Multiple Granularity Group Interaction Prediction

Taiping Yao, Minsi Wang, Bingbing Ni, Huawei Wei, Xiaokang Yang

Abstract: Most human activity analysis works (i.e., recognition or　prediction) only focus on a single granularity, i.e., either　modelling global motion based on the coarse level movement such as human trajectories or　forecasting future detailed action based on body parts’ movement such as skeleton motion. In contrast, in this work, we propose a multi-granularity interaction prediction network which integrates　both global motion and detailed local action. Built on a bi- directional LSTM network, the　proposed method possesses　between granularities links which encourage feature sharing as well as cross-feature consistency between both global　and local granularity (e.g., trajectory or local action), and in turn predict long-term global location and local dynamics of each individual. We validate our method on several　public datasets with promising performance.