Eigen-Evolution Dense Trajectory Descriptors

摘要

Trajectory-pooled Deep-learning Descriptors have been the state-of-the-art feature descriptors for human action recognition in video on many datasets. This paper improves their performance by applying the proposed eigen-evolution pooling to each trajectory, encoding the temporal evolution of deep learning features computed along the trajectory. This leads to Eigen-Evolution Trajectory (EET) descriptors, a novel type of video descriptor that significantly outperforms Trajectory-pooled Deep-learning Descriptors. EET descriptors are defined based on dense trajectories, and they provide complimentary benefits to video descriptors that are not based on trajectories. Empirically, we observe that the combination of EET descriptors and VideoDarwin outperforms the state-of-the-art methods on the Hollywood2 dataset, and its performance on the UCF101 dataset is close to the state-of-the-art.