当前的时空动作管检测方法通常将一个给定键框的边界框提案扩展到附近帧的3D颞轴和池特征。但是，如果演员的位置或形状通过大型的2D运动和可变性，由于大型摄像机运动，大型演员形状变形，快速演员的动作等，这种合并就无法积累有意义的时空特征。在这项工作中，我们旨在研究在大动作下的动作检测中观察到Cuboid感知特征聚集的性能。此外，我们建议通过跟踪参与者并沿各个轨道进行时间特征聚集来增强演员特征表示。我们在各种固定时间尺度的动作管/轨道框之间使用相交的行动者（IOU）定义了演员运动。随着时间的推移，具有较大运动的动作将导致较低的IOU，并且较慢的动作将保持更高的IOU。我们发现，轨道感知功能聚集始终取得了巨大的改善，尤其是对于与Cuboid感知的基线相比，在大型运动下进行的动作。结果，我们还报告了大规模多运动数据集的最先进。

虽然从图像中回归3D人类的方法迅速发展，但估计的身体形状通常不会捕获真正的人形状。这是有问题的，因为对于许多应用，准确的身体形状与姿势一样重要。身体形状准确性差姿势准确性的关键原因是缺乏数据。尽管人类可以标记2D关节，并且这些约束3D姿势，但“标记” 3D身体形状并不容易。由于配对的数据与图像和3D身体形状很少见，因此我们利用了两个信息来源：（1）我们收集了各种“时尚”模型的互联网图像，以及一系列的人体测量值； （2）我们为3D身体网眼和模型图像收集语言形状属性。综上所述，这些数据集提供了足够的约束来推断密集的3D形状。我们利用几种新型方法来利用人体测量和语言形状属性来训练称为Shapy的神经网络，从而从RGB图像中回归了3D人类的姿势和形状。我们在公共基准测试上评估shapy，但请注意，它们要么缺乏明显的身体形状变化，地面真实形状或衣服变化。因此，我们收集了一个新的数据集，用于评估3D人类形状估计，称为HBW，其中包含“野生人体”的照片，我们为其具有地面3D身体扫描。在这个新的基准测试中，Shapy在3D身体估计的任务上的最先进方法极大地胜过。这是第一次演示，即可以从易于观察的人体测量和语言形状属性中训练来自图像的3D体形回归。我们的模型和数据可在以下网址获得：shapy.is.tue.mpg.de

生成数字人类，现实地具有许多应用，并且被广泛研究，但现有的方法专注于身体的主要肢体，忽略了手和头部。手已经分开研究，但重点是在产生现实的静态爪子上。要综合与世界互动的虚拟字符，我们需要同时生成全身运动和现实手掌。两个子问题都是挑战自己，在一起，姿势的状态空间显着更大，手和身体运动的尺度不同，而且整体姿势和手柄必须同意，满足身体限制，以及是合理的。此外，头部涉及，因为化身必须查看对象与它交互。我们第一次解决了生成一个抓住未知物体的头像的全身，手和头部运动的问题。作为输入，我们的方法，称为目标，采用3D对象，其位置和起始3D身体姿势和形状。目标使用两种新颖的网络输出一系列全身姿势。首先，GNET通过现实的身体，头部，臂和手姿势产生目标全体掌握，以及手对象接触。其次，MNET生成起始和目标姿势之间的运动。这是具有挑战性的，因为它需要头像与脚踏接触朝向物体走向物体，将头部向朝向它朝向它，伸出伸展，并用现实的手姿势和手工触点抓住它。为了实现这一网络，网络利用组合SMPL-X身体参数和3D顶点偏移的表示。我们在标准数据集上培训和评估目标，定性和定量。结果表明，目标概括了不佳的对象，表现优于基线。目标是迈向综合现实的全身对象掌握。

以准确的，稳健和快速的方式拟合人体，手或面对稀疏输入信号的参数模型，这具有重要的是在AR和VR场景中显着改善浸入。解决这些问题的系统中的一个常见的第一步是直接从输入数据重新分配参数模型的参数。这种方法是快速，稳健的，并且是迭代最小化算法的良好起点。后者搜索最小的能量函数，通常由编码关于问题的结构的知识的数据项和前沿组成。虽然这无疑是一个非常成功的食谱，但前锋往往是手工定义的启发式，发现不同术语之间的正确平衡，以实现高质量的结果是一个非琐碎的任务。此外，转换和优化这些系统以表现方式运行，需要定制实现，要求从工程师和域专家进行大量时间投资。在这项工作中，我们建立了近期学习优化的进步，并提出了由Classic Levenberg-Marquardt算法启发的更新规则。我们展示了所提出的神经优化器对从2D地标的头戴式装置和面部配件的3D体表估计问题的有效性。我们的方法可以很容易地应用于新的模型拟合问题，并提供竞争替代方案，在准确性和速度方面都提供了良好的调谐“传统”模型拟合管道。

To facilitate the analysis of human actions, interactions and emotions, we compute a 3D model of human body pose, hand pose, and facial expression from a single monocular image. To achieve this, we use thousands of 3D scans to train a new, unified, 3D model of the human body, SMPL-X, that extends SMPL with fully articulated hands and an expressive face. Learning to regress the parameters of SMPL-X directly from images is challenging without paired images and 3D ground truth. Consequently, we follow the approach of SMPLify, which estimates 2D features and then optimizes model parameters to fit the features. We improve on SMPLify in several significant ways: (1) we detect 2D features corresponding to the face, hands, and feet and fit the full SMPL-X model to these; (2) we train a new neural network pose prior using a large MoCap dataset; (3) we define a new interpenetration penalty that is both fast and accurate; (4) we automatically detect gender and the appropriate body models (male, female, or neutral); (5) our PyTorch implementation achieves a speedup of more than 8× over Chumpy. We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild. We evaluate 3D accuracy on a new curated dataset comprising 100 images with pseudo ground-truth. This is a step towards automatic expressive human capture from monocular RGB data. The models, code, and data are available for research purposes at https://smpl-x.is.tue.mpg.de.

