Novel Temporal(新时空)研究综述
Novel Temporal 新时空 - Meanwhile, we also propose a novel temporal and spatial dual-discriminator for more robust network optimization. [1] In this paper, a novel Temporal-Difference Spatial Sampling and Aggregating graph neural network (TDSSA) is proposed to model spatial-temporal dependencies. [2] To address these issues, in this paper, a MI-EEG decoding framework is proposed, which uses a novel temporal-spectral-based squeeze-and-excitation feature fusion network (TS-SEFFNet). [3] It contributes to remarkable enhancement of both electrical (by 100%) and optical output (by 30%), as well as novel temporal-spatial resolution mode for motion capturing. [4] To address these issues, this paper presents a novel Temporal-Structural User Representation (named TSUR) network to predict LTV. [5] This paper proposes a novel Temporal-Free Semantic-Guided attention mechanism (TFSG) to utilize the raw caption pre-generated by a primary decoder as the extra input to provide global semantic guidance during generation, deepening visual understanding by balancing the semantic and visual information. [6] To ensure non-redundant data processing of deep network on a compact motion profile further, a novel temporal-shift memory (TSM) model is developed to perform deep learning of sequential input in linear processing time. [7] We propose that understanding of time-of-day dependent vulnerability to MR signalling in the heart versus the kidney may offer the rationale for the development of novel temporal or tissue specific-MR modulators in the management of cardiovascular disease. [8] We present a novel temporally coherent stylized rendering technique working entirely at the compositing stage. [9] To cope with this problem, a soft sensor modeling strategy of the BF wall temperature field based on a novel temporal–spatial dimensional finite-element extrapolation algorithm (TS-FEEA) is designed. [10] We develop a novel temporal-aware sequence classification to mine the correlation between I/O requests and represents the addresses with multidimensional vectors that shows better spatial locality. [11] In this paper, a novel temporally local recurrent radial basis function network for modeling and adaptive control of nonlinear systems is proposed. [12] We present, mathematically and experimentally, a novel temporally multiplexed polarimetric LADAR (TMP-LADAR) architecture which is capable of characterizing the polarimetric properties (Mueller matrix elements) of a target using a single 10 ns laser pulse. [13] To more conveniently remove the influence of noise interference and realize accurate identification, a novel temporal-frequency autoencoding based method is proposed. [14] Consequently, we design a novel temporal, functional and spatial big data computing framework for large-scale smart grid. [15]同时，我们还提出了一种新颖的时空双判别器，用于更稳健的网络优化。 [1] 在本文中，提出了一种新颖的时差空间采样和聚合图神经网络（TDSSA）来建模时空依赖关系。 [2] 为了解决这些问题，本文提出了一种 MI-EEG 解码框架，该框架使用了一种新颖的基于时谱的挤压和激发特征融合网络（TS-SEFFNet）。 [3] 它有助于显着增强电输出（100%）和光输出（30%），以及用于运动捕捉的新型时空分辨率模式。 [4] 为了解决这些问题，本文提出了一种新颖的时间结构用户表示（称为 TSUR）网络来预测 LTV。 [5] 本文提出了一种新颖的无时间语义引导注意机制（TFSG），利用初级解码器预先生成的原始字幕作为额外输入，在生成过程中提供全局语义引导，通过平衡语义和视觉信息来加深视觉理解. [6] 为了进一步确保深度网络在紧凑运动曲线上的非冗余数据处理，开发了一种新的时移记忆（TSM）模型，以在线性处理时间内对顺序输入进行深度学习。 [7] 我们提出，了解心脏与肾脏对 MR 信号的时间依赖性易感性可能为在心血管疾病管理中开发新型时间或组织特异性 MR 调节剂提供基本原理。 [8] 我们提出了一种完全在合成阶段工作的新颖的时间连贯风格化渲染技术。 [9] 针对这一问题，设计了一种基于新型时空维有限元外推算法（TS-FEEA）的高炉壁温场软传感器建模策略。 [10] 我们开发了一种新的时间感知序列分类来挖掘 I/O 请求之间的相关性，并用显示更好空间局部性的多维向量表示地址。 [11] 在本文中，提出了一种新的时间局部循环径向基函数网络，用于非线性系统的建模和自适应控制。 [12] 我们在数学和实验上提出了一种新颖的时间复用偏振激光雷达 (TMP-LADAR) 架构，该架构能够使用单个 10 ns 激光脉冲来表征目标的偏振特性（穆勒矩阵元素）。 [13] 为了更方便地去除噪声干扰的影响，实现准确识别，提出了一种新的基于时频自动编码的方法。 [14] 因此，我们为大规模智能电网设计了一种新颖的时间、功能和空间大数据计算框架。 [15]
