Deep-learning-based technologies such as deepfakes ones have been attracting widespread attention in both society and academia, particularly ones used to synthesize forged face images. These automatic and professional-skill-free face manipulation technologies can be used to replace the face in an original image or video with any target object while maintaining the expression and demeanor. Since human faces are closely related to identity characteristics, maliciously disseminated identity manipulated videos could trigger a crisis of public trust in the media and could even have serious political, social, and legal implications. To effectively detect manipulated videos, we focus on the position offset in the face blending process, resulting from the forced affine transformation of the normalized forged face. We introduce a method for detecting manipulated videos that is based on the trajectory of the facial region displacement. Specifically, we develop a virtual-anchor-based method for extracting the facial trajectory, which can robustly represent displacement information. This information was used to construct a network for exposing multidimensional artifacts in the trajectory sequences of manipulated videos that is based on dual-stream spatial-temporal graph attention and a gated recurrent unit backbone. Testing of our method on various manipulation datasets demonstrated that its accuracy and generalization ability is competitive with that of the leading detection methods.

Biomedical named entity recognition (BioNER) seeks to automatically recognize biomedical entities in natural language text, serving as a necessary foundation for downstream text mining tasks and applications such as information extraction and question answering. Manually labeling training data for the BioNER task is costly, however, due to the significant domain expertise required for accurate annotation. The resulting data scarcity causes current BioNER approaches to be prone to overfitting, to suffer from limited generalizability, and to address a single entity type at a time (e.g., gene or disease). We therefore propose a novel all-in-one (AIO) scheme that uses external data from existing annotated resources to improve generalization. We further present AIONER, a general-purpose BioNER tool based on cutting-edge deep learning and our AIO schema. We evaluate AIONER on 14 BioNER benchmark tasks and show that AIONER is effective, robust, and compares favorably to other state-of-the-art approaches such as multi-task learning. We further demonstrate the practical utility of AIONER in three independent tasks to recognize entity types not previously seen in training data, as well as the advantages of AIONER over existing methods for processing biomedical text at a large scale (e.g., the entire PubMed data).

Covid-19幸存者中很大一部分经历了经常影响日常生活的持续多系统症状，这种疾病被称为SARS-COV-2感染的长期或急性后静脉曲张。但是，识别长期的卷文章是具有挑战性的，因为文章是指使用各种较少常见的术语或根本不使用命名的条件。我们开发了一个迭代的人类机器学习框架，旨在有效利用可用的数据并最有效地利用人类标签。具体而言，我们的方法将数据编程与主动学习结合到了强大的集合模型中。在保留集上评估我们的模型表明了其他方法的灵敏度的三倍。我们将模型应用于PubMed来创建长期的共同集合，并证明（1）最长的卷vid文章在命名该条件时并不是用任何名称（2）来指代长的covid，在生物医学文献中最常使用的名称是长的，并且（3）长互联物与各种身体系统中的疾病有关。长期COVID系列每周更新，可在Litcovid门户网站上进行在线搜索：https：//www.ncbi.nlm.nih.gov/research/coronavirus/docsum/docsum?filters=e_condition.longcondition.longcovid.longcovid

本文解决了新型类别发现（NCD）的问题，该问题旨在区分大规模图像集中的未知类别。 NCD任务由于与现实世界情景的亲密关系而具有挑战性，我们只遇到了一些部分类和图像。与NCD上的其他作品不同，我们利用原型强调类别歧视的重要性，并减轻缺少新颖阶级注释的问题。具体而言，我们提出了一种新型的适应性原型学习方法，该方法由两个主要阶段组成：原型表示学习和原型自我训练。在第一阶段，我们获得了一个可靠的特征提取器，该功能提取器可以为所有具有基础和新颖类别的图像提供。该功能提取器的实例和类别歧视能力通过自我监督的学习和适应性原型来提高。在第二阶段，我们再次利用原型来整理离线伪标签，并训练类别聚类的最终参数分类器。我们对四个基准数据集进行了广泛的实验，并证明了该方法具有最先进的性能的有效性和鲁棒性。

对象目标视觉导航是一项具有挑战性的任务，旨在仅根据其视觉观察来指导机器人找到目标对象，并且该目标仅限于训练阶段中指定的类。但是，在实际家庭中，机器人可能需要处理许多对象类，并且在培训阶段，所有这些类都很难包含。为了应对这一挑战，我们通过将零照片学习与对象目标视频导航相结合，提出了一个零摄像的对象导航任务，该目标旨在指导机器人找到属于新颖类的对象而无需任何培训样本。这项任务导致需要将学习的政策推广到新颖的班级，这是使用深度强化学习的对象导航问题较小的问题。为了解决这个问题，我们利用“阶级无关”的数据来减轻培训阶段中指定的类过度拟合的输入。与类无关的输入包括检测结果和单词嵌入的余弦相似性，并且不包含任何与类相关的视觉特征或知识图。在AI2 Thor平台上进行的广泛实验表明，我们的模型在可见和看不见的类中都优于基线模型，这证明我们的模型对类别的敏感性较小，并且可以更好地概括。我们的代码可在https://github.com/pioneer-innovation/zero-sero-shot-object-navigation上找到

