In this work, we select three public video datasets commonly used for violence recognition and crowd behavior understanding: Real-Life Violence Situations (RLVS), RWF–2000, and HockeyFight. These datasets include aggressive behaviors such as interactions with crowds, crowd provocation, and non-violent actions in difficult, uncontrolled real-world settings.

For this study, we chose three publicly available video datasets that researchers frequently use to analyze violent behavior and understand crowd dynamics: Real-Life Violence Situations (RLVS), RWF-2000, and HockeyFight. These collections contain footage of aggressive conduct, including crowd interactions and provocative incidents, along with non-violent activities, all captured in challenging and uncontrolled real-world environments.