novel temporal attention 新颖的时间注意
To address this challenge, this paper proposes a novel temporal attention convolutional network (TACNet) for MI classification. [1] In the TARM, a novel temporal attention mechanism is built based on residual learning to recalibrate frames of skeleton data temporally. [2] We propose a novel temporal attention based neural network architecture for robotics tasks that involve fusion of time series of sensor data, and evaluate the performance improvements in the context of autonomous navigation of unmanned ground vehicles (UGVs) in uncertain environments. [3]为了应对这一挑战，本文提出了一种用于 MI 分类的新型时间注意卷积网络 (TACNet)。 [1] 在 TARM 中，基于残差学习构建了一种新的时间注意机制，以在时间上重新校准骨架数据的帧。 [2] 我们为涉及融合传感器数据时间序列的机器人任务提出了一种新颖的基于时间注意的神经网络架构，并评估了在不确定环境中无人地面车辆 (UGV) 自主导航背景下的性能改进。 [3]
novel temporal pattern
The role of EVs in trauma-induced coagulopathy and posttraumatic thrombosis should be studied bearing in mind this novel temporal pattern. [1] An application to wheal size data is discussed with an aim of identifying novel temporal patterns among allergens within subject clusters. [2] CONCLUSIONS In normal fetal lungs, we report a novel temporal pattern of varied morphometric and metabolic changes. [3]考虑到这种新的时间模式，应该研究 EV 在创伤引起的凝血病和创伤后血栓形成中的作用。 [1] 讨论了风团大小数据的应用，目的是识别主题群内过敏原之间的新时间模式。 [2] 结论 在正常胎肺中，我们报告了不同形态和代谢变化的新时间模式。 [3]
novel temporal graph
To efficiently tackle our problem, we first devise a novel temporal graph reduction algorithm to significantly reduce the temporal graph without losing any maximal ρ-stable (δ, ɣ)-quasi-clique. [1] In this paper, a novel temporal graph convolutional network (TGCN) for the representation learning network is proposed to effectively capture the graph-based spatiotemporal input features. [2] Herein, we propose Auxo, a novel temporal graph management system to support temporal graph analysis. [3]为了有效地解决我们的问题，我们首先设计了一种新的时间图缩减算法来显着减少时间图，而不会丢失任何最大的 ρ-stable (δ, ɣ)-quasi-clique。 [1] 在本文中，提出了一种用于表示学习网络的新型时间图卷积网络（TGCN），以有效地捕获基于图的时空输入特征。 [2] 在这里，我们提出了 Auxo，一种新的时间图管理系统，以支持时间图分析。 [3]
novel temporal fusion 新颖的时间融合
In this paper, we propose a novel temporal fusion and AU-supervised self-attention network (a socalled SAT-Net) to address the AU detection problem. [1] Additionally, a novel temporal fusion and prediction module is designed to fuse temporal information from the extracted spatial feature sequences and predict vehicle driving commands. [2] In this paper, we propose a novel temporal fusion (TF) module to fuse the two-stream joints’ information to predict human motion, including a temporal concatenation and a reinforcement trajectory spatial-temporal (TST) block, specifically designed to keep prediction temporal consistency. [3]在本文中，我们提出了一种新颖的时间融合和 AU 监督的自我注意网络（所谓的 SAT-Net）来解决 AU 检测问题。 [1] 此外，设计了一种新颖的时间融合和预测模块，用于融合提取的空间特征序列中的时间信息并预测车辆驾驶命令。 [2] nan [3]
novel temporal transformation
