This paper presents a new discriminative deep metric learning (DDML) method for face verification in the wild. Different from existing metric learning-based face verification methods which aim to learn a Mahalanobis distance metric to maximize the inter-class variations and minimize the intra-class variations, simultaneously, the proposed D-DML trains a deep neural network which learns a set of hierarchical nonlinear transformations to project face pairsinto the same feature subspace, under which the distance of each positive face pair is less than a smaller threshold and that of each negative pair is higher than a larger threshold, respectively, so that discriminative information can be exploited in the deep network. Our method achieves very competitive face verification performance on the widely used LFW and YouTube Faces (YTF) datasets.
Background There has been increasing reports associating the coronavirus disease 2019 (COVID-19) with thromboembolic phenomenon including ischemic strokes and venous thromboembolism. Cerebral venous thrombosis (CVT) is a rare neurovascular emergency that has been observed in some COVID-19 patients, yet much remains to be learnt of its underlying pathophysiology. Objective We present a case series of local patients with concomitant COVID-19 infection and CVT; and aim to perform a systematic review of known cases in the current literature. Methods We describe two patients with concomitant COVID-19 infection and CVT from a nationwide registry in Singapore. We then conducted a literature search in PubMed and Embase using a suitable keyword search strategy from 1st December 2019 to 11th June 2020. All studies reporting CVT in COVID-19 patients were included. Results Nine studies and 14 COVID-19 patients with CVT were studied. The median age was 43 years (IQR=36-58) and majority had no significant past medical conditions (60.0%). The time taken from onset of COVID-19 symptoms to CVT diagnosis was a median of 7 days (IQR=6-14). CVT was commonly seen in the transverse (75.0%) and sigmoid sinus (50.0%); 33.3% had involvement of the deep venous sinus system. A significant proportion of patients had raised D-dimer (75.0%) and CRP levels (50.0%). Two patients reported presence of antiphospholipid antibodies. Most patients received anticoagulation (91.7%) while overall mortality rate was 45.5%. Conclusions The high mortality rate of CVT in COVID-19 infection warrants a high index of suspicion from physicians, and early treatment with anticoagulation should be initiated.
Conventional appearance-based face recognition methods usually assume that there are multiple samples per person (MSPP) available for discriminative feature extraction during the training phase. In many practical face recognition applications such as law enhancement, e-passport, and ID card identification, this assumption, however, may not hold as there is only a single sample per person (SSPP) enrolled or recorded in these systems. Many popular face recognition methods fail to work well in this scenario because there are not enough samples for discriminant learning. To address this problem, we propose in this paper a novel discriminative multimanifold analysis (DMMA) method by learning discriminative features from image patches. First, we partition each enrolled face image into several nonoverlapping patches to form an image set for each sample per person. Then, we formulate the SSPP face recognition as a manifold-manifold matching problem and learn multiple DMMA feature spaces to maximize the manifold margins of different persons. Finally, we present a reconstruction-based manifold-manifold distance to identify the unlabeled subjects. Experimental results on three widely used face databases are presented to demonstrate the efficacy of the proposed approach.
Conventional metric learning methods usually assume that the training and test samples are captured in similar scenarios so that their distributions are assumed to be the same. This assumption doesn't hold in many real visual recognition applications, especially when samples are captured across different datasets. In this paper, we propose a new deep transfer metric learning (DTML) method to learn a set of hierarchical nonlinear transformations for crossdomain visual recognition by transferring discriminative knowledge from the labeled source domain to the unlabeled target domain. Specifically, our DTML learns a deep metric network by maximizing the inter-class variations and minimizing the intra-class variations, and minimizing the distribution divergence between the source domain and the target domain at the top layer of the network. To better exploit the discriminative information from the source domain, we further develop a deeply supervised transfer metric learning (DSTML) method by including an additional objective on DTML where the output of both the hidden layers and the top layer are optimized jointly. Experimental results on cross-dataset face verification and person re-identification validate the effectiveness of the proposed methods.
Most digital still cameras acquire imagery with a color filter array (CFA), sampling only one color value for each pixel and interpolating the other two color values afterwards. The interpolation process is commonly known as demosaicking. In general, a good demosaicking method should preserve the high-frequency information of imagery as much as possible, since such information is essential for image visual quality. We discuss in this paper two key observations for preserving high-frequency information in CFA demosaicking: (1) the high frequencies are similar across three color components, and (2) the high frequencies along the horizontal and vertical axes are essential for image quality. Our frequency analysis of CFA samples indicates that filtering a CFA image can better preserve high frequencies than filtering each color component separately. This motivates us to design an efficient filter for estimating the luminance at green pixels of the CFA image and devise an adaptive filtering approach to estimating the luminance at red and blue pixels. Experimental results on simulated CFA images, as well as raw CFA data, verify that the proposed method outperforms the existing state-of-the-art methods both visually and in terms of peak signal-to-noise ratio, at a notably lower computational cost.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.