We study novel approaches for automatically discovering typical and anomalous spatio-temporal patterns in complex dynamic scenes. Our works are based on unsupervised learning models, such as deep autoencoders and convex clustering.
D. Xu, E. Ricci, Y. Yan, J. Song, N. Sebe: “Learning Deep Representations of Appearance and Motion for Anomalous Event Detection”, In British Machine Vision Conference (BMVC), 2015.
E. Ricci, G. Zen, N. Sebe, S. Messelodi. “A Prototype Learning Framework using EMD: Application to Complex Scenes Analysis”, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). 2013.