药物误解是可能导致对患者造成不可预测后果的风险之一。为了减轻这种风险，我们开发了一个自动系统，该系统可以正确识别移动图像中的药丸的处方。具体来说，我们定义了所谓的药丸匹配任务，该任务试图匹配处方药中药丸所拍摄的药丸的图像。然后，我们提出了PIMA，这是一种使用图神经网络（GNN）和对比度学习来解决目标问题的新方法。特别是，GNN用于学习处方中文本框之间的空间相关性，从而突出显示带有药丸名称的文本框。此外，采用对比度学习来促进药丸名称的文本表示与药丸图像的视觉表示之间的跨模式相似性的建模。我们进行了广泛的实验，并证明PIMA在我们构建的药丸和处方图像的现实数据集上优于基线模型。具体而言，与其他基线相比，PIMA的准确性从19.09％提高到46.95％。我们认为，我们的工作可以为建立新的临床应用并改善药物安全和患者护理提供新的机会。

尽管在自动语音识别（ASR）中最近的表现方法增加了，但这种方法并不能确保其输出的适当套管和标点符号。这个问题对自然语言处理（NLP）算法和人类的理解都有重大影响。对于原始文本输入的预处理管道，必须进行资本化和标点符号恢复。对于越南人等低资源语言，此任务的公共数据集很少。在本文中，我们为越南人的资本化和标点符号恢复贡献了一个公共数据集；并提出了两个名为intercappunc的任务的联合模型。越南数据集的实验结果显示了我们联合模型的有效性与单个模型和先前的联合学习模型相比。我们在https://github.com/anhtunguyen98/jointcappund上公开发布数据集和模型的实现

在医疗应用中，建立深度学习方法以自动化诊断任务。然而，从业者通常面临的临床相关问题是如何预测疾病的未来轨迹（预后）。此类问题的当前方法通常需要域知识，并申请复杂。在本文中，我们将预后预测问题标准为来自多式联数据的一对多预测问题。灵感来自临床决策过程，其中两个代理商 - 放射科医生和一般从业者，我们模拟了一种与两个基于变压器的组件进行预后预测问题，该组件在彼此之间共享信息。该模型中的第一个块旨在分析成像数据，第二块利用第一个作为输入的内部表示，也使它们与辅助患者数据一起融合。我们展示了我们预测结构膝关节骨关节炎的发展的方法的有效性随着时间的推移。我们的研究结果表明，该方法在各种绩效指标方面优于最先进的基线。此外，我们经验证明，具有深度为2的多蛋白变压器的存在足以实现良好的性能。我们的代码公开可用于\ url {https:/github.com/mipt-ouru/climat}。

In this work, we propose a new approach that combines data from multiple sensors for reliable obstacle avoidance. The sensors include two depth cameras and a LiDAR arranged so that they can capture the whole 3D area in front of the robot and a 2D slide around it. To fuse the data from these sensors, we first use an external camera as a reference to combine data from two depth cameras. A projection technique is then introduced to convert the 3D point cloud data of the cameras to its 2D correspondence. An obstacle avoidance algorithm is then developed based on the dynamic window approach. A number of experiments have been conducted to evaluate our proposed approach. The results show that the robot can effectively avoid static and dynamic obstacles of different shapes and sizes in different environments.

We introduce an approach for the answer-aware question generation problem. Instead of only relying on the capability of strong pre-trained language models, we observe that the information of answers and questions can be found in some relevant sentences in the context. Based on that, we design a model which includes two modules: a selector and a generator. The selector forces the model to more focus on relevant sentences regarding an answer to provide implicit local information. The generator generates questions by implicitly combining local information from the selector and global information from the whole context encoded by the encoder. The model is trained jointly to take advantage of latent interactions between the two modules. Experimental results on two benchmark datasets show that our model is better than strong pre-trained models for the question generation task. The code is also available (shorturl.at/lV567).

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.

