Scaling up Cast Face Detection in Videos at Globo

• Felipe A. Ferreira PUC-Rio / Globo
• Bruno P. Oliveira Globo
• Rodrigo V. Kassick Globo
• Vinícius Furlan Globo
• Hélio Lopes PUC-Rio

DOI: https://doi.org/10.5753/semish.2021.15816

Resumo

It has been recognized that a significant increase in the production and consumption of video content occurred in the last decade. Many entertainment companies, like Globo, face challenges regarding video metadata generation. The objective of this paper is to present a suitable architecture for the Globo Group to automatically identify actors that appear in each scene of a video stream, generating new metadata annotations that can be used by recommender systems and search engines among different other applications in this industry sector.

Palavras-chave: computer vision, face recognition, video metadata

Referências

Castellano, B. (2012). Pyscenedetect.Journal Title, 13(52):123–456.

Pena, R.; Ferreira, F. A.; Caroli, F.; Silva, L. J. S.; and Lopes, H. (2020). Globo facestream: A system for video meta-data generation in an entertainment industry setting. In ICEIS 2020.

Sax, M. J. (2019). Apache kafka. In Sakr, S. and Zomaya, A. Y., editors, Encyclopedia of Big Data Technologies. Springer.

Schroff, F.; Kalenichenko, D.; and Philbin, J. (2015). Facenet: A unified embedding forface recognition and clustering. CoRR, abs/1503.03832