Furthermore, we address the output-feedback problem and show that a dynamic observer and controller can be designed based on our dual dynamic high gain scaling based design methodology along with a novel temporal transformation and form of the scaling dynamics with temporal forcing terms to achieve both state estimation and regulation in the prescribed time interval. [1] While prior results on prescribed-time stabilization considered systems in a normal form structure (chain of integrators with uncertainties matched with the control input), we address here a general strict-feedback-like system structure with uncertain nonlinear functions throughout the system dynamics and develop a prescribed-time stabilizing controller based on our dynamic high gain scaling technique along with a novel temporal transformation and scaling dynamics with temporal forcing terms. [2]此外，我们解决了输出反馈问题，并表明可以基于我们的基于双动态高增益缩放的设计方法以及新颖的时间变换和具有时间强制项的缩放动力学形式来设计动态观察器和控制器，以实现两者在规定的时间间隔内进行状态估计和调节。 [1] 虽然关于规定时间稳定的先前结果考虑了正常形式结构的系统（具有与控制输入匹配的不确定性的积分器链），但我们在这里解决了在整个系统动力学中具有不确定非线性函数的一般严格反馈系统结构，并开发基于我们的动态高增益缩放技术的规定时间稳定控制器以及具有时间强制项的新型时间变换和缩放动力学。 [2]
novel temporal clustering
In this paper we present a novel temporal clustering approach aimed at linking records of the same group (such as all births by the same mother) where temporal constraints (such as intervals between births) need to be enforced. [1] This is done by a novel temporal clustering algorithm, which measures motion similarity based on the curvature and torsion of a space curve formed by corresponding vertices along a series of animation frames. [2]在本文中，我们提出了一种新的时间聚类方法，旨在链接同一组的记录（例如同一母亲的所有出生），其中需要强制执行时间约束（例如出生间隔）。 [1] 这是通过一种新颖的时间聚类算法完成的，该算法基于由沿一系列动画帧的相应顶点形成的空间曲线的曲率和扭转来测量运动相似度。 [2]
novel temporal pose
In this work we propose a novel temporal pose-sequence modeling framework, which can embed the dynamics of 3D human-skeleton joints to a latent space in an efficient manner. [1] More specifically, we introduce a novel temporal pose convolution to aggregate spatial poses over frames. [2]在这项工作中，我们提出了一种新颖的时间姿势序列建模框架，它可以有效地将 3D 人体骨骼关节的动力学嵌入到潜在空间中。 [1] 更具体地说，我们引入了一种新的时间姿势卷积来聚合帧上的空间姿势。 [2]
novel temporal adaptive
Finally, we develop a novel Temporal Adaptive Ngram (TA-Ngram) model in CSCVP to capture the dynamic and non-deterministic dependency between check-ins. [1] Finally, we develop a novel Temporal Adaptive Ngram (TA-Ngram) model in CSCVP to capture the dynamic and non-deterministic dependency between check-ins. [2]最后，我们在 CSCVP 中开发了一种新的时间自适应 Ngram (TA-Ngram) 模型来捕获签入之间的动态和非确定性依赖关系。 [1] 最后，我们在 CSCVP 中开发了一种新的时间自适应 Ngram (TA-Ngram) 模型来捕获签入之间的动态和非确定性依赖关系。 [2]
novel temporal action
To learn the preference dynamics, a novel temporal action embedding represents user actions by incorporating the embeddings of items and temporal context as the inputs of the convolutional network. [1] Then, the actions in hand trajectories are identified with a novel temporal action localization model. [2]为了学习偏好动态，一种新颖的时间动作嵌入通过将项目的嵌入和时间上下文作为卷积网络的输入来表示用户动作。 [1] nan [2]
novel temporal feature 新颖的时间特征
In this paper, we propose a novel temporal feature extraction method, named Attentive Correlated Temporal Feature (ACTF), by exploring inter-frame correlation within a certain region. [1] In this paper, we propose a novel temporal feature extraction module, named Key Point Shifts Embedding Module ($KPSEM$), to adaptively extract channel-wise key point shifts across video frames without key point annotation for temporal feature extraction. [2]在本文中，我们通过探索特定区域内的帧间相关性，提出了一种新的时间特征提取方法，称为注意力相关时间特征（ACTF）。 [1] 在本文中，我们提出了一种新的时间特征提取模块，称为关键点移位嵌入模块 ($KPSEM$)，用于在没有关键点注释的情况下自适应地提取视频帧中的通道方式关键点移位以进行时间特征提取。 [2]