对于弱监督的异常检测，由于无法对长期上下文信息进行建模，大多数现有工作仅限于视频表示不足的问题。为了解决这个问题，我们提出了一个新型弱监督的自适应图卷积网络（WAGCN），以模拟视频片段之间复杂的上下文关系。通过此，我们完全考虑了其他视频片段对当前段的影响，在为每个段的异常概率分数生成当前段。首先，我们结合了视频片段的时间一致性以及功能相似性来构建全局图，该图可以充分利用视频中异常事件的时空特征之间的关联信息。其次，我们提出了一个图形学习层，以打破手动设置拓扑的限制，该拓扑可以根据数据自适应地提取图形邻接矩阵。在两个公共数据集（即UCF-Crime数据集和Shanghaitech数据集）上进行了广泛的实验，证明了我们的方法的有效性，从而实现了最先进的性能。

Weakly supervised video anomaly detection (WSVAD) is a challenging task since only video-level labels are available for training. In previous studies, the discriminative power of the learned features is not strong enough, and the data imbalance resulting from the mini-batch training strategy is ignored. To address these two issues, we propose a novel WSVAD method based on cross-batch clustering guidance. To enhance the discriminative power of features, we propose a batch clustering based loss to encourage a clustering branch to generate distinct normal and abnormal clusters based on a batch of data. Meanwhile, we design a cross-batch learning strategy by introducing clustering results from previous mini-batches to reduce the impact of data imbalance. In addition, we propose to generate more accurate segment-level anomaly scores based on batch clustering guidance further improving the performance of WSVAD. Extensive experiments on two public datasets demonstrate the effectiveness of our approach.

我们提出了一种轻巧，准确的方法，用于检测视频中的异常情况。现有方法使用多个实体学习（MIL）来确定视频每个段的正常/异常状态。最近的成功研​​究认为，学习细分市场之间的时间关系很重要，以达到高精度，而不是只关注单个细分市场。因此，我们分析了近年来成功的现有方法，并发现同时学习所有细分市场确实很重要，但其中的时间顺序与实现高准确性无关。基于这一发现，我们不使用MIL框架，而是提出具有自发机制的轻质模型，以自动提取对于确定所有输入段正常/异常非常重要的特征。结果，我们的神经网络模型具有现有方法的参数数量的1.3％。我们在三个基准数据集（UCF-Crime，Shanghaitech和XD-Violence）上评估了方法的帧级检测准确性，并证明我们的方法可以比最新方法实现可比或更好的准确性。

视频异常检测最近在弱监督下作为多个实例学习任务制定，其中每个视频都被视为要确定是否包含异常的片段。先前的努力主要集中于摘要本身的歧视，而无需对时间动力进行建模，这是指相邻摘要的变化。因此，我们提出了一种具有两个目标函数的歧视动力学学习（DDL）方法，即动态排名损耗和动态对齐损失。前者的目标是扩大正面和负袋之间的分数动态差距，而后者则在袋中进行特征动力学和得分动力学的时间对齐。此外，构建了一个局部意识的注意网络（LA-NET），以捕获全局相关性并重新校准跨段的位置偏好，然后是带有因果卷积的多层感知器以获得异常得分。实验结果表明，我们的方法在两个具有挑战性的基准（即UCF-Crime和XD-Violence）上取得了重大改进。

Weakly supervised detection of anomalies in surveillance videos is a challenging task. Going beyond existing works that have deficient capabilities to localize anomalies in long videos, we propose a novel glance and focus network to effectively integrate spatial-temporal information for accurate anomaly detection. In addition, we empirically found that existing approaches that use feature magnitudes to represent the degree of anomalies typically ignore the effects of scene variations, and hence result in sub-optimal performance due to the inconsistency of feature magnitudes across scenes. To address this issue, we propose the Feature Amplification Mechanism and a Magnitude Contrastive Loss to enhance the discriminativeness of feature magnitudes for detecting anomalies. Experimental results on two large-scale benchmarks UCF-Crime and XD-Violence manifest that our method outperforms state-of-the-art approaches.

Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseudo labels and self-refining anomaly scores with these labels. As the pseudo labels play a crucial role, we propose an enhancement framework by exploiting completeness and uncertainty properties for effective self-training. Specifically, we first design a multi-head classification module (each head serves as a classifier) with a diversity loss to maximize the distribution differences of predicted pseudo labels across heads. This encourages the generated pseudo labels to cover as many abnormal events as possible. We then devise an iterative uncertainty pseudo label refinement strategy, which improves not only the initial pseudo labels but also the updated ones obtained by the desired classifier in the second stage. Extensive experimental results demonstrate the proposed method performs favorably against state-of-the-art approaches on the UCF-Crime, TAD, and XD-Violence benchmark datasets.

Surveillance videos are able to capture a variety of realistic anomalies. In this paper, we propose to learn anomalies by exploiting both normal and anomalous videos. To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i.e. the training labels (anomalous or normal) are at videolevel instead of clip-level. In our approach, we consider normal and anomalous videos as bags and video segments as instances in multiple instance learning (MIL), and automatically learn a deep anomaly ranking model that predicts high anomaly scores for anomalous video segments. Furthermore, we introduce sparsity and temporal smoothness constraints in the ranking loss function to better localize anomaly during training.We also introduce a new large-scale first of its kind dataset of 128 hours of videos. It consists of 1900 long and untrimmed real-world surveillance videos, with 13 realistic anomalies such as fighting, road accident, burglary, robbery, etc. as well as normal activities. This dataset can be used for two tasks. First, general anomaly detection considering all anomalies in one group and all normal activities in another group. Second, for recognizing each of 13 anomalous activities. Our experimental results show that our MIL method for anomaly detection achieves significant improvement on anomaly detection performance as compared to the state-of-the-art approaches. We provide the results of several recent deep learning baselines on anomalous activity recognition. The low recognition performance of these baselines reveals that our dataset is very challenging and opens more opportunities for future work. The dataset is

开放式视频异常检测（OpenVAD）旨在从视频数据中识别出异常事件，在测试中都存在已知的异常和新颖的事件。无监督的模型仅从普通视频中学到的模型适用于任何测试异常，但遭受高误报率的损失。相比之下，弱监督的方法可有效检测已知的异常情况，但在开放世界中可能会失败。我们通过将证据深度学习（EDL）和将流量（NFS）归一化为多个实例学习（MIL）框架来开发出一种新颖的OpenVAD问题的弱监督方法。具体而言，我们建议使用图形神经网络和三重态损失来学习训练EDL分类器的区分特征，在该特征中，EDL能够通过量化不确定性来识别未知异常。此外，我们制定了一种不确定性感知的选择策略，以获取清洁异常实例和NFS模块以生成伪异常。我们的方法通过继承无监督的NF和弱监督的MIL框架的优势来优于现有方法。多个现实世界视频数据集的实验结果显示了我们方法的有效性。

Video anomaly detection (VAD) -- commonly formulated as a multiple-instance learning problem in a weakly-supervised manner due to its labor-intensive nature -- is a challenging problem in video surveillance where the frames of anomaly need to be localized in an untrimmed video. In this paper, we first propose to utilize the ViT-encoded visual features from CLIP, in contrast with the conventional C3D or I3D features in the domain, to efficiently extract discriminative representations in the novel technique. We then model long- and short-range temporal dependencies and nominate the snippets of interest by leveraging our proposed Temporal Self-Attention (TSA). The ablation study conducted on each component confirms its effectiveness in the problem, and the extensive experiments show that our proposed CLIP-TSA outperforms the existing state-of-the-art (SOTA) methods by a large margin on two commonly-used benchmark datasets in the VAD problem (UCF-Crime and ShanghaiTech Campus). The source code will be made publicly available upon acceptance.

