Finding Action Tubes
This work addresses action detection in videos, which is an incremental improvement over existing methods.
The paper tackles action detection in videos by building models using shape and kinematic cues, incorporating appearance and motion to reduce region proposals and extract spatio-temporal features, resulting in outperforming other techniques.
We address the problem of action detection in videos. Driven by the latest progress in object detection from 2D images, we build action models using rich feature hierarchies derived from shape and kinematic cues. We incorporate appearance and motion in two ways. First, starting from image region proposals we select those that are motion salient and thus are more likely to contain the action. This leads to a significant reduction in the number of regions being processed and allows for faster computations. Second, we extract spatio-temporal feature representations to build strong classifiers using Convolutional Neural Networks. We link our predictions to produce detections consistent in time, which we call action tubes. We show that our approach outperforms other techniques in the task of action detection.