Collecting large-scale medical datasets with fully annotated samples for training of deep networks is prohibitively expensive, especially for 3D volume data. Recent breakthroughs in self-supervised learning (SSL) offer the ability to overcome the lack of labeled training samples by learning feature representations from unlabeled data. However, most current SSL techniques in the medical field have been designed for either 2D images or 3D volumes. In practice, this restricts the capability to fully leverage unlabeled data from numerous sources, which may include both 2D and 3D data. Additionally, the use of these pre-trained networks is constrained to downstream tasks with compatible data dimensions. In this paper, we propose a novel framework for unsupervised joint learning on 2D and 3D data modalities. Given a set of 2D images or 2D slices extracted from 3D volumes, we construct an SSL task based on a 2D contrastive clustering problem for distinct classes. The 3D volumes are exploited by computing vectored embedding at each slice and then assembling a holistic feature through deformable self-attention mechanisms in Transformer, allowing incorporating long-range dependencies between slices inside 3D volumes. These holistic features are further utilized to define a novel 3D clustering agreement-based SSL task and masking embedding prediction inspired by pre-trained language models. Experiments on downstream tasks, such as 3D brain segmentation, lung nodule detection, 3D heart structures segmentation, and abnormal chest X-ray detection, demonstrate the effectiveness of our joint 2D and 3D SSL approach. We improve plain 2D Deep-ClusterV2 and SwAV by a significant margin and also surpass various modern 2D and 3D SSL approaches.

在现实世界应用中，联合学习（FL）遇到了两个挑战：（1）可伸缩性，尤其是应用于大型物联网网络时； （2）如何使用异质数据对环境进行健全。意识到第一个问题，我们旨在设计一个名为Full-Stack FL（F2L）的新型FL框架。更具体地说，F2L使用层次结构架构，使扩展FL网络可以访问而无需重建整个网络系统。此外，利用层次网络设计的优势，我们在全球服务器上提出了一种新的标签驱动知识蒸馏（LKD）技术来解决第二个问题。与当前的知识蒸馏技术相反，LKD能够训练学生模型，该模型由所有教师模型的良好知识组成。因此，我们提出的算法可以有效地提取区域数据分布（即区域汇总模型）的知识，以减少客户在使用非独立分布数据的FL系统下操作时客户模型之间的差异。广泛的实验结果表明：（i）我们的F2L方法可以显着提高所有全球蒸馏的总体FL效率，并且（ii）F2L随着全球蒸馏阶段的发生而迅速达到收敛性，而不是在每个通信周期中提高。

切成薄片的Wasserstein（SW）距离已在不同的应用程序场景中广泛使用，因为它可以缩放到大量的支撑量，而不会受到维数的诅咒。切成薄片的瓦斯坦距离的值是通过radon变换（RT）获得的原始度量的一维表示（投影）之间运输成本的平均值。尽管估计切成薄片的瓦斯坦族的支持效率，但仍需要在高维环境中进行相对较大的预测。因此，对于与维度相比，支撑次数相对较少的应用，例如，使用微型批量方法的几个深度学习应用，radon transform的矩阵乘法中的复杂性成为主要计算瓶颈。为了解决这个问题，我们建议通过线性和随机组合少量的预测来得出预测，这些预测被称为瓶颈预测。我们通过引入层次ra transform（HRT）来解释这些投影的用法，该层rad rad transform（HRT）是通过递归应用radon变换变体构建的。然后，我们将方法制定为措施之间的新指标，该指标命名为分层切片瓦斯坦（HSW）距离。通过证明HRT的注入性，我们得出了HSW的指标。此外，我们研究了HSW的理论特性，包括其与SW变体的联系及其计算和样品复杂性。最后，我们将HSW的计算成本和生成质量与常规SW进行比较，使用包括CIFAR10，Celeba和Tiny Imagenet在内的各种基准数据集进行深层生成建模的任务。

最近，提出了经典多军强盗的多代理变体来解决在线学习中的公平问题。受社会选择和经济学方面的长期工作的启发，目标是优化NASH的社会福利，而不是全面的效用。不幸的是，就回合$ t $的数量而言，以前的算法要么不是有效的，要么实现次级遗憾。我们提出了一种新的有效算法，其遗憾也比以前效率低下的算法要低。对于$ n $ agents，$ k $ ands和$ t $ rounds，我们的方法遗憾的是$ \ tilde {o}（\ sqrt {nkt} + nk）$。这是对先前方法的改进，后者对$ \ tilde {o}（\ min（nk，\ sqrt {n} k^{3/2}）\ sqrt {t}）$的遗憾。我们还使用$ \ tilde {o}（\ sqrt {kt} + n^2k）$遗憾的方法来补充有效算法。实验发现证实了与先前方法相比，我们有效算法的有效性。