supports scalable research into representation and supports content indexing. Core achievements: implemented frame extraction, face detection, filtering, classification, and clustering; integrated storage of predictions; improved code comments for maintainability; established a reproducible ML pipeline workflow. No major bugs fixed this period. Business impact: reduces manual review, accelerates data collection, enabling data-driven insights into cinema representations; technical impact: robust end-to-end pipeline with extensible design.
March 2025
Activity
Loading activity data...
Quality Metrics
Correctness90.0%
Maintainability80.0%
Architecture90.0%
Performance80.0%
AI Usage80.0%
Skills & Technologies
Programming Languages
Python
Technical Skills
Computer VisionData ProcessingDeep LearningMachine LearningPyTorchPythonVideo AnalysisYOLO
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline