Caspersenmacdonald9915

Our goal is to foster harmonization of perspectives for the field, which may help create a common ground forsystematization and discussion. We hope to influence and improve how research in this field is reported by providing a structured list ofthe defining characteristics. Selleckchem EGFR inhibitor Finally, some examples of the use of the taxonomy are presented to show how it can serve to gatherinformation for characterizing AR-supported collaborative work, and illustrate its potential as the grounds to elicit further.Minimizing the computation complexity is essential for the popularization of deep networks in practical applications. Nowadays, most researches attempt to accelerate deep networks by designing new network structure or compressing the network parameters. Meanwhile, transfer learning techniques such as knowledge distillation are utilized to keep the performance of deep models. In this paper, we focus on accelerating deep models and relieving the computation burden by using low-resolution (LR) images as inputs while maintaining competitive performance, which is rarely researched in the current literature. Deep networks may encounter serious performance degradation when using LR inputs because many details are unavailable from LR images. Besides, the existing approaches may fail to learn discriminative features for LR images because of the dramatic appearance variations between LR and high-resolution (HR) images. To tackle with the above problems, we propose a resolution-aware knowledge distillation (RKD) framewoRKD framework, especially when coping with large resolution differences.Blind image deblurring aims at recovering a clean image from the given blurry image without knowing the blur kernel. Recently proposed dark and extreme channel priors have shown their effectiveness in deblurring various blurry scenarios. However, these two priors fail to help the blur kernel estimation under the particular circumstance that clean images contain neither enough darkest nor brightest pixels. In this paper, we propose a novel and robust non-linear channel (NLC) prior for the blur kernel estimation to fill this gap. It is motivated by a simple idea that the blurring operation will increase the ratio of dark channel to bright channel. This change has been proved to be true both theoretically and empirically. Nonetheless, the presence of the NLC prior introduces a thorny optimization model. To handle it, an efficient algorithm based on projected alternating minimization (PAM) has been established which innovatively combines an approximate strategy, the half-quadratic splitting method, and fast iterative shrinkage-thresholding algorithm (FISTA). Extensive experimental results show that the proposed method achieves state-of-the-art results no matter when it has been applied in synthetic uniform and non-uniform benchmark datasets or in real blurry images.Shape from focus (SFF) reconstructs 3D shape of the scene from a sequence of multi-focus images, and the quality of reconstructed shape mainly depends on the accuracy of image focus volume (FV). Traditional SFF techniques exhibit poor performance in preserving structural edges and fine details while removing noisy artifacts, and mostly they do not incorporate any additional shape prior. Therefore, in this paper, we propose to refine FV by formulating an energy minimization framework that employs a nonconvex regularizer and incorporates two types of shape priors. The proposed regularizer is robust against noisy focus values. The first proposed shape prior is input image sequence and it is a single and static shape prior. While, the second shape prior corresponds to a series of shape priors. These shape priors are FVs which are iteratively obtained on-the-fly. Both of these shape priors constrain the solution space for output FV. We optimize nonconvex energy function through majorize-minimization algorithm which iteratively guarantees a local minimum and converges quickly. Experiments have been conducted to evaluate accuracy and convergence properties of the proposed method. Experimental results of synthetic and real image sequences demonstrate that our method achieves superior results in terms of ability to reconstruct accurate 3D shapes as compared to existing approaches.In recent years, reinforcement learning has achieved excellent results in low-dimensional static action spaces such as games and robotics. However, the action space is usually composite, composed of multiple sub-action with different functions, and time-varying for practical tasks. The existing sub-actions might be out of control due to the external environment, while unseen sub-actions can be added to the current system. To solve the robustness and transferability problems in time-varying composite action spaces, we propose a structured cooperative reinforcement learning algorithm based on the centralized critic and decentralized actor framework, called SCORE. We model the single-agent problem with composite action space as a fully cooperative partially observable stochastic game and further employ a graph attention network to capture the dependencies between heterogeneous sub-actions. To promote tighter cooperation between the decomposed heterogeneous agents, SCORE introduces a hierarchical variational autoencoder, which maps the heterogeneous sub-action space into a common latent action space. We also incorporate an implicit credit assignment structure into the SCORE to overcome the multi-agent credit assignment problem in the fully cooperative partially observable stochastic game. Performance experiments on the proof-of-concept task and precision agriculture task show that SCORE has significant advantages in robustness and transferability for time-varying composite action space.This paper presents a novel framework to recover detailed avatar from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, texture and viewpoints. Prior methods typically attempt to recover the human body shape using a parametric based template that lacks the surface details. As such the resulting body shape appears to be without clothing. In this paper, we propose a novel learning-based framework that combines the robustness of parametric model with the flexibility of free-form 3D deformation. We use the deep neural networks to refine the 3D shape in a Hierarchical Mesh Deformation (HMD) framework, utilizing the constraints from body joints, silhouettes, and per-pixel shading information. We are able to restore detailed human body shapes with complete textures beyond skinned models. Experiments demonstrate that our method has outperformed previous state-of-the-art approaches, achieving better accuracy in terms of both 2D IoU number and 3D metric distance.Few-shot learning is an emerging yet challenging problem in which the goal is to achieve generalization from only few examples. Meta-learning tackles few-shot learning via the learning of prior knowledge shared across tasks and using it to learn new tasks. One of the most representative meta-learning algorithms is the model-agnostic meta-learning (MAML), which formulates prior knowledge as a common initialization, a shared starting point from where a learner can quickly adapt to unseen tasks. However, forcibly sharing an initialization can lead to conflicts among tasks and the compromised (undesired by tasks) location on optimization landscape, thereby hindering task adaptation. Furthermore, the degree of conflict is observed to vary not only among the tasks but also among the layers of a neural network. Thus, we propose task-and-layer-wise attenuation on the compromised initialization to reduce its adverse influence on task adaptation. As attenuation dynamically controls (or selectively forgets) the influence of the compromised prior knowledge for a given task and each layer, we name our method Learn to Forget (L2F). Experimental results demonstrate that the proposed method greatly improves the performance of the state-of-the-art MAML-based frameworks across diverse domains few-shot classification, cross-domain few-shot classification, regression, reinforcement learning, and visual tracking.

The purpose of this study is to develop a biophysical model of human spiral ganglion neurons (SGNs) that includes voltage-gated hyperpolarization-activated cation (HCN) channels and low-threshold potassium voltage-gated, delayed-rectifier low-threshold potassium (KLT) channels, providing for a more complete simulation of spike-rate adaptation, a feature of most spiking neurons in which spiking activity is reduced in response to sustained stimulation.

Our model incorporates features of spike-rate adaptation reported from in vivo studies, whilst also displaying similar behaviour to existing models of human SGNs, including the dependence of electrically evoked thresholds on the polarity of electrical pulses.

Hypothesizing that the mode of stimulation intracellular or extracellular predicts features of spike-rate adaptation similar to in vivo studies, including the influence of stimulus intensity and pulse-rate, we find that the mode of stimulation alters features of spike-rate adaptation. In particular, th and its effects on neural responses. This will help develop novel, and perhaps personalised, stimulation strategies to reduce variability in CI user outcomes.AbstractResting-state functional magnetic resonance imaging (rs-fMRI) has become a popular non-invasive way of diagnosing neurological disorders or their early stages by probing functional connectivity between different brain regions of interest (ROIs) across subjects. In the past decades, researchers have proposed many methods to estimate brain functional networks (BFNs) based on blood-oxygen-level-dependent (BOLD) signals captured by rs-fMRI. However, most of the existing methods estimate BFNs under the assumption that signals are independently sampled, which ignores the temporal dependency and sequential order of different time points (or volumes). To address this problem, in this paper, we first propose a novel BFN estimation model by introducing a latent variable to control the sequence of volumes for encoding the temporal dependency and sequential information of signals into the estimated BFNs. Then, we develop an efficient learning algorithm to solve the proposed model by the alternating optimization scheme. To verify the effectiveness of the proposed method, the estimated BFNs are used to identify subjects with mild cognitive impairment (MCIs) from normal controls (NCs). Experimental results show that our method outperforms the baseline methods in the sense of classification performance.

The objective of this paper is to model and experimentally validate the path loss benefits of magnetic human body communication (mHBC) using small form-factor-accurate coils operating under realistic conditions.

A radiating near-field coupling model and numerical simulations are presented to show that the magnetic-dominant near-field coupling between resonant coils offers low path loss across the body and exhibits extra robustness to antenna misalignment compared to far-field RF schemes. To overcome the pitfalls in conventional vector-network-analyzer-based measurement configurations, we propose a standardized setup applied to broadband channel loss measurement with portable instruments. Two types of PCB coils for mHBC communication, designed for large devices such as smartphones and small devices such as earbuds, respectively, are built and measured.

The mHBC link for the ear-to-ear non-line-of-sight (NLOS) path measures up to -23.1 dB and -31.2dB with large and small coils, respectively, which is 50 dB more efficient than the conventional Bluetooth channels utilizing antennas of similar sizes.