Exploiting Image-trained CNN Architectures for Unconstrained Video Classification

We conduct an in-depth exploration of different strategies for doing event detection in videos using convolutional neural networks (CNNs) trained for image classification. We study different ways of performing spatial and temporal pooling, feature normalization, choice of CNN layers as well as choice of classifiers. Making judicious choices along these dimensions led to a very significant increase in performance over more naive approaches that have been used till now. We evaluate our approach on the challenging TRECVID MED14 dataset with two popular CNN architectures pretrained on ImageNet. On this MED14 dataset, our methods, based entirely on image-trained CNN features, can outperform several state-of-the-art non-CNN models. Our proposed late fusion of CNN- and motion-based features can further increase the mean average precision (mAP) on MED14 from 34.95% to 38.74%. The fusion approach achieves the state-of-the-art classification performance on the challenging UCF-101 dataset.

A CURE for noisy magnetic resonance images: Chi-square unbiased risk estimation

In this article we derive an unbiased expression for the expected mean-squared error associated with continuously differentiable estimators of the noncentrality parameter of a chi-square random variable. We then consider the task of denoising squared-magnitude magnetic resonance image data, which are well modeled as independent noncentral chi-square random variables on two degrees of freedom. We consider two broad classes of linearly parameterized shrinkage estimators that can be optimized using our risk estimate, one in the general context of undecimated filterbank transforms, and another in the specific case of the unnormalized Haar wavelet transform. The resultant algorithms are computationally tractable and improve upon state-of-the-art methods for both simulated and actual magnetic resonance image data.