Projection operations are a typical computation bottleneck in online learning. In this paper, we enable projection-free online learning within the framework of Online Convex Optimization with Memory (OCO-M) -- OCO-M captures how the history of decisions affects the current outcome by allowing the online learning loss functions to depend on both current and past decisions. Particularly, we introduce the first projection-free meta-base learning algorithm with memory that minimizes dynamic regret, i.e., that minimizes the suboptimality against any sequence of time-varying decisions. We are motivated by artificial intelligence applications where autonomous agents need to adapt to time-varying environments in real-time, accounting for how past decisions affect the present. Examples of such applications are: online control of dynamical systems; statistical arbitrage; and time series prediction. The algorithm builds on the Online Frank-Wolfe (OFW) and Hedge algorithms. We demonstrate how our algorithm can be applied to the online control of linear time-varying systems in the presence of unpredictable process noise. To this end, we develop the first controller with memory and bounded dynamic regret against any optimal time-varying linear feedback control policy. We validate our algorithm in simulated scenarios of online control of linear time-invariant systems.

Identifying named entities such as a person, location or organization, in documents can highlight key information to readers. Training Named Entity Recognition (NER) models requires an annotated data set, which can be a time-consuming labour-intensive task. Nevertheless, there are publicly available NER data sets for general English. Recently there has been interest in developing NER for legal text. However, prior work and experimental results reported here indicate that there is a significant degradation in performance when NER methods trained on a general English data set are applied to legal text. We describe a publicly available legal NER data set, called E-NER, based on legal company filings available from the US Securities and Exchange Commission's EDGAR data set. Training a number of different NER algorithms on the general English CoNLL-2003 corpus but testing on our test collection confirmed significant degradations in accuracy, as measured by the F1-score, of between 29.4\% and 60.4\%, compared to training and testing on the E-NER collection.

Graph neural networks have shown to learn effective node representations, enabling node-, link-, and graph-level inference. Conventional graph networks assume static relations between nodes, while relations between entities in a video often evolve over time, with nodes entering and exiting dynamically. In such temporally-dynamic graphs, a core problem is inferring the future state of spatio-temporal edges, which can constitute multiple types of relations. To address this problem, we propose MTD-GNN, a graph network for predicting temporally-dynamic edges for multiple types of relations. We propose a factorized spatio-temporal graph attention layer to learn dynamic node representations and present a multi-task edge prediction loss that models multiple relations simultaneously. The proposed architecture operates on top of scene graphs that we obtain from videos through object detection and spatio-temporal linking. Experimental evaluations on ActionGenome and CLEVRER show that modeling multiple relations in our temporally-dynamic graph network can be mutually beneficial, outperforming existing static and spatio-temporal graph neural networks, as well as state-of-the-art predicate classification methods.

In contrast to the rapid digitalization of several industries, agriculture suffers from low adoption of smart farming tools. While AI-driven digital agriculture tools can offer high-performing predictive functionalities, they lack tangible quantitative evidence on their benefits to the farmers. Field experiments can derive such evidence, but are often costly, time consuming and hence limited in scope and scale of application. To this end, we propose an observational causal inference framework for the empirical evaluation of the impact of digital tools on target farm performance indicators (e.g., yield in this case). This way, we can increase farmers' trust via enhancing the transparency of the digital agriculture market and accelerate the adoption of technologies that aim to secure farmer income resilience and global agricultural sustainability. As a case study, we designed and implemented a recommendation system for the optimal sowing time of cotton based on numerical weather predictions, which was used by a farmers' cooperative during the growing season of 2021. We then leverage agricultural knowledge, collected yield data, and environmental information to develop a causal graph of the farm system. Using the back-door criterion, we identify the impact of sowing recommendations on the yield and subsequently estimate it using linear regression, matching, inverse propensity score weighting and meta-learners. The results reveal that a field sown according to our recommendations exhibited a statistically significant yield increase that ranged from 12% to 17%, depending on the method. The effect estimates were robust, as indicated by the agreement among the estimation methods and four successful refutation tests. We argue that this approach can be implemented for decision support systems of other fields, extending their evaluation beyond a performance assessment of internal functionalities.

Mobile traffic prediction is of great importance on the path of enabling 5G mobile networks to perform smart and efficient infrastructure planning and management. However, available data are limited to base station logging information. Hence, training methods for generating high-quality predictions that can generalize to new observations on different parties are in demand. Traditional approaches require collecting measurements from different base stations and sending them to a central entity, followed by performing machine learning operations using the received data. The dissemination of local observations raises privacy, confidentiality, and performance concerns, hindering the applicability of machine learning techniques. Various distributed learning methods have been proposed to address this issue, but their application to traffic prediction has yet to be explored. In this work, we study the effectiveness of federated learning applied to raw base station aggregated LTE data for time-series forecasting. We evaluate one-step predictions using 5 different neural network architectures trained with a federated setting on non-iid data. The presented algorithms have been submitted to the Global Federated Traffic Prediction for 5G and Beyond Challenge. Our results show that the learning architectures adapted to the federated setting achieve equivalent prediction error to the centralized setting, pre-processing techniques on base stations lead to higher forecasting accuracy, while state-of-the-art aggregators do not outperform simple approaches.