视频中的战斗检测是当今监视系统和流媒体的流行率的新兴深度学习应用程序。以前的工作主要依靠行动识别技术来解决这个问题。在本文中，我们提出了一种简单但有效的方法，该方法从新的角度解决了任务：我们将战斗检测模型设计为动作感知功能提取器和异常得分生成器的组成。另外，考虑到视频收集帧级标签太费力了，我们设计了一个弱监督的两阶段训练计划，在此我们使用在视频级别标签上计算出的多个实体学习损失来培训得分生成器，并采用自我训练的技术以进一步提高其性能。在公开可用的大规模数据集（UBI-Fights）上进行了广泛的实验，证明了我们方法的有效性，并且数据集的性能超过了几种先前的最先进的方法。此外，我们收集了一个新的数据集VFD-2000，该数据集专门研究视频战斗检测，比现有数据集更大，场景更大。我们的方法的实现和拟议的数据集将在https://github.com/hepta-col/videofightdetection上公开获得。

Detecting abnormal crowd motion emerging from complex interactions of individuals is paramount to ensure the safety of crowds. Crowd-level abnormal behaviors (CABs), e.g., counter flow and crowd turbulence, are proven to be the crucial causes of many crowd disasters. In the recent decade, video anomaly detection (VAD) techniques have achieved remarkable success in detecting individual-level abnormal behaviors (e.g., sudden running, fighting and stealing), but research on VAD for CABs is rather limited. Unlike individual-level anomaly, CABs usually do not exhibit salient difference from the normal behaviors when observed locally, and the scale of CABs could vary from one scenario to another. In this paper, we present a systematic study to tackle the important problem of VAD for CABs with a novel crowd motion learning framework, multi-scale motion consistency network (MSMC-Net). MSMC-Net first captures the spatial and temporal crowd motion consistency information in a graph representation. Then, it simultaneously trains multiple feature graphs constructed at different scales to capture rich crowd patterns. An attention network is used to adaptively fuse the multi-scale features for better CAB detection. For the empirical study, we consider three large-scale crowd event datasets, UMN, Hajj and Love Parade. Experimental results show that MSMC-Net could substantially improve the state-of-the-art performance on all the datasets.

弱监督的时间动作本地化（WSTAL）旨在仅使用视频级别标签将动作定位在未修剪的视频中。当前，大多数最先进的WSTAL方法遵循多实施学习（MIL）管道：首先产生摘要级预测，然后汇总到视频级别的预测。但是，我们认为现有的方法忽略了两个重要的缺点：1）使用运动信息不足和2）盛行的跨凝结训练损失的不相容性。在本文中，我们分析了光流功能背后的运动提示是互补的信息。受到这一点的启发，我们建议建立一个与上下文有关的运动，称为运动性。具体而言，将运动图引入基于局部运动载体（例如光流）的模型运动性。此外，为了突出显示更多信息的视频片段，提出了运动引导的损失，以调节运动性得分条件的网络训练。广泛的消融研究证实，运动性有效地模拟了利益的作用，运动引导的损失会导致更准确的结果。此外，我们的运动引导损失是插件损失功能，适用于现有的WSTAL方法。基于标准的MIL管道，我们的方法在不丧失的情况下，我们的方法在三个具有挑战性的基准上实现了新的最新性能，包括Thumos'14，ActivityNet v1.2和v1.3。

未经监控视频中的弱监督时间行动本地化（WTAL）已成为实际但具有挑战性的任务，因为只有视频级标签。现有方法通常利用现成的分段级别特征，这些特征患有空间不完整性和时间不一致，从而限制了它们的性能。在本文中，我们通过使用简单但有效的图表卷积网络增强段级表示，即动作补充图网络（ACGNET）来从新的角度来解决这个问题。它促进了当前的视频段来从其他潜在传达互补线索的其他人感知空间时间依赖性，隐含地减轻由上述两个问题引起的负面影响。通过这种方式，分段级别特征是对空间时间变化的更具判别和鲁棒性的，有助于较高的定位精度。更重要的是，所提出的ACGNET作为通用模块，可以灵活插入不同的WTAL框架，同时保持端到端的培训方式。在Thumos'14和ActivityNET1.2基准上进行了广泛的实验，其中最先进的结果清楚地证明了所提出的方法的优越性。