生物医学文献中的自动关系提取（RE）对于研究和现实世界中的许多下游文本挖掘应用至关重要。但是，用于生物医学的大多数现有基准测试数据集仅关注句子级别的单一类型（例如蛋白质 - 蛋白质相互作用）的关系，从而极大地限制了生物医学中RE系统的开发。在这项工作中，我们首先审查了常用的名称实体识别（NER）和RE数据集。然后，我们提出了Biored，这是一种具有多种实体类型（例如，基因/蛋白质，疾病，化学）和关系对（例如，基因 - 疾病；化学化学化学化学）的首个生物医学RE语料库，在文档水平上，在一组600个PubMed摘要中。此外，我们将每个关系标记为描述一种新颖的发现或先前已知的背景知识，使自动化算法能够区分新颖和背景信息。我们通过基准在NER和RE任务上对几种现有的最新方法（包括基于BERT的模型）进行基准测试来评估Biored的实用性。我们的结果表明，尽管现有方法可以在NER任务上达到高性能（F-评分为89.3％），但重新任务的改进空间很大，尤其是在提取新颖的关系时（F-评分为47.7％）。我们的实验还表明，如此丰富的数据集可以成功地促进生物医学更准确，高效和健壮的RE系统的开发。 Biored数据集和注释指南可在https://ftp.ncbi.nlm.nih.gov/pub/lu/biored/中免费获得。

在现实世界中，在雾度下拍摄的图像的降解可以是非常复杂的，其中雾度的空间分布从图像变化到图像。最近的方法采用深神经网络直接从朦胧图像中恢复清洁场景。然而，由于悖论由真正捕获的雾霾的变化和当前网络的固定退化参数引起的悖论，最近在真实朦胧的图像上的脱水方法的泛化能力不是理想的。解决现实世界建模问题阴霾退化，我们建议通过对不均匀雾度分布的鉴定和建模密度来解决这个问题。我们提出了一种新颖的可分离混合注意力（SHA）模块来编码雾霾密度，通过捕获正交方向上的特征来实现这一目标。此外，提出了密度图以明确地模拟雾度的不均匀分布。密度图以半监督方式生成位置编码。这种雾度密度感知和建模有效地捕获特征水平的不均匀分布性变性。通过SHA和密度图的合适组合，我们设计了一种新型的脱水网络架构，实现了良好的复杂性性能权衡。两个大规模数据集的广泛实验表明，我们的方法通过量化和定性地通过大幅度超越所有最先进的方法，将最佳发布的PSNR度量从28.53 DB升高到Haze4K测试数据集和在SOTS室内测试数据集中的37.17 dB至38.41 dB。

T2磁共振成像（MRI）中淋巴结（LN）的鉴定是放射科在评估淋巴抑制性疾病期间的重要步骤。节点的大小在其分期中发挥着至关重要的作用，并且放射科有时有时使用额外的对比度序列，例如扩散加权成像（DWI）进行确认。然而，淋巴结在T2 MRI扫描中具有多样化的外观，使得转移的阶段难以实现。此外，放射科医师通常会在繁忙的一天中错过较小的转移性淋巴结。要处理这些问题，我们建议使用检测变压器（DETR）网络本地化可疑转移性淋巴结，用于挑战不同扫描仪和考试协议获得的T2 MRI扫描。通过边界盒融合技术降低了误报（FP），并且达到了每张图像4 FP的65.41 \％的精确度和91.66 \％。据我们所知，我们的结果改善了T2 MRI扫描中的目前的淋巴结检测最先进的淋巴结检测。

Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information. In this paper, taking advantage of both classical architecture in the conventional video compression method and the powerful nonlinear representation ability of neural networks, we propose the first end-to-end video compression deep model that jointly optimizes all the components for video compression. Specifically, learning based optical flow estimation is utilized to obtain the motion information and reconstruct the current frames. Then we employ two auto-encoder style neural networks to compress the corresponding motion and residual information. All the modules are jointly learned through a single loss function, in which they collaborate with each other by considering the trade-off between reducing the number of compression bits and improving quality of the decoded video. Experimental results show that the proposed approach can outperform the widely used video coding standard H.264 in terms of PSNR and be even on par with the latest standard H.265 in terms of MS-SSIM. Code is released at https://github.com/GuoLusjtu/DVC. * Corresponding author (a) Original frame (Bpp/MS-SSIM) (b) H.264 (0.0540Bpp/0.945) (c) H.265 (0.082Bpp/0.960) (d) Ours ( 0.0529Bpp/ 0.961

The chest X-ray is one of the most commonly accessible radiological examinations for screening and diagnosis of many lung diseases. A tremendous number of X-ray imaging studies accompanied by radiological reports are accumulated and stored in many modern hospitals' Picture Archiving and Communication Systems (PACS). On the other side, it is still an open question how this type of hospital-size knowledge database containing invaluable imaging informatics (i.e., loosely labeled) can be used to facilitate the data-hungry deep learning paradigms in building truly large-scale high precision computer-aided diagnosis (CAD) systems.In this paper, we present a new chest X-ray database, namely "ChestX-ray8", which comprises 108,948 frontalview X-ray images of 32,717 unique patients with the textmined eight disease image labels (where each image can have multi-labels), from the associated radiological reports using natural language processing. Importantly, we demonstrate that these commonly occurring thoracic diseases can be detected and even spatially-located via a unified weaklysupervised multi-label image classification and disease localization framework, which is validated using our proposed dataset. Although the initial quantitative results are promising as reported, deep convolutional neural network based "reading chest X-rays" (i.e., recognizing and locating the common disease patterns trained with only image-level labels) remains a strenuous task for fully-automated high precision CAD systems.