A Comparative Analysis of Contrastive and Generative Vision-Language Models for Zero-Shot Behavior Recognition in Surveillance Videos. Engineering Systems and Intelligent Technologies (ESIT), [S. l.], v. 3, n. 1, p. 23–37, 2026. DOI: 10.66279/vcth9h10. Disponível em: https://pub.scientificirg.com/index.php/ESIT/article/view/241. Acesso em: 2 jul. 2026.