Automatic anomaly detection is a crucial task in video surveillance system intensively used for public safety and others. The present system adopts a spatial branch and a temporal branch in a unified network that exploits both spatial and temporal information effectively. The network has a residual autoencoder architecture, consisting of a deep convolutional neural network-based encoder and a multi-stage channel attention-based decoder, trained in an unsupervised manner. The temporal shift method is used for exploiting the temporal feature, whereas the contextual dependency is extracted by channel attention modules. System performance is evaluated using three standard benchmark datasets. Result suggests that our network outperforms the state-of-the-art methods, achieving 97.4% for UCSD Ped2, 86.7% for CUHK Avenue, and 73.6% for ShanghaiTech dataset in term of Area Under Curve, respectively.

Anomaly detection in video surveillance is a highly developed subject that is attracting increased attention from the research community. There is great demand for intelligent systems with the capacity to automatically detect anomalous events in streaming videos. Due to this, a wide variety of approaches have been proposed to build an effective model that would ensure public security. There has been a variety of surveys of anomaly detection, such as of network anomaly detection, financial fraud detection, human behavioral analysis, and many more. Deep learning has been successfully applied to many aspects of computer vision. In particular, the strong growth of generative models means that these are the main techniques used in the proposed methods. This paper aims to provide a comprehensive review of the deep learning-based techniques used in the field of video anomaly detection. Specifically, deep learning-based approaches have been categorized into different methods by their objectives and learning metrics. Additionally, preprocessing and feature engineering techniques are discussed thoroughly for the vision-based domain. This paper also describes the benchmark databases used in training and detecting abnormal human behavior. Finally, the common challenges in video surveillance are discussed, to offer some possible solutions and directions for future research.

Human action recognition is an important field in computer vision that has attracted remarkable attention from researchers. This survey aims to provide a comprehensive overview of recent human action recognition approaches based on deep learning using RGB video data. Our work divides recent deep learning-based methods into five different categories to provide a comprehensive overview for researchers who are interested in this field of computer vision. Moreover, a pure-transformer architecture (convolution-free) has outperformed its convolutional counterparts in many fields of computer vision recently. Our work also provides recent convolution-free-based methods which replaced convolution networks with the transformer networks that achieved state-of-the-art results on many human action recognition datasets. Firstly, we discuss proposed methods based on a 2D convolutional neural network. Then, methods based on a recurrent neural network which is used to capture motion information are discussed. 3D convolutional neural network-based methods are used in many recent approaches to capture both spatial and temporal information in videos. However, with long action videos, multistream approaches with different streams to encode different features are reviewed. We also compare the performance of recently proposed methods on four popular benchmark datasets. We review 26 benchmark datasets for human action recognition. Some potential research directions are discussed to conclude this survey.

Class imbalances in healthcare data, characterized by a disproportionate number of positive cases compared to negative ones, can lead to biased machine learning models that favor the majority class. Ensuring good performance across all classes is crucial for improving healthcare delivery and patient safety. Traditional oversampling methods like SMOTE and its variants face several limitations: they struggle with capturing complex data distributions, handling heterogeneous data types, and natively supporting multi-class datasets. To address these issues, we propose a deep learning based solution using an Auxiliary-guided Conditional Variational Autoencoder (ACVAE) enhanced with contrastive learning. Additionally, we introduce an ensemble technique where ACVAE creates synthetic positive samples, followed by the use of the Edited Centroid-Displacement Nearest Neighbor (ECDNN) algorithm to reduce the majority class. This combined approach takes advantage of ACVAE's ability to produce diverse oversampled data and ECDNN's skill in handling noise through selective undersampling, leading to a more balanced and informative dataset. Our experiments on 12 different health datasets show the effectiveness of our method. We conduct a thorough evaluation of our approach against traditional oversampling techniques and several benchmark machine learning models. The results demonstrate notable improvements in model performance across various metrics, highlighting the potential of deep learning based synthetic oversampling to address class imbalances in healthcare data.

Transformer models have emerged as dominant networks for various tasks in computer vision compared to Convolutional Neural Networks (CNNs). The transformers demonstrate the ability to model long-range dependencies by utilizing a self-attention mechanism. This study aims to provide a comprehensive survey of recent transformer-based approaches in image and video applications, as well as diffusion models. We begin by discussing existing surveys of vision transformers and comparing them to this work. Then, we review the main components of a vanilla transformer network, including the self-attention mechanism, feed-forward network, position encoding, etc. In the main part of this survey, we review recent transformer-based models in three categories: Transformer for downstream tasks, Vision Transformer for Generation, and Vision Transformer for Segmentation. We also provide a comprehensive overview of recent transformer models for video tasks and diffusion models. We compare the performance of various hierarchical transformer networks for multiple tasks on popular benchmark datasets. Finally, we explore some future research directions to further improve the field.

Anomaly detection is to identify abnormal events against normal ones within surveillance videos mainly collected in ground-based settings. Recently, the demand for processing drone-collected data is rapidly growing with the expanding range of drone applications. However, as most aerial videos collected by flying drones contain dynamic backgrounds and others, it is necessary to deal with their spatio-temporal features in detecting anomalies. This study presents a transformer-based video anomaly detection method whereby we investigate a challenging aerial dataset and three benchmark ground-based datasets. A multi-stage transformer is leveraged as an encoder to generate multi-scale feature maps, which are then conveyed to a hierarchical spatio-temporal transformer, that is linked to a decoder and used to capture spatial and temporal information by utilizing a joint attention mechanism. Extensive evaluations including several ablation studies suggest that this network outperforms the state-of-the-art methods. We expect the proposed transformer for U-net can find diverse applications in the video processing area. Code and pre-trained models are publicly available at https://github.com/vt-le/HSTforU.