Self-powered MSM solar-blind AlGaN photodetector realized by in-plane polarization modulation.

Solid-state self-powered UV detection is strongly required in various application fields to enable long-term operation. However, this requirement is incompatible with conventionally used metal-semiconductor-metal (MSM) UV photodetectors (PDs) due to the symmetric design of Schottky contacts. In this work, a self-powered MSM solar-blind UV-PD was realized using a lateral pn junction architecture. A large built-in electric field was obtained in the MSM-type UV-PD without impurity doping, leading to efficiency carrier separation and enhanced photoresponsivity at zero external bias. The solar-blind UV-PD exhibits a cutoff wavelength of 280 nm, a photo/dark current ratio of over 105, and a responsivity of 425.13 mA/W at -10 V. The mechanism of self-powered UV photodetection was further investigated by TCAD simulation of the internal electric field and carrier distributions.

Pose-Aware Attention Network for Flexible Motion Retargeting by Body Part.

Motion retargeting is a fundamental problem in computer graphics and computer vision. Existing approaches usually have many strict requirements, such as the source-target skeletons needing to have the same number of joints or share the same topology. To tackle this problem, we note that skeletons with different structure may have some common body parts despite the differences in joint numbers. Following this observation, we propose a novel, flexible motion retargeting framework. The key idea of our method is to regard the body part as the basic retargeting unit rather than directly retargeting the whole body motion. To enhance the spatial modeling capability of the motion encoder, we introduce a pose-aware attention network (PAN) in the motion encoding phase. The PAN is pose-aware since it can dynamically predict the joint weights within each body part based on the input pose, and then construct a shared latent space for each body part by feature pooling. Extensive experiments show that our approach can generate better motion retargeting results both qualitatively and quantitatively than state-of-the-art methods. Moreover, we also show that our framework can generate reasonable results even for a more challenging retargeting scenario, like retargeting between bipedal and quadrupedal skeletons because of the body part retargeting strategy and PAN. Our code is publicly available.

Motif-GCNs With Local and Non-Local Temporal Blocks for Skeleton-Based Action Recognition.

Recent works have achieved remarkable performance for action recognition with human skeletal data by utilizing graph convolutional models. Existing models mainly focus on developing graph convolutional operations to encode structural properties of a skeletal graph, whose topology is manually predefined and fixed over all action samples. Some recent works further take sample-dependent relationships among joints into consideration. However, the complex relationships between arbitrary pairwise joints are difficult to learn and the temporal features between frames are not fully exploited by simply using traditional convolutions with small local kernels. In this paper, we propose a motif-based graph convolution method, which makes use of sample-dependent latent relations among non-physically connected joints to impose a high-order locality and assigns different semantic roles to physical neighbors of a joint to encode hierarchical structures. Furthermore, we propose a sparsity-promoting loss function to learn a sparse motif adjacency matrix for latent dependencies in non-physical connections. For extracting effective temporal information, we propose an efficient local temporal block. It adopts partial dense connections to reuse temporal features in local time windows, and enrich a variety of information flow by gradient combination. In addition, we introduce a non-local temporal block to capture global dependencies among frames. Our model can capture local and non-local relationships both spatially and temporally, by integrating the local and non-local temporal blocks into the sparse motif-based graph convolutional networks (SMotif-GCNs). Comprehensive experiments on four large-scale datasets show that our model outperforms the state-of-the-art methods. Our code is publicly available at https://github.com/wenyh1616/SAMotif-GCN.

Multiscale Mesh Deformation Component Analysis With Attention-Based Autoencoders.

Deformation component analysis is a fundamental problem in geometry processing and shape understanding. Existing approaches mainly extract deformation components in local regions at a similar scale while deformations of real-world objects are usually distributed in a multi-scale manner. In this article, we propose a novel method to exact multiscale deformation components automatically with a stacked attention-based autoencoder. The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales. Quantitative and qualitative evaluations show that our method outperforms state-of-the-art methods. Furthermore, with the multiscale deformation components extracted by our method, the user can edit shapes in a coarse-to-fine fashion which facilitates effective modeling of new shapes.

Active Colorization for Cartoon Line Drawings.

