Earth mover's prototypes: A convex learning approach for discovering activity patterns in dynamic scenes

We present a novel approach for automatically discovering spatio-temporal patterns in complex dynamic scenes. Similarly to recent non-object centric methods, we use low level visual cues to detect atomic activities and then con- struct clip histograms. Differently from previous works, we formulate the task of discovering high level activity pat- terns as a prototype learning problem where the correla- tion among atomic activities is explicitly taken into account when grouping clip histograms. Interestingly at the core of our approach there is a convex optimization problem which allows us to efficiently extract patterns at multiple levels of detail. The effectiveness of our method is demonstrated on publicly available datasets.