Deep Point-wise Prediction for Action Temporal Proposal
This addresses the challenge of real-time action detection in videos for computer vision applications, representing an incremental improvement over previous methods.
The paper tackles the problem of temporal action proposal generation in videos by introducing Deep Point-wise Prediction (DPP), which simultaneously predicts action existence and temporal locations without handcrafted sliding windows or grouping, achieving over 1000 frames per second on the THUMOS14 dataset.
Detecting actions in videos is an important yet challenging task. Previous works usually utilize (a) sliding window paradigms, or (b) per-frame action scoring and grouping to enumerate the possible temporal locations. Their performances are also limited to the designs of sliding windows or grouping strategies. In this paper, we present a simple and effective method for temporal action proposal generation, named Deep Point-wise Prediction (DPP). DPP simultaneously predicts the action existing possibility and the corresponding temporal locations, without the utilization of any handcrafted sliding window or grouping. The whole system is end-to-end trained with joint loss of temporal action proposal classification and location prediction. We conduct extensive experiments to verify its effectiveness, generality and robustness on standard THUMOS14 dataset. DPP runs more than 1000 frames per second, which largely satisfies the real-time requirement. The code is available at https://github.com/liluxuan1997/DPP.