Over the past few years, Convolutional Neural Networks (CNNs) have shown promise on facial expression recognition. However, the performance degrades dramatically under real-world settings due to variations introduced by subtle facial appearance changes, head pose variations, illumination changes, and occlusions.In this paper, a novel island loss is proposed to enhance the discriminative power of the deeply learned features. Specifically, the IL is designed to reduce the intra-class variations while enlarging the inter-class differences simultaneously. Experimental results on four benchmark expression databases have demonstrated that the CNN with the proposed island loss (IL-CNN) outperforms the baseline CNN models with either traditional softmax loss or the center loss and achieves comparable or better performance compared with the state-of-the-art methods for facial expression recognition.

Recognizing facial action units (AUs) during spontaneous facial displays is a challenging problem. Most recently, Convolutional Neural Networks (CNNs) have shown promise for facial AU recognition, where predefined and fixed convolution filter sizes are employed. In order to achieve the best performance, the optimal filter size is often empirically found by conducting extensive experimental validation. Such a training process suffers from expensive training cost, especially as the network becomes deeper.This paper proposes a novel Optimized Filter Size CNN (OFS-CNN), where the filter sizes and weights of all convolutional layers are learned simultaneously from the training data along with learning convolution filters. Specifically, the filter size is defined as a continuous variable, which is optimized by minimizing the training loss. Experimental results on two AU-coded spontaneous databases have shown that the proposed OFS-CNN is capable of estimating optimal filter size for varying image resolution and outperforms traditional CNNs with the best filter size obtained by exhaustive search. The OFS-CNN also beats the CNN using multiple filter sizes and more importantly, is much more efficient during testing with the proposed forward-backward propagation algorithm.

the FDA to require that it be notified of all GRAS determinations and the financial conflicts of interest of those who make these determinations. The agency should routinely make pub-lic all notifications of GRAS determinations, including those made by the FEMA panel, and all the information that it receives about conflicts of interest in these determinations. ARTICLE INFORMATION

The potential role of oestrogenic agents, antioxidants and intestinal glucose-uptake inhibitors in the treatment of diabetes is briefly reviewed. Reports in the literature suggest that oestrogen replacement therapy may favourably modulate glucose homeostasis. A soya phytochemical extract (SPE) containing the isoflavone phytoestrogens genistein and daidzein (mostly in their glycone forms as genistin and daidzin) was investigated as an antioxidant and modulator of intestinal glucose-transport. In the present study, SPE was found to protect against glucose-induced oxidation of human low density lipoproteins (LDL) in vitro. Equol (a gut bacterial metabolite of daidzein) was a more effective antioxidant than daidzein or genistein in this system and was of similar antioxidant potency to the dietary flavonols quercetin and kaempferol and to the endogenous antioxidant 17beta-oestradiol. SPE was found to be an inhibitor of glucose uptake into rabbit intestinal brush border membrane vesicles in vitro, though of weaker potency than the classical sodium dependent glucose transporter (SGLT) inhibitor, phlorizin. Thus SPE displays a range of properties which may be of benefit in diabetes, namely as an oestrogenic agent, an inhibitor of intestinal glucose-uptake and a preventive agent for glucose-induced lipid peroxidation.

A novel Identity-Free conditional Generative Adversarial Network (IF-GAN) was proposed for Facial Expression Recognition (FER) to explicitly reduce high inter-subject variations caused by identity-related facial attributes, e.g., age, race, and gender. As part of an end-to-end system, a cGAN was designed to transform a given input facial expression to an "average" identity face with the same expression as the input. Then, identity-free FER is possible since the generated images have the same synthetic "average" identity and differ only in their displayed expressions. Experiments on four facial expression datasets, one with spontaneous expressions, show that IF-GAN outperforms the baseline CNN and achieves state-of-the-art performance for FER.