尖峰神经网络（SNN）是一种受脑启发的模型，具有更时空的信息处理能力和计算能效效率。但是，随着SNN深度的增加，由SNN​​的重量引起的记忆问题逐渐引起了人们的注意。受到人工神经网络（ANN）量化技术的启发，引入了二进制SNN（BSNN）来解决记忆问题。由于缺乏合适的学习算法，BSNN通常由ANN-SNN转换获得，其准确性将受到训练有素的ANN的限制。在本文中，我们提出了具有准确性损失估计器的超低潜伏期自适应局部二进制二进制尖峰神经网络（ALBSNN），该网络层动态选择要进行二进制的网络层，以通过评估由二进制重量引起的错误来确保网络的准确性在网络学习过程中。实验结果表明，此方法可以将存储空间降低超过20％，而不会丢失网络准确性。同时，为了加速网络的训练速度，引入了全球平均池（GAP）层，以通过卷积和合并的组合替换完全连接的层，以便SNN可以使用少量时间获得更好识别准确性的步骤。在仅使用一个时间步骤的极端情况下，我们仍然可以在三个不同的数据集（FashionMnist，CIFAR-10和CIFAR-10和CIFAR-100）上获得92.92％，91.63％和63.54％的测试精度。

最近的基于学习的初始化算法已经达到了在删除视频中的不期望的对象之后完成缺失区域的令人信服的结果。为了保持帧之间的时间一致性，3D空间和时间操作通常在深网络中使用。但是，这些方法通常遭受内存约束，只能处理低分辨率视频。我们提出了一种用于高分辨率视频侵略的新型空间剩余聚集框架。关键的想法是首先在下采样的低分辨率视频上学习和应用空间和时间内染色网络。然后，我们通过将学习的空间和时间图像残差（细节）聚合到上采样的染色帧来细化低分辨率结果。定量和定性评估都表明，我们可以生产出比确定高分辨率视频的最先进的方法产生更多的时间相干和视觉上吸引力。

通过不懈的研究增强了StyleGAN的语义可控性。尽管现有的弱监督方法在沿一个属性操纵样式代码方面很好地奏效，但操纵多个属性的准确性被忽略了。多属性表示很容易在stylegan潜在空间中纠缠，而顺序编辑会导致错误积累。为了解决这些局限性，我们设计了一个动态样式操纵网络（Dystyle），其结构和参数因输入样本而异，以执行非线性和自适应操纵潜在代码，以进行灵活和精确的属性控制。为了有效且稳定地优化障碍网络，我们提出了动态的多属性对比度学习（DMACL）方法：包括动态的多重构造对比度和动态多属性对比损失，同时将各种属性从生成中删除模型的图像和潜在空间。结果，我们的方法表明了沿多个数字和二进制属性的细粒度分离的编辑。与现有样式操纵方法的定性和定量比较验证了我们方法在多属性控制的准确性和身份保存方面的优越性，而不会损害光真相。

Conditional Generative Adversarial Networks (GANs) for cross-domain image-to-image translation have made much progress recently [7,8,21,12,4,18]. Depending on the task complexity, thousands to millions of labeled image pairs are needed to train a conditional GAN. However, human labeling is expensive, even impractical, and large quantities of data may not always be available. Inspired by dual learning from natural language translation [23], we develop a novel dual-GAN mechanism, which enables image translators to be trained from two sets of unlabeled images from two domains. In our architecture, the primal GAN learns to translate images from domain U to those in domain V , while the dual GAN learns to invert the task. The closed loop made by the primal and dual tasks allows images from either domain to be translated and then reconstructed. Hence a loss function that accounts for the reconstruction error of images can be used to train the translators. Experiments on multiple image translation tasks with unlabeled data show considerable performance gain of Du-alGAN over a single GAN. For some tasks, DualGAN can even achieve comparable or slightly better results than conditional GAN trained on fully labeled data.

Query-focused summarization has been considered as an important extension for text summarization. It aims to generate a concise highlight for a given query. Different from text summarization, query-focused summarization has long been plagued by the problem of lacking high-quality large-scale datasets. In this paper, we investigate the idea that whether we can integrate and transfer the knowledge of text summarization and question answering to assist the few-shot learning in query-focused summarization. Here, we propose prefix-merging, a prefix-based pretraining strategy for few-shot learning in query-focused summarization. Drawn inspiration from prefix-tuning, we are allowed to integrate the task knowledge from text summarization and question answering into a properly designed prefix and apply the merged prefix to query-focused summarization. With only a small amount of trainable parameters, prefix-merging outperforms fine-tuning on query-focused summarization. We further discuss the influence of different prefix designs and propose a visualized explanation for how prefix-merging works.