视频异常检测旨在识别视频中发生的异常事件。由于异常事件相对较少，收集平衡数据集并培训二进制分类器以解决任务是不可行的。因此，最先前的方法只使用无监督或半监督方法从正常视频中学到。显然，它们是有限的捕获和利用鉴别异常特征，这导致受损的异常检测性能。在本文中，为了解决这个问题，我们通过充分利用用于视频异常检测的正常和异常视频来提出新的学习范式。特别是，我们制定了一个新的学习任务：跨域几次射击异常检测，可以从源域中的众多视频中学习知识，以帮助解决目标域中的几次异常检测。具体而言，我们利用目标普通视频的自我监督培训来减少域间隙，并设计一个Meta Context Cenception模块，以探索几次拍摄设置中的事件的视频上下文。我们的实验表明，我们的方法显着优于DotA和UCF犯罪数据集的基线方法，新任务有助于更实用的异常检测范例。

Aiming at the problem that the current video anomaly detection cannot fully use the temporal information and ignore the diversity of normal behavior, an anomaly detection method is proposed to integrate the spatiotemporal information of pedestrians. Based on the convolutional autoencoder, the input frame is compressed and restored through the encoder and decoder. Anomaly detection is realized according to the difference between the output frame and the true value. In order to strengthen the characteristic information connection between continuous video frames, the residual temporal shift module and the residual channel attention module are introduced to improve the modeling ability of the network on temporal information and channel information, respectively. Due to the excessive generalization of convolutional neural networks, in the memory enhancement modules, the hopping connections of each codec layer are added to limit autoencoders' ability to represent abnormal frames too vigorously and improve the anomaly detection accuracy of the network. In addition, the objective function is modified by a feature discretization loss, which effectively distinguishes different normal behavior patterns. The experimental results on the CUHK Avenue and ShanghaiTech datasets show that the proposed method is superior to the current mainstream video anomaly detection methods while meeting the real-time requirements.

Most action recognition datasets and algorithms assume a closed world, where all test samples are instances of the known classes. In open set problems, test samples may be drawn from either known or unknown classes. Existing open set action recognition methods are typically based on extending closed set methods by adding post hoc analysis of classification scores or feature distances and do not capture the relations among all the video clip elements. Our approach uses the reconstruction error to determine the novelty of the video since unknown classes are harder to put back together and thus have a higher reconstruction error than videos from known classes. We refer to our solution to the open set action recognition problem as "Humpty Dumpty", due to its reconstruction abilities. Humpty Dumpty is a novel graph-based autoencoder that accounts for contextual and semantic relations among the clip pieces for improved reconstruction. A larger reconstruction error leads to an increased likelihood that the action can not be reconstructed, i.e., can not put Humpty Dumpty back together again, indicating that the action has never been seen before and is novel/unknown. Extensive experiments are performed on two publicly available action recognition datasets including HMDB-51 and UCF-101, showing the state-of-the-art performance for open set action recognition.

异常识别高度取决于对象与场景之间的关系，因为相同/不同场景中的不同/相同对象动作可能导致各种程度的正态性和异常。因此，对象场景关系实际上在异常检测中起着至关重要的作用，但在以前的工作中探讨了不足。在本文中，我们提出了一个时空关系学习（STRL）框架来解决视频异常检测任务。首先，考虑到对象的动态特征以及场景区域，我们构建了一个时空自动编码器（STAE），以共同利用代表学习的空间和时间演化模式。为了获得更好的图案提取，在STAE模块中设计了两个解码分支，即通过直接预测下一个帧来捕获空间提示的外观分支，以及一个运动分支，重点是通过光流预测对动态进行建模。然后，为了很好地融合对象场所关系，设计了一个关系学习（RL）模块来通过引入知识图嵌入方法来分析和总结正常关系。在此过程中具体来说，通过共同建模对象/场景特征和优化的对象场所关系图来衡量对象场景关系的合理性。在三个公共数据集上进行了广泛的实验，而对最新方法的优越性能证明了我们方法的有效性。

