Spatio-temporal modeling as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the underlying heterogeneity and non-stationarity implied in the graph streams, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal data. Specifically, we implement this idea into Meta-Graph Convolutional Recurrent Network (MegaCRN) by plugging the Meta-Graph Learner powered by a Meta-Node Bank into GCRN encoder-decoder. We conduct a comprehensive evaluation on two benchmark datasets (METR-LA and PEMS-BAY) and a large-scale spatio-temporal dataset that contains a variaty of non-stationary phenomena. Our model outperformed the state-of-the-arts to a large degree on all three datasets (over 27% MAE and 34% RMSE). Besides, through a series of qualitative evaluations, we demonstrate that our model can explicitly disentangle locations and time slots with different patterns and be robustly adaptive to different anomalous situations. Codes and datasets are available at https://github.com/deepkashiwa20/MegaCRN.

To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-view ambiguities. Existing solutions typically suffer from poor generalization performance to new settings, largely due to the limited diversity of image-mesh pairs in multi-view training data. To address this shortcoming, people have explored the use of synthetic images. But besides the usual impact of visual gap between rendered and target data, synthetic-data-driven multi-view estimators also suffer from overfitting to the camera viewpoint distribution sampled during training which usually differs from real-world distributions. Tackling both challenges, we propose a novel simulation-based training pipeline for multi-view human mesh recovery, which (a) relies on intermediate 2D representations which are more robust to synthetic-to-real domain gap; (b) leverages learnable calibration and triangulation to adapt to more diversified camera setups; and (c) progressively aggregates multi-view information in a canonical 3D space to remove ambiguities in 2D representations. Through extensive benchmarking, we demonstrate the superiority of the proposed solution especially for unseen in-the-wild scenarios.

Spatial-temporal (ST) graph modeling, such as traffic speed forecasting and taxi demand prediction, is an important task in deep learning area. However, for the nodes in graph, their ST patterns can vary greatly in difficulties for modeling, owning to the heterogeneous nature of ST data. We argue that unveiling the nodes to the model in a meaningful order, from easy to complex, can provide performance improvements over traditional training procedure. The idea has its root in Curriculum Learning which suggests in the early stage of training models can be sensitive to noise and difficult samples. In this paper, we propose ST-Curriculum Dropout, a novel and easy-to-implement strategy for spatial-temporal graph modeling. Specifically, we evaluate the learning difficulty of each node in high-level feature space and drop those difficult ones out to ensure the model only needs to handle fundamental ST relations at the beginning, before gradually moving to hard ones. Our strategy can be applied to any canonical deep learning architecture without extra trainable parameters, and extensive experiments on a wide range of datasets are conducted to illustrate that, by controlling the difficulty level of ST relations as the training progresses, the model is able to capture better representation of the data and thus yields better generalization.

Traffic forecasting as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the spatio-temporal heterogeneity and non-stationarity implied in the traffic stream, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal data. Specifically, we implement this idea into Meta-Graph Convolutional Recurrent Network (MegaCRN) by plugging the Meta-Graph Learner powered by a Meta-Node Bank into GCRN encoder-decoder. We conduct a comprehensive evaluation on two benchmark datasets (METR-LA and PEMS-BAY) and a new large-scale traffic speed dataset in which traffic incident information is contained. Our model outperformed the state-of-the-arts to a large degree on all three datasets (over 27% MAE and 34% RMSE). Besides, through a series of qualitative evaluations, we demonstrate that our model can explicitly disentangle the road links and time slots with different patterns and be robustly adaptive to any anomalous traffic situations. Codes and datasets are available at https://github.com/deepkashiwa20/MegaCRN.

了解动态场景中的3D运动对于许多视觉应用至关重要。最近的进步主要集中在估计人类等某些特定元素的活动上。在本文中，我们利用神经运动场来估计多视图设置中所有点的运动。由于颜色相似的点和与时变颜色的点的歧义，从动态场景中对动态场景进行建模运动是具有挑战性的。我们建议将估计运动的正规化为可预测。如果已知来自以前的帧的运动，那么在不久的将来的运动应该是可以预测的。因此，我们通过首先调节潜在嵌入的估计运动来引入可预测性正则化，然后通过采用预测网络来在嵌入式上执行可预测性。所提出的框架pref（可预测性正则化字段）比基于最先进的神经运动场的动态场景表示方法在PAR或更好的结果上取得了更好的成绩，同时不需要对场景的先验知识。

