非对比度CT（NCCT）图像中准确的梗塞分割是迈向计算机辅助急性缺血性中风（AIS）评估的关键步骤。在临床实践中，脑半球的双侧对称比较通常用于定位病理异常。最近的研究探索了不对称的协助AIS分割。但是，在评估其对AIS的贡献时，大多数以前基于对称性的工作都混合了不同类型的不对称性。在本文中，我们提出了一个新型的不对称分解网络（ADN），以自动将NCCT中的病理不对称性和内在的解剖不对称分离，以进行更有效和可解释的AIS分割。 ADN首先基于输入NCCT进行不对称分解，该输入nccts产生不同类型的3D不对称图。然后生成合成的，固有的 - 敏化补偿和病理 - 空气 - 对称盐的NCCT体积，后来用作分割网络的输入。 ADN的培训结合了领域知识，并采用了组织型意识到的正则化损失函数，以鼓励临床上敏感的病理不对称提取。加上无监督的3D转换网络，ADN在公共NCCT数据集上实现了最新的AIS分割性能。除了出色的表现外，我们认为学到的临床可解剖的不对称图也可以为更好地理解AIS评估提供见解。我们的代码可从https://github.com/nihaomiao/miccai22_adn获得。

当社会机器人和其他智能机器进入家中时，人工情感智力（AEI）正在焦点，以应对用户对更深入，更有意义的人类机器互动的渴望。为了完成这种有效的互动，下一代AEI需要全面的人类情感模型才能进行训练。与情感理论（一直是心理学的历史重点）不同，情感模型是一种描述性工具。在实践中，最强的模型需要强大的覆盖范围，这意味着定义最小的情绪集可以从中得出所有其他情感。为了实现所需的覆盖范围，我们转向自然语言处理中的单词嵌入。我们的实验使用无监督的聚类技术表明，只有15个离散的情绪类别，我们可以在六种主要语言（阿拉伯语，中文，英语，法语，西班牙语和俄语）上提供最大的覆盖范围。为了支持我们的发现，我们还检查了来自两个大规模情感识别数据集的注释，以评估与人类观念的规模观念相比，评估现有情绪模型的有效性。由于强大的，全面的情感模型是开发现实世界情感计算应用的基础，因此这项工作对社会机器人技术，人机互动，心理保健和计算心理学具有广泛的影响。

大多数传统人群计数方法利用完全监督的学习框架来学习场景图像和人群密度映射之间的映射。在这种完全监督培训设置的情况下，需要大量昂贵且耗时的像素级注释，以产生密度图作为监控。减少昂贵标签的一种方法是利用未标记图像之间的自我结构信息和内在关系。与利用原始图像级别的这些关系和结构信息的先前方法不同，我们从潜在特征空间探讨了这种自我关系，因为它可以提取更丰富的关系和结构信息。具体而言，我们提出了S $ ^ 2 $ FPR，其可以提取结构信息，并在潜在空间中学习粗良好的金字塔特征的部分订单，以便更好地与大规模未标记的图像计数。此外，我们收集了一个新的未标记的人群计数数据集（Fudan-UCC），总共有4,000张图片进行培训。一个副产物是我们提出的S $ ^ 2 $ FPR方法可以利用未标记图像之间的潜在空间中的众多部分订单来加强模型表示能力，并减少人群计数任务的估计误差。关于四个基准数据集的大量实验，即UCF-QNRF，Shanghaitech Parta和Partb以及UCF-CC-50，与先前半监督方法相比，我们的方法显示了我们的方法。源代码和数据集可用于https://github.com/bridgeqiqi/s2fpr。

在急诊室（ER）环境中，中风分类或筛查是一个普遍的挑战。由于MRI的慢速吞吐量和高成本，通常会进行快速CT而不是MRI。在此过程中通常提到临床测试，但误诊率仍然很高。我们提出了一个新型的多模式深度学习框架，深沉的中风，以通过识别较小的面部肌肉不协调的模式来实现计算机辅助中风的存在评估，并使怀疑急性环境中的中风的患者无能为力。我们提出的深雷克斯（Deepstroke）在中风分流器中容易获得一分钟的面部视频数据和音频数据，用于局部面部瘫痪检测和全球语音障碍分析。采用了转移学习来减少面部侵蚀偏见并提高普遍性。我们利用多模式的横向融合来结合低水平和高级特征，并为关节训练提供相互正则化。引入了新型的对抗训练以获得无身份和中风的特征。与实际急诊室患者进行的视频ADIO数据集进行的实验表明，与分类团队和ER医生相比，中风的表现要优于最先进的模型，并且取得更好的性能，比传统的敏感性高出10.94％，高7.37％的精度高出7.37％。当特异性对齐时，中风分类。同时，每个评估都可以在不到六分钟的时间内完成，这表明该框架的临床翻译潜力很大。

This paper presents a Neuromorphic Starter Kit, which has been designed to help a variety of research groups perform research, exploration and real-world demonstrations of brain-based, neuromorphic processors and hardware environments. A prototype kit has been built and tested. We explain the motivation behind the kit, its design and composition, and a prototype physical demonstration.

