Eigen Evolution Pooling for Human Action Recognition
arXiv:1708.05465
Abstract
We introduce Eigen Evolution Pooling, an efficient method to aggregate a sequence of feature vectors. Eigen evolution pooling is designed to produce compact feature representations for a sequence of feature vectors, while maximally preserving as much information about the sequence as possible, especially the temporal evolution of the features over time. Eigen evolution pooling is a general pooling method that can be applied to any sequence of feature vectors, from low-level RGB values to high-level Convolutional Neural Network (CNN) feature vectors. We show that eigen evolution pooling is more effective than average, max, and rank pooling for encoding the dynamics of human actions in video. We demonstrate the power of eigen evolution pooling on UCF101 and Hollywood2 datasets, two human action recognition benchmarks, and achieve state-of-the-art performance.
References in corpus (5)
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- Real-time Action Recognition with Enhanced Motion Vector CNNs
- Generalized Rank Pooling for Activity Recognition