估计路径的旅行时间是智能运输系统的重要主题。它是现实世界应用的基础，例如交通监控，路线计划和出租车派遣。但是，为这样的数据驱动任务构建模型需要大量用户的旅行信息，这与其隐私直接相关，因此不太可能共享。数据所有者之间的非独立和相同分布的（非IID）轨迹数据也使一个预测模型变得极具挑战性，如果我们直接应用联合学习。最后，以前关于旅行时间估算的工作并未考虑道路的实时交通状态，我们认为这可以极大地影响预测。为了应对上述挑战，我们为移动用户组引入GOF-TTE，生成的在线联合学习框架以进行旅行时间估计，这是我）使用联合学习方法，允许在培训时将私人数据保存在客户端设备上，并设计设计和设计。所有客户共享的全球模型作为在线生成模型推断实时道路交通状态。 ii）除了在服务器上共享基本模型外，还针对每个客户调整了一个微调的个性化模型来研究其个人驾驶习惯，从而弥补了本地化全球模型预测的残余错误。 ％iii）将全球模型设计为所有客户共享的在线生成模型，以推断实时道路交通状态。我们还对我们的框架采用了简单的隐私攻击，并实施了差异隐私机制，以进一步保证隐私安全。最后，我们对Didi Chengdu和Xi'an的两个现实世界公共出租车数据集进行了实验。实验结果证明了我们提出的框架的有效性。

由于物联网（IoT）技术的快速开发，许多在线Web应用程序（例如Google Map和Uber）估计移动设备收集的轨迹数据的旅行时间。但是，实际上，复杂的因素（例如网络通信和能量限制）使以低采样率收集的多个轨迹。在这种情况下，本文旨在解决稀疏场景中的旅行时间估计问题（TTE）和路线恢复问题，这通常会导致旅行时间的不确定标签以及连续采样的GPS点之间的路线。我们将此问题提出为不进行的监督问题，其中训练数据具有粗糙的标签，并共同解决了TTE和路线恢复的任务。我们认为，这两个任务在模型学习过程中彼此互补并保持这种关系：更精确的旅行时间可以使路由更好地推断，从而导致更准确的时间估计）。基于此假设，我们提出了一种EM算法，以替代E估计通过E步中通过弱监督的推断路线的行进时间，并根据M步骤中的估计行进时间来检索途径，以稀疏轨迹。我们对三个现实世界轨迹数据集进行了实验，并证明了该方法的有效性。

半监督的对象检测在平均教师驱动的自我训练的发展中取得了重大进展。尽管结果有令人鼓舞，但在先前的工作中尚未完全探索标签不匹配问题，从而导致自训练期间严重确认偏见。在本文中，我们从两个不同但互补的角度（即分布级别和实例级别）提出了一个简单而有效的标签框架。对于前者，根据Monte Carlo采样，可以合理地近似来自标记数据的未标记数据的类分布。在这种弱监督提示的指导下，我们引入了一个重新分配卑鄙的老师，该老师利用自适应标签 - 分布意识到的信心阈值来生成无偏见的伪标签来推动学生学习。对于后一个，存在着跨教师模型的被忽视的标签分配歧义问题。为了解决这个问题，我们提出了一种新的标签分配机制，用于自我训练框架，即提案自我分配，该机制将学生的建议注入教师，并生成准确的伪标签，以相应地匹配学生模型中的每个建议。 MS-Coco和Pascal-VOC数据集的实验证明了我们提出的框架与其他最先进的框架相当优越。代码将在https://github.com/hikvision-research/ssod上找到。

常见的图像到图像翻译方法依赖于来自源和目标域的数据的联合培训。这可以防止培训过程保留域数据的隐私（例如，在联合环境中），并且通常意味着必须对新模型进行新的模型。我们提出了双扩散隐式桥（DDIB），这是一种基于扩散模型的图像翻译方法，它绕过域对训练。带有DDIBS的图像翻译依赖于对每个域独立训练的两个扩散模型，并且是一个两步的过程：DDIB首先获得具有源扩散模型的源图像的潜在编码，然后使用目标模型来解码此类编码，以构造目标模型。这两个步骤均通过ODE定义，因此该过程仅与ODE求解器的离散误差有关。从理论上讲，我们将DDIB解释为潜在源的串联，而潜在的靶向Schr \” Odinger Bridges是一种熵调节的最佳运输形式，以解释该方法的功效。我们在实验上都应用了ddibs，在合成和高级和高位上应用DDIB分辨率图像数据集，以在各种翻译任务中演示其实用性及其与现有最佳传输方法的连接。

作为一个决定性的部分，在移动式服务（MAA）的成功中，人群运动的时空预测建模是一个具有挑战性的任务，特别是考虑到社会事件驱动偏离正常性的移动性行为的情景。虽然已经进行了深入学习的高级时空态度，但大多数情况下都是巨大进展，如果不是所有现有方法都不知道多种传输模式之间的动态相互作用，也不是对潜在的社会事件带来的前所未有的波动性。在本文中，我们的动力是从两个视角改善规范时空网络（ST-Net）：（1）设计异质移动信息网络（Hmin），明确地在多模式移动性中明确代表差异; （2）提出内存增强的动态滤波器发生器（MDFG），以产生各种场景的动态方式生成序列特定参数。增强的事件感知的时空网络，即East-Net，在几个现实世界数据集中评估了各种各样的社会事件的繁多和覆盖范围。与最先进的基线相比，定量和定性实验结果验证了我们方法的优势。代码和数据在https://github.com/dunderdoc-wang/east-net上发布。