深度学习模型已广泛用于监控视频中的异常检测。典型模型配备了重建普通视频的能力，并评估异常视频的重建错误以指示异常的程度。然而，现有方法遭受了两个缺点。首先，它们只能独立地编码每个身份的运动，而不考虑身份之间的相互作用，这也可以指示异常。其次，他们利用了结构在不同场景下固定的粘合模型，这种配置禁止了对场景的理解。在本文中，我们提出了一个分层时空图卷积神经网络（HSTGCNN）来解决这些问题，HSTGCNN由对应于不同级别的图形表示的多个分支组成。高级图形表示编码人们的轨迹以及多个身份之间的交互，而低级图表表示编码每个人的本地身体姿势。此外，我们建议加权组合在不同场景中更好的多个分支。以这种方式实现了对单级图形表示的改进。实现了对场景的理解并提供异常检测。在低分辨率视频中为在低分辨率视频中编码低分辨率视频中的人员的移动速度和方向编码高级别的图表表示，而在高分辨率视频中将更高的权重分配更高的权重。实验结果表明，建议的HSTGCNN在四个基准数据集（UCSD Spistrian，Shanghaitech，Cuhk Aveance和IITB-Whent）上的当前最先进的模型显着优于最新的最先进模型。

在计算机视觉中长期以来一直研究了时间行动定位。现有的最先进的动作定位方法将每个视频划分为多个动作单位（即，在一级方法中的两级方法和段中的提案），然后单独地对每个视频进行操作，而不明确利用他们在学习期间的关系。在本文中，我们声称，动作单位之间的关系在行动定位中发挥着重要作用，并且更强大的动作探测器不仅应捕获每个动作单元的本地内容，还应允许更广泛的视野与相关的上下文它。为此，我们提出了一般图表卷积模块（GCM），可以轻松插入现有的动作本地化方法，包括两阶段和单级范式。具体而言，我们首先构造一个图形，其中每个动作单元被表示为节点，并且两个动作单元之间作为边缘之间的关系。在这里，我们使用两种类型的关系，一个类型的关系，用于捕获不同动作单位之间的时间连接，另一类是用于表征其语义关系的另一个关系。特别是对于两级方法中的时间连接，我们进一步探索了两种不同的边缘，一个连接重叠动作单元和连接周围但脱节的单元的另一个。在我们构建的图表上，我们将图形卷积网络（GCNS）应用于模拟不同动作单位之间的关系，这能够了解更有信息的表示来增强动作本地化。实验结果表明，我们的GCM始终如一地提高了现有行动定位方法的性能，包括两阶段方法（例如，CBR和R-C3D）和一级方法（例如，D-SSAD），验证我们的一般性和有效性GCM。

动作检测是一项必不可少且具有挑战性的任务，尤其是对于未修剪视频的密集标记的数据集。这些数据集中有许多现实世界中的挑战，例如复合动作，共存在的动作和实例持续时间的高时间变化。为了应对这些挑战，我们建议探索被检测行动的阶级和时间关系。在这项工作中，我们介绍了一个端到端网络：阶级关系网络（CTRN）。它包含三个关键组件：（1）表示变换模块过滤了从混合表示形式中特定的特定功能来构建图形结构化数据。 （2）阶级模块以顺序的方式对类和时间关系进行建模。 （3）G分类器利用摘要的共同出现作用对的特权知识，以进一步改善同时发生的动作检测。我们在三个具有挑战性的密集标签数据集上评估CTRN，并实现最先进的性能，以反映我们方法的有效性和鲁棒性。