Multimodal Attention-Based Mixture of Experts for Video-Level Activity Recognition using the YouTube-8M Dataset. ITEGAM-JETIA, [S. l.], v. 12, n. 61, p. 1490–1499, 2026. DOI: 10.5935/jetia.v12i61.4267. Disponível em: https://itegam-jetia.org/journal/index.php/jetia/article/view/4267. Acesso em: 22 oct. 2026.