Generalizability to unseen forgery types is crucial for face forgery detectors. Recent works have made significant progress in terms of generalization by synthetic forgery data augmentation. In this work, we explore another path for improving the generalization. Our goal is to reduce the features that are easy to learn in the training phase, so as to reduce the risk of overfitting on specific forgery types. Specifically, in our method, a teacher network takes as input the face images and generates an attention map of the deep features by a diverse multihead attention ViT. The attention map is used to guide a student network to focus on the low-attended features by reducing the highly-attended deep features. A deep feature mixup strategy is also proposed to synthesize forgeries in the feature domain. Experiments demonstrate that, without data augmentation, our method is able to achieve promising performances on unseen forgeries and highly compressed data.

In this work, we investigate improving the generalizability of GAN-generated image detectors by performing data augmentation in the fingerprint domain. Specifically, we first separate the fingerprints and contents of the GAN-generated images using an autoencoder based GAN fingerprint extractor, followed by random perturbations of the fingerprints. Then the original fingerprints are substituted with the perturbed fingerprints and added to the original contents, to produce images that are visually invariant but with distinct fingerprints. The perturbed images can successfully imitate images generated by different GANs to improve the generalization of the detectors, which is demonstrated by the spectra visualization. To our knowledge, we are the first to conduct data augmentation in the fingerprint domain. Our work explores a novel prospect that is distinct from previous works on spatial and frequency domain augmentation. Extensive cross-GAN experiments demonstrate the effectiveness of our method compared to the state-of-the-art methods in detecting fake images generated by unknown GANs.

音频文本检索需要自然语言查询以在数据库中检索相关的音频文件。相反，文本审计检索将音频文件作为查询来检索相关的自然语言描述。大多数带有一个音频字幕数据集的文献训练检索系统，但是评估多个数据集培训的好处是没有充满反感的。此外，检索系统必须学习描述从几秒钟到几秒钟的可变长度的音频内容之间的详细句子之间的对齐。在这项工作中，我们提出了一个新的Web音频文本对以及一个新的检索框架。首先，我们提供了大约五千个Web音频纹理对的新集合，我们称为WavText5k。当用来训练我们的检索系统时，WavText5K比其他音频字幕更多地提高了性能。其次，我们的框架学会了使用文本编码器，两个音频编码器和对比度学习目标来连接语言和音频内容。组合两个音频编码器有助于处理可变长度音频。这两个贡献超过了AudioCaps和Clote的Text-Audio检索的最新表现，相对2％和16％，而音频检索则达到6％和23％。

引号提取旨在从书面文本中提取引号。引号中有三个组成部分：来源是指引号的持有人，提示是触发词，内容是主体。引号提取的现有解决方案主要利用基于规则的方法和序列标签模型。尽管基于规则的方法通常会导致召回率低，但序列标记模型不能很好地处理带有复杂结构的报价。在本文中，我们提出了上下文和以前的标签增强净（Cofenet），以提取引号。Cofenet能够提取具有可变长度和复杂结构的组成部分的复杂报价。在两个公共数据集（即polnear和Riqua）和一个专有数据集（即Politicszh）上，我们表明我们的Cofenet在复杂的引号提取方面取得了最先进的表现。

Enterprise financial risk analysis aims at predicting the enterprises' future financial risk.Due to the wide application, enterprise financial risk analysis has always been a core research issue in finance. Although there are already some valuable and impressive surveys on risk management, these surveys introduce approaches in a relatively isolated way and lack the recent advances in enterprise financial risk analysis. Due to the rapid expansion of the enterprise financial risk analysis, especially from the computer science and big data perspective, it is both necessary and challenging to comprehensively review the relevant studies. This survey attempts to connect and systematize the existing enterprise financial risk researches, as well as to summarize and interpret the mechanisms and the strategies of enterprise financial risk analysis in a comprehensive way, which may help readers have a better understanding of the current research status and ideas. This paper provides a systematic literature review of over 300 articles published on enterprise risk analysis modelling over a 50-year period, 1968 to 2022. We first introduce the formal definition of enterprise risk as well as the related concepts. Then, we categorized the representative works in terms of risk type and summarized the three aspects of risk analysis. Finally, we compared the analysis methods used to model the enterprise financial risk. Our goal is to clarify current cutting-edge research and its possible future directions to model enterprise risk, aiming to fully understand the mechanisms of enterprise risk communication and influence and its application on corporate governance, financial institution and government regulation.

