Human Action Recognition via Body Part Region Segmented Dense Trajectories

説明

We propose a novel action recognition framework based on trajectory features with human-aware spatial segmentation. Our insight is that the critical features for recognition are appeared in the partial regions of human, thus we segment a video frame into spatial regions based on the human body parts to enhance feature representation. We utilize an object detector and a pose estimator to segment four regions, namely full body, left/right arm, and upper body. From these regions, we extract dense trajectory features and feed them into a shallow RNN to effectively consider the long-term relationships. The evaluation result shows that our framework outperforms previous approaches on the standard two benchmarks, i.e. J-HMDB and MPII Cooking Activities.

詳細情報 詳細情報について

問題の指摘

ページトップへ