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 pool...

Object recognition is difficult because the appearance of an object changes in many different ways. To recognize objects robustly, one needs representations that are constant despite those changes. Such invariant representations can be obtained by features with low sensitivity to various visual transformations. Spatial pooling is a widely used technique for extracting invariant features from im...

two models are commonly made use to explain the behavior of insurance industries, namely: risk-pooling and the risk-absorbing models. neither of the two models provides an acceptable definition of insurance output in the economies experiencing high inflation rate. to address the deficiencies of the present models, an alternative was proposed in the current study as based on the theory of in...

Fish and long-chain ω-3 polyunsaturated fatty acid (LCω3PUFA) intake in relation to the risk of cardiovascular diseases have been well studied. However, studies that directly link fish consumption or LCω3PUFA intake to the risk of metabolic syndrome (MetS) are sparse and the results are inconsistent. We reviewed literature through December 2014 and used random-effects or fixed-effects models, a...

Convolutional autoencoders (CAEs) are unsupervised feature extractors for high-resolution images. In the preprocessing step, whitening transformation has widely been adopted to remove redundancy by making adjacent pixels less correlated. Pooling is a biologically inspired operation to reduce the resolution of feature maps and achieve spatial invariance in convolutional neural networks. Conventi...

A key step in many image quantification solutions is feature pooling, where subsets of lower-level features are combined so that higher-level, more invariant predictions can be made. The pooling region which defines the subsets often has a fixed spatial size and geometry, but data adaptive pooling regions have also been used. In this paper we investigate pooling strategies for the data adaptive...