This paper proposes an encoder-decoder network to disentangle shape features during 3D face reconstruction from single 2D images, such that the tasks of reconstructing accurate 3D face shapes and learning discriminative shape features for face recognition can be accomplished simultaneously. Unlike existing 3D face reconstruction methods, our proposed method directly regresses dense 3D face shapes from single 2D images, and tackles identity and residual (i.e., non-identity) components in 3D face shapes explicitly and separately based on a composite 3D face shape model with latent representations. We devise a training process for the proposed network with a joint loss measuring both face identification error and 3D face shape reconstruction error. To construct training data we develop a method for fitting 3D morphable model (3DMM) to multiple 2D images of a subject. Comprehensive experiments have been done on MICC, BU3DFE, LFW and YTF databases. The results show that our method expands the capacity of 3DMM for capturing discriminative shape features and facial detail, and thus outperforms existing methods both in 3D face reconstruction accuracy and in face recognition accuracy.
Face alignment and 3D face reconstruction are traditionally accomplished as separated tasks. By exploring the strong correlation between 2D landmarks and 3D shapes, in contrast, we propose a joint face alignment and 3D face reconstruction method to simultaneously solve these two problems for 2D face images of arbitrary poses and expressions. This method, based on a summation model of 3D faces and cascaded regression in 2D and 3D shape spaces, iteratively and alternately applies two cascaded regressors, one for updating 2D landmarks and the other for 3D shape. The 3D shape and the landmarks are correlated via a 3D-to-2D mapping matrix, which is updated in each iteration to refine the location and visibility of 2D landmarks. Unlike existing methods, the proposed method can fully automatically generate both pose-and-expression-normalized (PEN) and expressive 3D faces and localize both visible and invisible 2D landmarks. Based on the PEN 3D faces, we devise a method to enhance face recognition accuracy across poses and expressions. Both linear and nonlinear implementations of the proposed method are presented and evaluated in this paper. Extensive experiments show that the proposed method can achieve the state-of-the-art accuracy in both face alignment and 3D face reconstruction, and benefit face recognition owing to its reconstructed PEN 3D face.
Although the role of Krüppel-like factor 17 (KLF17) in regulating epithelial-mesenchymal transition (EMT) has been explored in breast cancer, its influence on primary hepatocellular carcinoma (HCC) remains unclear. This study aims to investigate the expression status of KLF17 in hepatocellular carcinoma (HCC) and the correlation between KLF17 expression and metastatic potential of HCC. KLF17 expression in HCC and adjacent liver tissues was studied by real-time PCR and Western blot, and the relationship between KLF17 expression and the clinicopathological features of HCC was evaluated in 60 patients. By using RNA interference technique, the correlation of KLF17 expression and metastatic potential was investigated by down-regulating KLF17 expression in HepG2 cells, and the effects of KLF17 down-regulation on cell migration, and invasion were then analyzed. Furthermore, the correlation between KLF17 expression and the surgical outcomes of a cohort of HCC patients was analyzed. Reduced expression of KLF17 is associated with a short survival time in clinical patients (P = 0.034). Low KLF17 expression is related to tumor T stage (P = 0.045), tumor size (P = 0.027), lymph node stage (P = 0.030), M stage (P = 0.048), and portal vein tumor thrombosis significantly in HCC. Reduced expression of KLF17 promoted motility and invasion ability of HepG2 cells and changed the expression of E-cadherin, ZO-1, Snai1, and vimentin (genes are associated with EMT). Overall, these findings suggest a repressing role of KLF17 in tumor invasion and a new prognostic indicator in directing therapy. It deserves further exploration.
Abstract-In current IaaS datacenters, tenants are suffering unfairness since the network bandwidth is shared in a besteffort manner. To achieve predictable network performance for rented virtual machines (VMs), cloud providers should guarantee minimum bandwidth for VMs or allocate the network bandwidth in a fairness fashion at VM-level. At the same time, the network should be efficiently utilized in order to maximize cloud providers' revenue. In this paper, we model the bandwidth sharing problem as a Nash bargaining game, and propose the allocation principles by defining a tunable base bandwidth for each VM. Specifically, we guarantee bandwidth for those VMs with lower network rates than their base bandwidth, while maintaining fairness among other VMs with higher network rates than their base bandwidth. Based on rigorous cooperative game-theoretic approaches, we design a distributed algorithm to achieve efficient and fair bandwidth allocation corresponding to the Nash bargaining solution (NBS). With simulations under typical scenarios, we show that our strategy can meet the two desirable requirements towards predictable performance for tenants as well as high utilization for providers. And by tuning the base bandwidth, our solution can enable cloud providers to flexibly balance the tradeoff between minimum guarantees and fair sharing of datacenter networks.
The limited capacity to recognise faces under occlusions is a long-standing problem that presents a unique challenge for face recognition systems and even humans. The problem regarding occlusion is less covered by research when compared to other challenges such as pose variation, different expressions, etc. Nevertheless, occluded face recognition is imperative to exploit the full potential of face recognition for real-world applications. In this article, the scope to occluded face recognition is restricted and a systematic categorisation that new as well as classic methods fit into is presented. First, the authors explore the kind of the occlusion problem and the type of inherent difficulties that can arise. As a part of this review, face detection under occlusion, a preliminary step in face recognition. Second the authors analyse how the existing face recognition methods cope with the occlusion problem and classify them into three categories, which are given as: 1) occlusion robust feature extraction approaches, 2) occlusion aware face recognition approaches, and 3) occlusion recovery based face recognition approaches. Furthermore, the motivations, innovations, pros and cons, and the performance of representative approaches for comparison are analyzed. Finally, future challenges and method trends of occluded face recognition are thoroughly discussed.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Glioma is the most common malignant tumor of the central nervous system (CNS). Therapeutic efficacy of glioma treatment is greatly limited by the blood–brain barrier (BBB) and blood–brain tumor barrier (BBTB), which restrict the passage of most drugs into the brain and tumors. Developing drug delivery systems that cross the BBB and BBTB will aid in the treatment of glioma and malignant brain metastases. One emerging solution is to identify peptide vectors that penetrate the BBB/BBTB. Herein, a novel BBB/BBTB-penetrating peptide was identified from the phage-displayed peptide library. Peptide–drug conjugates (PDCs) were derived and applied to treat glioma and breast cancer brain metastases. Antitumor activity was achieved in both tumor models with synergistic effects when combined with the currently used chemotherapy drug temozolomide. The peptide reported herein can serve as a universal vector for shuttling compounds across the BBB; therefore, it may have wide applications for treating brain tumors and other CNS diseases.
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.