🍿 Popcorn
Popcorn is a resource for reproducible multimodal movie recommendation. It standardizes data ingestion, representation construction, model training, and evaluation under controlled configurations. The framework is designed to interface directly with standard interaction benchmarks (e.g., MovieLens 100K, 1M, and 25M), enabling straightforward substitution of the underlying user-item feedback source. To respect copyright restrictions, Popcorn-Visual distributes embeddings rather than raw videos, while the framework provides scripts to (re)compute embeddings when users have lawful access to the underlying content
📎 Related Repositories
🔑 License
This project is licensed under the GPL-3.0 license - see the LICENSE for more details.
📬 Contact
If you have any questions or collaboration opportunities, please open an issue or contact the authors.