Classifying facial expressions into different categories requires capturing regional distortions of facial landmarks. We believe that second-order statistics such as covariance is better able to capture such distortions in regional facial features. In this work, we explore the benefits of using a manifold network structure for covariance pooling to improve facial expression recognition. In particular, we first employ such kind of manifold networks in conjunction with traditional convolutional networks for spatial pooling within individual image feature maps in an end-to-end deep learning manner. By doing so, we are able to achieve a recognition accuracy of 58.14% on the validation set of Static Facial Expressions in the Wild (SFEW 2.0) and 87.0% on the validation set of Real-World Affective Faces (RAF) Database 1 . Both of these results are the best results we are aware of. Besides, we leverage covariance pooling to capture the temporal evolution of per-frame features for video-based facial expression recognition. Our reported results demonstrate the advantage of pooling image-set features temporally by stacking the designed manifold network of covariance pooling on top of convolutional network layers. arXiv:1805.04855v1 [cs.CV] 13 May 2018Accordingly, the core techniques of the two proposed models are spatial/temporal covariance pooling and the manifold network for learning the second-order features deeply. In the following we will introduce the two crucial techniques.

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of highdimensional distributions. In contrast, the sliced Wasserstein distance (SWD) factorizes high-dimensional distributions into their multiple one-dimensional marginal distributions and is thus easier to approximate.In this paper, we introduce novel approximations of the primal and dual SWD. Instead of using a large number of random projections, as it is done by conventional SWD approximation methods, we propose to approximate SWDs with a small number of parameterized orthogonal projections in an end-to-end deep learning fashion. As concrete applications of our SWD approximations, we design two types of differentiable SWD blocks to equip modern generative frameworks-Auto-Encoders (AE) and Generative Adversarial Networks (GAN).In the experiments, we not only show the superiority of the proposed generative models on standard image synthesis benchmarks, but also demonstrate the state-of-the-art performance on challenging high resolution image and video generation in an unsupervised manner 1 .

In many domains of computer vision, generative adversarial networks (GANs) have achieved great success, among which the family of Wasserstein GANs (WGANs) is considered to be state-of-the-art due to the theoretical contributions and competitive qualitative performance. However, it is very challenging to approximate the k-Lipschitz constraint required by the Wasserstein-1 metric (W-met). In this paper, we propose a novel Wasserstein divergence (W-div), which is a relaxed version of W-met and does not require the k-Lipschitz constraint. As a concrete application, we introduce a Wasserstein divergence objective for GANs (WGAN-div), which can faithfully approximate Wdiv through optimization. Under various settings, including progressive growing training, we demonstrate the stability of the proposed WGANdiv owing to its theoretical and practical advantages over WGANs. Also, we study the quantitative and visual performance of WGAN-div on standard image synthesis benchmarks, showing the superior performance of WGAN-div compared to the state-of-the-art methods.

Information security is one of the most important factors to be considered when secret information has to be communicated between two parties. Cryptography and steganography are the two techniques used for this purpose. Cryptography scrambles the information, but it reveals the existence of the information. Steganography hides the actual existence of the information so that anyone else other than the sender and the recipient cannot recognize the transmission. In steganography the secret information to be communicated is hidden in some other carrier in such a way that the secret information is invisible. In this paper an image steganography technique is proposed to hide audio signal in image in the transform domain using wavelet transform. The audio signal in any format (MP3 or WAV or any other type) is encrypted and carried by the image without revealing the existence to anybody. When the secret information is hidden in the carrier the result is the stego signal. In this work, the results show good quality stego signal and the stego signal is analyzed for different attacks. It is found that the technique is robust and it can withstand the attacks. The quality of the stego image is measured by Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Metric (SSIM), Universal Image Quality Index (UIQI). The quality of extracted secret audio signal is measured by Signal to Noise Ratio (SNR), Squared Pearson Correlation Coefficient (SPCC). The results show good values for these metrics.

No abstract