Daniel Casanova, Pedro Luiz Paula Filho, Kelyn Schenatto, and Alessandra Hoffmann. 2025.
 Emotion Recognition in Videos: A Comparative Analysis of LSTM, CNNs, YOLO, and Vision Transformers on CMU-MOSEI. In <em>Proceedings of the 22nd Latin American Congress on Free Software and Open Technologies</em>, October 22, 2025, Foz do Iguaçu/PR, Brasil. SBC, Porto Alegre, Brasil, 354-361. DOI: <a href="https://doi.org/10.5753/latinoware.2025.16446">https://doi.org/10.5753/latinoware.2025.16446</a>.