大多数现有的半监督基于图的聚类方法通过完善亲和力矩阵或直接限制数据点的低维表示来利用监督信息。亲和力矩阵代表图形结构，对于半监督基于图的聚类的性能至关重要。但是，现有方法采用静态亲和力矩阵来学习数据点的低维表示，并且在学习过程中不会优化亲和力矩阵。在本文中，我们提出了一种新型的动态图结构学习方法，用于半监督聚类。在这种方法中，我们通过利用给定的成对约束来同时优化数据点的亲和力矩阵和低维表示。此外，我们提出了一种交替的最小化方法，并通过可靠的收敛来解决提出的非凸模型。在迭代过程中，我们的方法周期性地更新数据点的低维表示并完善了亲和力矩阵，从而导致动态亲和力矩阵（图结构）。具体而言，为了更新亲和力矩阵，我们强制使用具有明显不同的低维表示的数据点具有相关值为0。点。在不同设置下的八个基准数据集上的实验结果显示了所提出方法的优势。

股票运动预测（SMP）旨在预测上市公司的股份量股份，由于金融市场的挥发性，这是一个具有挑战性的任务。最近的财务研究表明，动量溢出效应在股票波动中发挥着重要作用。然而，以前的研究通常只学习相关公司之间的简单连接信息，这不可避免地未能模仿真实金融市场中上市公司的复杂关系。为了解决这个问题，我们首先建立一个更全面的市场知识图（MKG），其中包含有限的公司，包括上市公司及其相关的高管，以及包括明确关系和隐性关系的混合关系。之后，我们提出了一种新颖的双重关注网络，以了解基于构造的MKG用于库存预测的势头溢出信号。对九个SOTA基线构建数据集的实证实验表明，所提出的丹林公司能够改善与构造的MKG的库存预测。

双类型的异构图形应用于许多真实情景。然而，以前的异构图形学习研究通常忽略这种异构图中的双键入实体之间的复杂相互作用。为了解决这个问题，在本文中，我们提出了一种新的双重分层关注网络（DHAN），以了解与类内和级别的分层关注网络的双键入异构图中的综合节点表示。具体地，课堂上的注意力旨在从相同类型的邻居中学习节点表示，而级别的关注能够从其不同类型的邻居聚合节点表示。因此，双重关注操作使DHAN不仅能够充分地利用节点帧内邻近信息，而且可以在双键入的异构图中提供帧间相邻信息。关于针对最先进的各种任务的实验结果充分证实了DHAN在学习节点的学习节点综合陈述的能力

In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed implicitly, by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. CMT obtains 73.0% NDS on nuScenes benchmark. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code will be released at https://github.com/junjie18/CMT.

Knowledge graphs (KG) have served as the key component of various natural language processing applications. Commonsense knowledge graphs (CKG) are a special type of KG, where entities and relations are composed of free-form text. However, previous works in KG completion and CKG completion suffer from long-tail relations and newly-added relations which do not have many know triples for training. In light of this, few-shot KG completion (FKGC), which requires the strengths of graph representation learning and few-shot learning, has been proposed to challenge the problem of limited annotated data. In this paper, we comprehensively survey previous attempts on such tasks in the form of a series of methods and applications. Specifically, we first introduce FKGC challenges, commonly used KGs, and CKGs. Then we systematically categorize and summarize existing works in terms of the type of KGs and the methods. Finally, we present applications of FKGC models on prediction tasks in different areas and share our thoughts on future research directions of FKGC.