ViVoLab and CVLab - MediaEval 2014: Violent Scenes Detection Affect Task
Diego Castán, Mario Rodríguez, Alfonso Ortega, Carlos Orrite, Eduardo Lleida · 2014
This paper describes the ViVoLab/CVLab system to pro-vide segments of violent scenes from Hollywood movies and “wild-user ” videos from the internet. We propose a system based on a fusion of acoustic features, audio concepts and video features. Our joint audio-visual approach achieves MAP2014 values of 17.81 % and 43.03%, for the main task and the generalization task, respectively. 1.