步态识别旨在通过相机来识别一个距离的人。随着深度学习的出现，步态识别的重大进步通过使用深度学习技术在许多情况下取得了鼓舞人心的成功。然而，对视频监视的越来越多的需求引入了更多的挑战，包括在各种方差下进行良好的识别，步态序列中的运动信息建模，由于协议方差，生物量标准安全性和预防隐私而引起的不公平性能比较。本文对步态识别的深度学习进行了全面的调查。我们首先介绍了从传统算法到深层模型的步态识别的奥德赛，从而提供了对步态识别系统的整个工作流程的明确知识。然后，从深度表示和建筑的角度讨论了步态识别的深入学习，并深入摘要。具体而言，深层步态表示分为静态和动态特征，而深度体系结构包括单流和多流架构。遵循我们提出的新颖性分类法，它可能有益于提供灵感并促进对步态认识的感知。此外，我们还提供了所有基于视觉的步态数据集和性能分析的全面摘要。最后，本文讨论了一些潜在潜在前景的开放问题。

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

我们通过与与前面令牌的局部相似度，通过调节从大语料库检索的文档块来增强自动回归语言模型。尽管使用25美元\时分，我们的检索增强型变压器（RetroCro）的检索增强型变压器（RetroCr）对GPT-3和侏罗纪-1获得了可比性的性能。微调后，复古表演转换为下游知识密集型任务，如问题应答。复古结合了冷冻BERT猎犬，一种可微分的编码器和块状的横向机制，以预测基于数量级的令牌，而不是训练期间通常消耗的数量。我们通常从头开始训练复古，还可以快速改造预先接受的变压器，通过检索，仍然达到良好的性能。我们的工作通过以前所未有的规模开辟了通过显式内存改进语言模型的新途径。

移动边缘计算（MEC）是一个突出的计算范例，它扩展了无线通信的应用领域。由于用户设备和MEC服务器的能力的限制，边缘缓存（EC）优化对于有效利用启用MEC的无线网络中的高速利用。然而，内容普及空间和时间的动态和复杂性以及用户的隐私保护对EC优化构成了重大挑战。在本文中，提出了一种隐私保留的分布式深度确定性政策梯度（P2D3PG）算法，以最大化MEC网络中设备的高速缓存命中率。具体而言，我们认为内容流行度是动态，复杂和不可观察的事实，并制定了在隐私保存的限制下作为分布式问题的设备的高速缓存命中速率的最大化。特别是，我们将分布式优化转换为分布式的无模型马尔可夫决策过程问题，然后介绍一种隐私保留的联合学习方法，用于普及预测。随后，基于分布式增强学学习开发了P2D3PG算法以解决分布式问题。仿真结果表明，在保护用户隐私的同时通过基线方法提高EC击中率的提出方法的优越性。

医疗AI通过支持基于证据的医学实践，个性化患者治疗，降低成本以及改善提供者和患者体验，推进医疗保健的巨大潜力。我们认为解锁此潜力需要一种系统的方法来衡量在大规模异构数据上的医疗AI模型的性能。为了满足这种需求，我们正在建立Medperf，这是一个开放的框架，用于在医疗领域的基准测试机器学习。 Medperf将使联合评估能够将模型安全地分配给不同的评估设施，从而赋予医疗组织在高效和人类监督过程中评估和验证AI模型的性能，同时优先考虑隐私。我们描述了当前的挑战医疗保健和AI社区面临，需要开放平台，Medperf的设计理念，其目前的实施状态和我们的路线图。我们呼吁研究人员和组织加入我们创建Medperf开放基准平台。

Terahertz频段（0.1---10 THZ）中的无线通信被视为未来第六代（6G）无线通信系统的关键促进技术之一，超出了大量多重输入多重输出（大量MIMO）技术。但是，THZ频率的非常高的传播衰减和分子吸收通常限制了信号传输距离和覆盖范围。从最近在可重构智能表面（RIS）上实现智能无线电传播环境的突破，我们为多跳RIS RIS辅助通信网络提供了一种新型的混合波束形成方案，以改善THZ波段频率的覆盖范围。特别是，部署了多个被动和可控的RIS，以协助基站（BS）和多个单人体用户之间的传输。我们通过利用最新的深钢筋学习（DRL）来应对传播损失的最新进展，研究了BS在BS和RISS上的模拟光束矩阵的联合设计。为了改善拟议的基于DRL的算法的收敛性，然后设计了两种算法，以初始化数字波束形成和使用交替优化技术的模拟波束形成矩阵。仿真结果表明，与基准相比，我们提出的方案能够改善50 \％的THZ通信范围。此外，还表明，我们提出的基于DRL的方法是解决NP-固定光束形成问题的最先进方法，尤其是当RIS辅助THZ通信网络的信号经历多个啤酒花时。