磁共振光谱成像（MRSI）是量化体内代谢物的必不可少的工具，但是低空间分辨率限制了其临床应用。基于深度学习的超分辨率方法为改善MRSI的空间分辨率提供了有希望的结果，但是与实验获得的高分辨率图像相比，超级分辨图像通常是模糊的。已经使用生成对抗网络进行了尝试，以提高图像视觉质量。在这项工作中，我们考虑了另一种类型的生成模型，即基于流的模型，与对抗网络相比，训练更稳定和可解释。具体而言，我们提出了一个基于流动的增强器网络，以提高超分辨率MRSI的视觉质量。与以前的基于流的模型不同，我们的增强器网络包含了来自其他图像模式（MRI）的解剖信息，并使用可学习的基础分布。此外，我们施加指南丢失和数据一致性丢失，以鼓励网络在保持高忠诚度的同时以高视觉质量生成图像。从25名高级神经胶质瘤患者获得的1H-MRSI数据集上进行的实验表明，我们的增强子网络的表现优于对抗网络和基线基线方法。我们的方法还允许视觉质量调整和不确定性估计。

Multivariate time series forecasting with hierarchical structure is pervasive in real-world applications, demanding not only predicting each level of the hierarchy, but also reconciling all forecasts to ensure coherency, i.e., the forecasts should satisfy the hierarchical aggregation constraints. Moreover, the disparities of statistical characteristics between levels can be huge, worsened by non-Gaussian distributions and non-linear correlations. To this extent, we propose a novel end-to-end hierarchical time series forecasting model, based on conditioned normalizing flow-based autoregressive transformer reconciliation, to represent complex data distribution while simultaneously reconciling the forecasts to ensure coherency. Unlike other state-of-the-art methods, we achieve the forecasting and reconciliation simultaneously without requiring any explicit post-processing step. In addition, by harnessing the power of deep model, we do not rely on any assumption such as unbiased estimates or Gaussian distribution. Our evaluation experiments are conducted on four real-world hierarchical datasets from different industrial domains (three public ones and a dataset from the application servers of Alipay's data center) and the preliminary results demonstrate efficacy of our proposed method.

In this work, we explore a useful but often neglected methodology for robustness analysis of text generation evaluation metrics: stress tests with synthetic data. Basically, we design and synthesize a wide range of potential errors and check whether they result in a commensurate drop in the metric scores. We examine a range of recently proposed evaluation metrics based on pretrained language models, for the tasks of open-ended generation, translation, and summarization. Our experiments reveal interesting insensitivities, biases, or even loopholes in existing metrics. For example, we find that BERTScore ignores truncation errors in summarization, and MAUVE (built on top of GPT-2) is insensitive to errors at the beginning of generations. Further, we investigate the reasons behind these blind spots and suggest practical workarounds for a more reliable evaluation of text generation.

Facial action units (FAUs) are critical for fine-grained facial expression analysis. Although FAU detection has been actively studied using ideally high quality images, it was not thoroughly studied under heavily occluded conditions. In this paper, we propose the first occlusion-robust FAU recognition method to maintain FAU detection performance under heavy occlusions. Our novel approach takes advantage of rich information from the latent space of masked autoencoder (MAE) and transforms it into FAU features. Bypassing the occlusion reconstruction step, our model efficiently extracts FAU features of occluded faces by mining the latent space of a pretrained masked autoencoder. Both node and edge-level knowledge distillation are also employed to guide our model to find a mapping between latent space vectors and FAU features. Facial occlusion conditions, including random small patches and large blocks, are thoroughly studied. Experimental results on BP4D and DISFA datasets show that our method can achieve state-of-the-art performances under the studied facial occlusion, significantly outperforming existing baseline methods. In particular, even under heavy occlusion, the proposed method can achieve comparable performance as state-of-the-art methods under normal conditions.

While many systems have been developed to train Graph Neural Networks (GNNs), efficient model inference and evaluation remain to be addressed. For instance, using the widely adopted node-wise approach, model evaluation can account for up to 94% of the time in the end-to-end training process due to neighbor explosion, which means that a node accesses its multi-hop neighbors. On the other hand, layer-wise inference avoids the neighbor explosion problem by conducting inference layer by layer such that the nodes only need their one-hop neighbors in each layer. However, implementing layer-wise inference requires substantial engineering efforts because users need to manually decompose a GNN model into layers for computation and split workload into batches to fit into device memory. In this paper, we develop Deep Graph Inference (DGI) -- a system for easy and efficient GNN model inference, which automatically translates the training code of a GNN model for layer-wise execution. DGI is general for various GNN models and different kinds of inference requests, and supports out-of-core execution on large graphs that cannot fit in CPU memory. Experimental results show that DGI consistently outperforms layer-wise inference across different datasets and hardware settings, and the speedup can be over 1,000x.