SciCombinator

Discover the most talked about and latest scientific content & concepts.

 

0

The comorbidity of obsessive-compulsive disorder (OCD) and personality disorders (PDs) is frequent but there are conflicting findings about which PDs are the most common. This study aimed to investigate the personality beliefs that exist on a more pathological level among OCD patients, to explore the association between personality beliefs and OCD severity, and to clarify the mediator effect of depression in this relationship.

0

This study investigated the treatment response and cognitive enhancement effects of buspirone augmentation of escitalopram in patients with major depressive disorder (MDD), according to atypical feature subtypes of MDD.

0

We aimed to explore the differential impact of cigarette smoking on fracture risks in SCD and dementia.

0

Several lines of evidence support a relationship between circadian rhythms disruption in the onset, course, and maintenance of mental disorders. Despite the study of circadian phenotypes promising a decent understanding of the pathophysiologic or etiologic mechanisms of psychiatric entities, several questions still need to be addressed. In this review, we aimed to synthesize the literature investigating chronobiologic theories and their associations with psychiatric entities.

0

This study aimed to examine the associations between multiple modifiable risk/protective factors and the onset of cognitive impairment, using nationally representative panel data spanning 10 years.

0

Gait, the walking pattern of individuals, is one of the important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as gait features. These methods suffer from degraded recognition performance when handling confounding variables, such as clothing, carrying and view angle. To remedy this issue, we propose a novel AutoEncoder framework, GaitNet, to explicitly disentangle appearance, canonical and pose features from RGB imagery. The LSTM integrates pose features over time as dynamic gait feature while canonical features are averaged as static gait feature. Both of them are utilized as classification features. In addition, we collect a Frontal-View Gait (FVG) dataset to focus on gait recognition from frontal-view walking, which is a challenging problem since it contains minimal gait cues compared to other views. FVG also includes other important variations, e.g., walking speed, carrying, and clothing. With extensive experiments on CASIA-B, USF, and FVG datasets, our method demonstrates superior performance to the SOTA quantitatively, the ability of feature disentanglement qualitatively, and promising computational efficiency. We further compare our GaitNet with state of the art face recognition to demonstrate the advantages of gait biometrics identification under certain scenarios, e.g., long distance/ lower resolutions, cross view angles.

0

Recent years witness the booming trend of applying Generative Adversarial Nets (GAN) and its variants to image style transfer. Although many reported results strongly demonstrate the power of GAN on this task, there is still little known about neither the interpretations of several fundamental phenomenons of image style transfer by generative adversarial learning, nor its underlying mechanism. To bridge this gap, this paper presents a general framework for analyzing style transfer with adversarial learning through the lens of differential geometry. To demonstrate the utility of our proposed framework, we provide an in-depth analysis of Isola et al.’s pioneering style transfer model pix2pix and reach a comprehensive interpretation on their major experimental phenomena. Furthermore, we extend the notion of generalization to conditional GAN and derive a condition to control the generalization capability of the pix2pix model. From a higher viewpoint, we further prove a learning-free condition to guarantee the existence of infinitely many perfect style transfer mappings. Besides, we also provide a number of practical suggestions on model design and dataset construction based on these derived theoretical results to facilitate further researches.

0

In this paper, we propose a deep Age-Invariant Model (AIM) for face recognition in the wild with three distinct novelties. First, AIM presents a novel unified deep architecture jointly performing cross-age face synthesis and recognition in a mutual boosting way. Second, AIM achieves continuous face rejuvenation/aging with remarkable photorealistic and identity-preserving properties, avoiding the requirement of paired data and the true age of testing samples. Third, effective and novel training strategies are developed for end-to-end learning of the whole deep architecture, which generates powerful age-invariant face representations explicitly disentangled from the age variation. Moreover, we construct a new large-scale Cross-Age Face Recognition (CAFR) benchmark dataset to facilitate existing efforts and push the frontiers of age-invariant face recognition research. Extensive experiments on both our CAFR dataset and several other cross-age datasets (MORPH, CACD, and FG-NET) demonstrate the superiority of the proposed AIM model over the state-of-the-arts. Benchmarking our model on the popular unconstrained face recognition datasets YTF and IJB-C additionally verifies its promising generalization ability in recognizing faces in the wild.

0

In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models, but also bridges the theoretical gap between traditional Convolutional Neural Network (CNN) models and spatially-based GCN models. Furthermore, the proposed BASGCN model can both adaptively discriminate the importance between specified vertices during the convolution process and reduce the notorious tottering problem of existing spatially-based GCNs related to the Weisfeiler-Lehman algorithm, explaining the effectiveness of the proposed model. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model.

0

Generative adversarial networks (GANs) have shown remarkable success in generating realistic data from some predefined prior distributions. However, such prior distributions are often independent of real data and thus may lose semantic information of data. In practice, the semantic information might be represented by some latent distribution learned from data. However, such latent distribution may incur difficulties in data sampling for GAN methods. In this paper, rather than sampling from the predefined prior distribution, we propose a local coordinate coding GAN (LCCGAN-v1) to improve the performance of GANs. First, we propose a local coordinate coding (LCC)-based sampling method to sample points from the latent manifold. With the LCC sampling method, we can exploit the local information on the latent manifold and thus produce new data with promising quality. Second, we propose an advanced LCCGAN-v2 by introducing a higher-order term in the generator approximation. This term is able to achieve better approximation and thus further improve the performance. More critically, we derive the generalization bound for both LCCGAN-v1 and LCCGAN-v2 and prove that a small-dimensional input is sufficient to achieve good generalization performance. Extensive experiments on four benchmark datasets demonstrate the superiority of the proposed method over existing GAN methods.