由于其快速和低功率配置，可重新配置的智能表面（RISS）最近被视为未来无线网络的节能解决方案，这在实现大规模连通性和低延迟通信方面具有增加的潜力。基于RIS的系统中的准确且低空的通道估计是通常的RIS单元元素及其独特的硬件约束，这是最关键的挑战之一。在本文中，我们专注于RIS授权的多用户多用户多输入单输出（MISO）上行链路通信系统的上行链路，并根据并行因子分解提出了一个通道估计框架，以展开所得的级联通道模型。我们为基站和RIS之间的渠道以及RIS与用户之间的渠道提供了两种迭代估计算法。一个基于交替的最小二乘（ALS），而另一个使用向量近似消息传递到迭代的迭代中，从估计的向量重建了两个未知的通道。为了从理论上评估基于ALS的算法的性能，我们得出了其估计值CRAM \'ER-RAO BOND（CRB）。我们还通过估计的通道和基本站的不同预码方案讨论了可实现的总和率计算。我们的广泛仿真结果表明，我们的算法表现优于基准方案，并且ALS技术可实现CRB。还证明，使用估计通道的总和率总是在各种设置下达到完美通道的总和，从而验证了提出的估计算法的有效性和鲁棒性。

Existing automated techniques for software documentation typically attempt to reason between two main sources of information: code and natural language. However, this reasoning process is often complicated by the lexical gap between more abstract natural language and more structured programming languages. One potential bridge for this gap is the Graphical User Interface (GUI), as GUIs inherently encode salient information about underlying program functionality into rich, pixel-based data representations. This paper offers one of the first comprehensive empirical investigations into the connection between GUIs and functional, natural language descriptions of software. First, we collect, analyze, and open source a large dataset of functional GUI descriptions consisting of 45,998 descriptions for 10,204 screenshots from popular Android applications. The descriptions were obtained from human labelers and underwent several quality control mechanisms. To gain insight into the representational potential of GUIs, we investigate the ability of four Neural Image Captioning models to predict natural language descriptions of varying granularity when provided a screenshot as input. We evaluate these models quantitatively, using common machine translation metrics, and qualitatively through a large-scale user study. Finally, we offer learned lessons and a discussion of the potential shown by multimodal models to enhance future techniques for automated software documentation.

View-dependent effects such as reflections pose a substantial challenge for image-based and neural rendering algorithms. Above all, curved reflectors are particularly hard, as they lead to highly non-linear reflection flows as the camera moves. We introduce a new point-based representation to compute Neural Point Catacaustics allowing novel-view synthesis of scenes with curved reflectors, from a set of casually-captured input photos. At the core of our method is a neural warp field that models catacaustic trajectories of reflections, so complex specular effects can be rendered using efficient point splatting in conjunction with a neural renderer. One of our key contributions is the explicit representation of reflections with a reflection point cloud which is displaced by the neural warp field, and a primary point cloud which is optimized to represent the rest of the scene. After a short manual annotation step, our approach allows interactive high-quality renderings of novel views with accurate reflection flow. Additionally, the explicit representation of reflection flow supports several forms of scene manipulation in captured scenes, such as reflection editing, cloning of specular objects, reflection tracking across views, and comfortable stereo viewing. We provide the source code and other supplemental material on https://repo-sam.inria.fr/ fungraph/neural_catacaustics/

In large-scale machine learning, recent works have studied the effects of compressing gradients in stochastic optimization in order to alleviate the communication bottleneck. These works have collectively revealed that stochastic gradient descent (SGD) is robust to structured perturbations such as quantization, sparsification, and delays. Perhaps surprisingly, despite the surge of interest in large-scale, multi-agent reinforcement learning, almost nothing is known about the analogous question: Are common reinforcement learning (RL) algorithms also robust to similar perturbations? In this paper, we investigate this question by studying a variant of the classical temporal difference (TD) learning algorithm with a perturbed update direction, where a general compression operator is used to model the perturbation. Our main technical contribution is to show that compressed TD algorithms, coupled with an error-feedback mechanism used widely in optimization, exhibit the same non-asymptotic theoretical guarantees as their SGD counterparts. We then extend our results significantly to nonlinear stochastic approximation algorithms and multi-agent settings. In particular, we prove that for multi-agent TD learning, one can achieve linear convergence speedups in the number of agents while communicating just $\tilde{O}(1)$ bits per agent at each time step. Our work is the first to provide finite-time results in RL that account for general compression operators and error-feedback in tandem with linear function approximation and Markovian sampling. Our analysis hinges on studying the drift of a novel Lyapunov function that captures the dynamics of a memory variable introduced by error feedback.