Motion Part Regularization: Improving Action Recognition via Trajectory Selection

Dense local motion features such as dense trajectories have been widely used in action recognition. For most actions, only a few local features (e.g., critical movements of the hand, arm, leg etc.) are responsible to the action label. Therefore, discovering important motion part will lead to a more discriminative and compact action representation. Inspired by the recent advance in sentence regularization for text classification, we introduce a Motion Part Regularization framework to mining discriminative semi-local groups of dense trajectories. First, motion part candidates are generated by spatio-temporal grouping of densely sampled trajectories. Then, we develop a learning objective function which encourages sparse selection for these trajectory groups in conjunction with a discriminative term. We propose an alternative optimization algorithm to efficiently solve this objective function by introducing a set of auxiliary variables. The learned trajectory group weights are further utilized for weighted bag-of-feature representation for unknown action samples. The proposed motion part regularization framework achieves the state-of-the-art performances on several action recognition benchmarks.