In the animation industry, the colorization of raw sketch images is a vitally important but very time-consuming task. This article focuses on providing a novel solution that semiautomatically colorizes a set of images using a single colorized reference image. Our method is able to provide coherent colors for regions that have similar semantics to those in the reference image. An active-learning-based framework is used to match local regions, followed by mixed-integer quadratic programming (MIQP) which considers the spatial contexts to further refine the matching results. We efficiently utilize user interactions to achieve high accuracy in the final colorized images. Experiments show that our method outperforms the current state-of-the-art deep learning based colorization method in terms of color coherency with the reference image. The region matching framework could potentially be applied to other applications, such as color transfer.

Upregulation of endothelial cell-derived exosomal microRNA-125b-5p protects from sepsis-induced acute lung injury by inhibiting topoisomerase II alpha.

OBJECTIVE: Emerging evidence has revealed that exosomal microRNAs (miRNAs) are implicated in human diseases. However, role of exosomal miR-125b-5p in sepsis-induced acute lung injury (ALI) remains further explored. We focused on the effect of exosomal miR-125b-5p on ALI progression via targeting topoisomerase II alpha (TOP2A). METHODS: The ALI mouse models were established by cecal ligation and perforation, which were then treated with miR-125b-5p agomir or overexpressed TOP2A. Next, the pathological structure of ALI mouse lung tissues were observed, miR-125b-5p, TOP2A and vascular endothelial growth factor (VEGF) expression was determined, and the lung water content, inflammatory response, protein content in bronchoalveolar lavage fluid (BALF) and cell apoptosis in ALI mouse lung tissues were assessed. Exosomes were extracted from endothelial cells (ECs) and identified, which were then injected into the modeled mice to observe their roles in ALI. The targeting relationship between miR-125b-5p and TOP2A was confirmed. RESULTS: MiR-125b-5p was downregulated while TOP2A was upregulated in ALI mice. MiR-125b-5p elevation or ECs-derived exosomes promoted VEGF expression, improved pathological changes and restrained lung water content, inflammatory response, protein content in BALF and cell apoptosis in lung tissues ALI mice. TOP2A overexpression reversed the repressive role of miR-125b-5p upregulation in ALI, while downregulated miR-125b-5p abrogated the effect of ECs-derived exosomes on ALI. TOP2A was confirmed as a direct target gene of miR-125b-5p. CONCLUSION: Our study indicates that ECs-derived exosomes overexpressed miR-125b-5p to protect from sepsis-induced ALI by inhibiting TOP2A, which may contribute to ALI therapeutic strategies.

Combining Recurrent Neural Networks and Adversarial Training for Human Motion Synthesis and Control.

This paper introduces a new generative deep learning network for human motion synthesis and control. Our key idea is to combine recurrent neural networks (RNNs) and adversarial training for human motion modeling. We first describe an efficient method for training an RNN model from prerecorded motion data. We implement RNNs with long short-term memory (LSTM) cells because they are capable of addressing the nonlinear dynamics and long term temporal dependencies present in human motions. Next, we train a refiner network using an adversarial loss, similar to generative adversarial networks (GANs), such that refined motion sequences are indistinguishable from real mocap data using a discriminative network. The resulting model is appealing for motion synthesis and control because it is compact, contact-aware, and can generate an infinite number of naturally looking motions with infinite lengths. Our experiments show that motions generated by our deep learning model are always highly realistic and comparable to high-quality motion capture data. We demonstrate the power and effectiveness of our models by exploring a variety of applications, ranging from random motion synthesis, online/offline motion control, and motion filtering. We show the superiority of our generative model by comparison against baseline models.

Sparse Data Driven Mesh Deformation.

Example-based mesh deformation methods are powerful tools for realistic shape editing. However, existing techniques typically combine all the example deformation modes, which can lead to overfitting, i.e., using an overly complicated model to explain the user-specified deformation. This leads to implausible or unstable deformation results, including unexpected global changes outside the region of interest. To address this fundamental limitation, we propose a sparse blending method that automatically selects a smaller number of deformation modes to compactly describe the desired deformation. This along with a suitably chosen deformation basis including spatially localized deformation modes leads to significant advantages, including more meaningful, reliable, and efficient deformations because fewer and localized deformation modes are applied. To cope with large rotations, we develop a simple but effective representation based on polar decomposition of deformation gradients, which resolves the ambiguity of large global rotations using an as-consistent-as-possible global optimization. This simple representation has a closed form solution for derivatives, making it efficient for our sparse localized representation and thus ensuring interactive performance. Experimental results show that our method outperforms state-of-the-art data-driven mesh deformation methods, for both quality of results and efficiency.

Weakly Supervised Adversarial Learning for 3D Human Pose Estimation from Point Clouds.

