Cardiac magnetic resonance imaging (CMR) has been widely used in clinical
practice for the medical diagnosis of cardiac diseases. However, the long
acquisition time hinders its development in real-time applications. Here, we
propose a novel self-consistency guided multi-prior learning framework named
$k$-$t$ CLAIR to exploit spatiotemporal correlations from highly undersampled
data for accelerated dynamic parallel MRI reconstruction. The $k$-$t$ CLAIR
progressively reconstructs faithful images by leveraging multiple complementary
priors learned in the $x$-$t$, $x$-$f$, and $k$-$t$ domains in an iterative
fashion, as dynamic MRI exhibits high spatiotemporal redundancy. Additionally,
$k$-$t$ CLAIR incorporates calibration information for prior learning,
resulting in a more consistent reconstruction. Experimental results on cardiac
cine and T1W/T2W images demonstrate that $k$-$t$ CLAIR achieves high-quality
dynamic MR reconstruction in terms of both quantitative and qualitative
performance.

通过自一致性引导的多先验学习框架 $k$-$t$ CLAIR，利用高度欠采样数据中的时空相关性来加速动态并行磁共振成像重建，$k$-$t$ CLAIR 通过在迭代过程中学习 $x$-$t$、$x$-$f$ 和 $k$-$t$ 领域中的多个互补先验逐步重建可靠图像，实验结果表明 $k$-$t$ CLAIR 在心脏影像重建方面具有高质量的定量和定性性能。

$k$-$t$ CLAIR: 动态并行 MR 图像重构的自一致引导多先验学习

$k$-$t$ CLAIR: Self-Consistency Guided Multi-Prior Learning for Dynamic  Parallel MR Image Reconstruction

Spatiotemporal traffic data imputation (STDI), estimating the missing data
from partially observed traffic data, is an inevitable and challenging task in
data-driven intelligent transportation systems (ITS). Due to traffic data's
multidimensional and spatiotemporal properties, we treat the missing data
imputation as a tensor completion problem. Many studies have been on STDI based
on tensor decomposition in the past decade. However, how to use spatiotemporal
correlations and core tensor sparsity to improve the imputation performance
still needs to be solved. This paper reshapes a 3rd/4th order Hankel tensor and
proposes an innovative manifold regularized Tucker decomposition (ManiRTD)
model for STDI. Expressly, we represent the sensory traffic state data as the
3rd/4th tensors by introducing Multiway Delay Embedding Transforms. Then,
ManiRTD improves the sparsity of the Tucker core using a sparse regularization
term and employs manifold regularization and temporal constraint terms of
factor matrices to characterize the spatiotemporal correlations. Finally, we
address the ManiRTD model through a block coordinate descent framework under
alternating proximal gradient updating rules with convergence-guaranteed.
Numerical experiments are conducted on real-world spatiotemporal traffic
datasets (STDs). Our results demonstrate that the proposed model outperforms
the other factorization approaches and reconstructs the STD more precisely
under various missing scenarios.

本论文提出了一个创新的流形正则化 Tucker 分解（ManiRTD）模型，通过引入多元时延嵌入变换，将感官交通状态数据表示为三阶 / 四阶张量，并利用稀疏正则化项改善 Tucker 核的稀疏性以及使用流形正则化和时间约束条件特征化其时空关联，最终在交替近端梯度更新规则下通过块坐标下降框架解决 ManiRTD 模型，并在实际交通数据集上进行数字实验，结果表明所提出的模型在各种缺失情况下优于其他分解方法，并更精确地重建了 STD。

流形正则化 Tucker 分解方法在时空交通数据插值中的应用

Manifold Regularized Tucker Decomposition Approach for Spatiotemporal  Traffic Data Imputation

The goal of precipitation nowcasting is to predict the future rainfall
intensity in a local region over a relatively short period of time. Very few
previous studies have examined this crucial and challenging weather forecasting
problem from the machine learning perspective. In this paper, we formulate
precipitation nowcasting as a spatiotemporal sequence forecasting problem in
which both the input and the prediction target are spatiotemporal sequences. By
extending the fully connected LSTM (FC-LSTM) to have convolutional structures
in both the input-to-state and state-to-state transitions, we propose the
convolutional LSTM (ConvLSTM) and use it to build an end-to-end trainable model
for the precipitation nowcasting problem. Experiments show that our ConvLSTM
network captures spatiotemporal correlations better and consistently
outperforms FC-LSTM and the state-of-the-art operational ROVER algorithm for
precipitation nowcasting.

本文将降水短时预报问题作为时空序列预测问题，并使用卷积 LSTM (ConvLSTM) 构建可端到端训练的模型，数据实验表明，相比全连接的 LSTM 和 ROVER 算法，ConvLSTM 能够更好地捕捉时空相关性，并在降水短时预报中具有更好的预测性能。