Weakly supervised video anomaly detection aims to detect anomalous events with only video-level labels. In the absence of boundary information for anomaly segments, most existing methods rely on multiple instance learning. In these approaches, the predictions for unlabeled video snippets are guided by the classification of labeled untrimmed videos. However, these methods do not account for issues such as video blur and visual occlusion, which can hinder accurate anomaly detection. To address these issues, we propose a novel weakly supervised video anomaly detection method that fuses multimodal and multiscale features. Firstly, RGB and optical flow snippets are input into pre-trained I3D to extract appearance and motion features. Then, we introduce an Attention De-redundancy (AD) module, which employs an attention mechanism to filter out task-irrelevant redundancy in these appearance and motion features. Next, to mitigate the effects of video blurring and visual occlusion, we propose a Multi-scale Feature Learning module. This module captures long-term and short-term temporal dependencies among video snippets to provide global and local guidance for blurred or occluded video snippets. Finally, to effectively utilize the discriminative features of different modalities, we propose an Adaptive Feature Fusion module. This module adaptively fuses appearance and motion features based on their respective feature weights. Extensive experimental results demonstrate that our proposed method outperforms mainstream unsupervised and weakly supervised methods in terms of AUC. Specifically, our proposed method achieves 97.00% AUC and 85.31% AUC on two benchmark datasets, i.e., ShanghaiTech and UCF-Crime, respectively.

As an important technology in 3D vision, point-cloud registration has broad development prospects in the fields of space-based remote sensing, photogrammetry, robotics, and so on. Of the available algorithms, the Iterative Closest Point (ICP) algorithm has been used as the classic algorithm for solving point cloud registration. However, with the point cloud data being under the influence of noise, outliers, overlapping values, and other issues, the performance of the ICP algorithm will be affected to varying degrees. This paper proposes a global structure and adaptive weight aware ICP algorithm (GSAW-ICP) for image registration. Specifically, we first proposed a global structure mathematical model based on the reconstruction of local surfaces using both the rotation of normal vectors and the change in curvature, so as to better describe the deformation of the object. The model was optimized for the convergence strategy, so that it had a wider convergence domain and a better convergence effect than either of the original point-to-point or point-to-point constrained models. Secondly, for outliers and overlapping values, the GSAW-ICP algorithm was able to assign appropriate weights, so as to optimize both the noise and outlier interference of the overall system. Our proposed algorithm was extensively tested on noisy, anomalous, and real datasets, and the proposed method was proven to have a better performance than other state-of-the-art algorithms.

Image colorization has a widespread application in video and image restoration in the past few years. Recently, automatic colorization methods based on deep learning have shown impressive performance. However, these methods map grayscale image input into multi-channel output directly. In the process, it usually loses detailed information during feature extraction, resulting in abnormal colors in local areas of the colorization image. To overcome abnormal colors and improve colorization quality, we propose a novel Double-Channel Guided Generative Adversarial Network (DCGGAN). It includes two modules: a reference component matching module and a double-channel guided colorization module. The reference component matching module is introduced to select suitable reference color components as auxiliary information of the input. The double-channel guided colorization module is designed to learn the mapping relationship from the grayscale to each color channel with the assistance of reference color components. Experimental results show that the proposed DCGGAN outperforms existing methods on different quality metrics and achieves state-of-the-art performance.

Sketch face recognition has recently gained significant attention in the field of computer vision due to its ability to quickly identify matched pairs of optical and sketch images. This technology has the potential to greatly improve the efficiency of law enforcement agencies in criminal investigations. However, there are still challenges that need to be addressed in sketch face recognition algorithms, such as modal differences and limited sample sizes. To overcome these issues, this study proposes a Residual Serialized Cross Grouping Transformer (RSCGT), which contains a residual serialized module to reduce the computation complexity, a two-layer Cross Grouping Transformer module that is capable of extracting modality-invariant context features, a domain adaptive module to mitigate the impact of modal differences. Additionally, we introduce a meta-learning training strategy to augment the generalization ability of this model. Experimental results demonstrate that the RSCGT achieves high accuracy in sketch face recognition tasks, even with small-scale datasets.

Sketch face recognition refers to the process of matching sketches to photos. Recently, there has been a growing interest in using deep learning to learn discriminative features for sketch face recognition. However, the success of deep learning relies on the large-scale paired images to counteract effects such as over-fitting, since the amount of the paired training data is relatively small, the discriminative power of the deeply learned features will inevitably be reduced. This paper proposes a novel deep metric learning method termed domain alignment embedding network for sketch face recognition. Specifically, a training episode strategy is designed to alleviate the small sample problem, and a domain alignment embedding loss is proposed to guide the feature embedding network to learn discriminative features. Extensive experimental results on the UoM-SGFSv2 and PRIP-VSGC datasets are verified to show the effectiveness of the proposed method.

Face sketch synthesis has made significant progress in the past few years. Recently, GAN-based methods have shown promising results on image-to-image translation problems, especially photo-to-sketch synthesis. Because the facial sketch has a hyper-abstract style and continuous graphic elements, compared with other image styles, its local details are easier to expose small artifacts and blur. The existing face sketch synthesis methods lack models for specific facial regions and usually generate face sketches with coarse structures. To synthesis high-quality sketches and overcome the blurs and deformations, this paper proposes a novel Multi-Hierarchies GAN, which divides the face image into multiple hierarchical structures to learn different regions’ features of the face. It includes three modules: a local region module, mask module, and fusion module. The local region module can learn the detailed features of different local regions of the face by GAN. The mask module can generate a coarse facial structure of a sketch and uses the facial feature extractor to enhance the high-level image and learn the latent spaces’ feature. The fusion module can generate the final sketch by combining fine local regions and coarse facial structure. Extensive qualitative and quantitative experiments illustrate that the proposed method outperforms the state-of-the-art methods on the CUFS and CUFSF standard datasets and photos on the internet.