Point clouds-based 3D human pose estimation that aims to recover the 3D locations of human skeleton joints plays an important role in many AR/VR applications. The success of existing methods is generally built upon large scale data annotated with 3D human joints. However, it is a labor-intensive and error-prone process to annotate 3D human joints from input depth images or point clouds, due to the self-occlusion between body parts as well as the tedious annotation process on 3D point clouds. Meanwhile, it is easier to construct human pose datasets with 2D human joint annotations on depth images. To address this problem, we present a weakly supervised adversarial learning framework for 3D human pose estimation from point clouds. Compared to existing 3D human pose estimation methods from depth images or point clouds, we exploit both the weakly supervised data with only annotations of 2D human joints and fully supervised data with annotations of 3D human joints. In order to relieve the human pose ambiguity due to weak supervision, we adopt adversarial learning to ensure the recovered human pose is valid. Instead of using either 2D or 3D representations of depth images in previous methods, we exploit both point clouds and the input depth image. We adopt 2D CNN to extract 2D human joints from the input depth image, 2D human joints aid us in obtaining the initial 3D human joints and selecting effective sampling points that could reduce the computation cost of 3D human pose regression using point clouds network. The used point clouds network can narrow down the domain gap between the network input i.e. point clouds and 3D joints. Thanks to weakly supervised adversarial learning framework, our method can achieve accurate 3D human pose from point clouds. Experiments on the ITOP dataset and EVAL dataset demonstrate that our method can achieve state-of-the-art performance efficiently.

Realtime and Accurate 3D Eye Gaze Capture with DCNN-based Iris and Pupil Segmentation.

This paper presents a realtime and accurate method for 3D eye gaze tracking with a monocular RGB camera. Our key idea is to train a deep convolutional neural network(DCNN) that automatically extracts the iris and pupil pixels of each eye from input images. To achieve this goal, we combine the power of Unet\cite{ronneberger2015u-net:} and Squeezenet\cite{iandola2017squeezenet:} to train an efficient convolutional neural network for pixel classification. In addition, we track the 3D eye gaze state in the Maximum A Posteriori (MAP) framework, which sequentially searches for the most likely state of the 3D eye gaze at each frame. When eye blinking occurs, the eye gaze tracker can obtain an inaccurate result. We further extend the convolutional neural network for eye close detection in order to improve the robustness and accuracy of the eye gaze tracker. Our system runs in realtime on desktop PCs and smart phones. We have evaluated our system on live videos and Internet videos, and our results demonstrate that the system is robust and accurate for various genders, races, lighting conditions, poses, shapes and facial expressions. A comparison against Wang et al.[3] shows that our method advances the state of the art in 3D eye tracking using a single RGB camera.

Temporal Upsampling of Depth Maps Using a Hybrid Camera.

In recent years, consumer-level depth cameras have been adopted for various applications. However, they often produce depth maps at only a moderately high frame rate (approximately 30 frames per second), preventing them from being used for applications such as digitizing human performance involving fast motion. On the other hand, low-cost, high-frame-rate video cameras are available. This motivates us to develop a hybrid camera that consists of a high-frame-rate video camera and a low-frame-rate depth camera and to allow temporal interpolation of depth maps with the help of auxiliary color images. To achieve this, we develop a novel algorithm that reconstructs intermediate depth maps and estimates scene flow simultaneously. We test our algorithm on various examples involving fast, non-rigid motions of single or multiple objects. Our experiments show that our scene flow estimation method is more precise than a tracking-based method and the state-of-the-art techniques.

Effect of tibia marker placement on knee joint kinematic analysis.

Variability of kinematic measures determined by different marker sets among sites participating in a collaborative study is necessary for determining the reliability of a multi-site gait analysis research. We compared knee kinematics based on different marker sets on the tibia, calculating by segmental optimization (SO) and multi-body optimization (MBO) methods respectively, in order to assess the effect of marker locations on the methods. 11 healthy subjects participated in the study with 33 markers attached to the lower extremity segments, and 4 groups were identified according to markers on the tibia. Knee joint kinematics during level walking were measured and then compared among the 4 groups using statistical parametric mapping. For SO method, the results showed that there were no significant differences in the knee joint angles when used different marker sets on the tibia. However, significant differences were found in the transverse plane kinematics for MBO method. It was concluded that MBO method was more likely to be influenced by different marker sets. More attention should be paid to marker sets, specifically for MBO method, when three-dimensional gait analysis data are shared and interpreted among sites for clinical decision-making.