Increasing number of COVID-19 research literatures cause new challenges in effective literature screening and COVID-19 domain knowledge aware Information Retrieval. To tackle the challenges, we demonstrate two tasks along withsolutions, COVID-19 literature retrieval, and question answering. COVID-19 literature retrieval task screens matching COVID-19 literature documents for textual user query, and COVID-19 question answering task predicts proper text fragments from text corpus as the answer of specific COVID-19 related questions. Based on transformer neural network, we provided solutions to implement the tasks on CORD-19 dataset, we display some examples to show the effectiveness of our proposed solutions.

双层金属管（BMT）在工程应用中起着极其至关重要的作用，旋转弯曲弯曲（RDB）可以实现高精度弯曲处理，但是，该产品将进一步弹回。由于BMT的复杂结构和数据集获取的高成本，基于机制研究和机器学习的现有方法无法满足Spresback预测的工程要求。根据初步机制分析，提出了物理逻辑增强网络（PE-NET）。该体系结构包括ES-NET等效BMT与单层管等效，SP-NET用于带有足够的单层管样品的浮回本的最终预测。具体而言，在第一阶段，通过理论驱动的预探测和数据驱动的预处理，ES-NET和SP-NET分别构建。在第二阶段，在物理逻辑下，PE-NET由ES-NET和SP-NET组装，然后与小样本BMT数据集和复合损耗函数进行微调。 FE模拟数据集，小样本数据集BMT BMT弹回角预测验证了所提出方法的有效性和稳定性，并证明了跨性别和工程应用程序的潜在方法。

In online experimentation, appropriate metrics (e.g., purchase) provide strong evidence to support hypotheses and enhance the decision-making process. However, incomplete metrics are frequently occurred in the online experimentation, making the available data to be much fewer than the planned online experiments (e.g., A/B testing). In this work, we introduce the concept of dropout buyers and categorize users with incomplete metric values into two groups: visitors and dropout buyers. For the analysis of incomplete metrics, we propose a clustering-based imputation method using $k$-nearest neighbors. Our proposed imputation method considers both the experiment-specific features and users' activities along their shopping paths, allowing different imputation values for different users. To facilitate efficient imputation of large-scale data sets in online experimentation, the proposed method uses a combination of stratification and clustering. The performance of the proposed method is compared to several conventional methods in both simulation studies and a real online experiment at eBay.

两阶段探测器在3D对象检测中已广受欢迎。大多数两阶段的3D检测器都使用网格点，体素电网或第二阶段的ROI特征提取的采样关键点。但是，这种方法在处理不均匀分布和稀疏的室外点方面效率低下。本文在三个方面解决了这个问题。 1）动态点聚集。我们建议补丁搜索以快速在本地区域中为每个3D提案搜索点。然后，将最远的体素采样采样用于均匀采样点。特别是，体素尺寸沿距离变化，以适应点的不均匀分布。 2）Ro-Graph Poling。我们在采样点上构建本地图，以通过迭代消息传递更好地模型上下文信息和地雷关系。 3）视觉功能增强。我们引入了一种简单而有效的融合策略，以补偿具有有限语义提示的稀疏激光雷达点。基于这些模块，我们将图形R-CNN构建为第二阶段，可以将其应用于现有的一阶段检测器，以始终如一地提高检测性能。广泛的实验表明，图R-CNN的表现优于最新的3D检测模型，而Kitti和Waymo Open DataSet的差距很大。我们在Kitti Bev汽车检测排行榜上排名第一。代码将在\ url {https://github.com/nightmare-n/graphrcnn}上找到。

已经提出了需要树木，以模拟在开放域的文本问题答案的背景下进行解释产生的人类推理过程。但是，实际上，手动构建这些解释树是一个艰苦的过程，需要积极的人类参与。鉴于捕获从问题到答案的推理线的复杂性，或者从索赔中捕获了前提，因此出现了如何帮助用户有效地构建多个级别的树木，并给定大量可用事实。在本文中，我们将需要树的构造作为一系列主动的前提选择步骤，即，对于说明树中的每个中间节点，专家需要注释大型候选人列表中的前提事实的正面和负面示例。然后，我们迭代地进行精细 - 训练前训练的变压器模型，并产生了正面和紧密控制的负面样本，并旨在平衡语义关系和解释性的关系关系的编码。实验评估证实了拟议的主动精细研究方法的可测量效率提高，以促进累积树的构建：与几种替代方案相比，解释性前提选择的提高了20 \％。