Palavras-chave
Deep learning
Sensitive content
Elsagate
Sensitive content
Elsagate
Como Citar
ISHIKAWA, Akari; AVILA, Sandra; BOLLIS, Edson. What are kids watching at youtube? Elsagate detection through deep neural networks. Revista dos Trabalhos de Iniciação Científica da UNICAMP, Campinas, SP, n. 27, p. 1–1, 2019. DOI: 10.20396/revpibic2720192770. Disponível em: https://econtents.sbu.unicamp.br/eventos/index.php/pibic/article/view/2770. Acesso em: 18 mar. 2026.
Resumo
Despite YouTube’s efforts to block violent and pornographic content from its platform, it is not prepared to deal with the Elsagate phenomenon. As a first to introduce the disturbing cartoons to the literature, we propose along with a dataset a pipeline that classifies Elsagate videos with 92.6% of accuracy and discuss the subjectivity of this problem.
Referências
Ishikawa, Akari, Edson Bollis, and Sandra Avila. "Combating the Elsagate phenomenon: Deep learning architectures for disturbing cartoons." arXiv preprint arXiv:1904.08910 (2019).
Perez, Mauricio, et al. "Video pornography detection through deep learning techniques and motion information." Neurocomputing 230 (2017): 279-293.
Perez, Mauricio, et al. "Video pornography detection through deep learning techniques and motion information." Neurocomputing 230 (2017): 279-293.
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
Copyright (c) 2019 Revista dos Trabalhos de Iniciação Científica da UNICAMP