Explore the vast range of titles available.

The Siamese network-based tracker calculates object templates and search images independently, and the template features are not updated online when performing object tracking. Adapting to interference scenarios with performance-guaranteed tracking accuracy when background clutter, illumination variation or partial occlusion occurs in the search area is a challenging task. To effectively address the issue with the abovementioned interference and to improve location accuracy, this paper devises a Siamese residual attentional aggregation network framework for self-adaptive feature implicit updating. First, SiamRAAN introduces Self-RAAN into the backbone network by applying residual self-attention to extract effective objective features. Then, we introduce Cross-RAAN to update the template features online by focusing on the high-relevance parts in the feature extraction process of both the object template and search image. Finally, a multilevel feature fusion module is introduced to fuse the RAAN-enhanced feature information and improve the network’s ability to perceive key features. Extensive experiments conducted on benchmark datasets (GOT-10K, LaSOT, OTB-50, OTB-100 and UAV123) demonstrated that our SiamRAAN delivers excellent performance and runs at 51 FPS in various challenging object tracking tasks. Code is available at https://github.com/MallowYi/SiamRAAN .

In the era of information explosion, the energy consumption of cloud data centers is significant. It’s critical to reduce the energy consumption of large-scale data centers while guaranteeing quality of service (QoS), especially the energy consumption of video cloud computing platforms. The application of virtual machine (VM) consolidation has been regarded as a promising approach to improve resource utilization and save energy of the data centers. In this paper, an energy efficient and QoS-aware VM consolidation method is proposed to address the issues. A combined prediction model based on grey model and ARIMA is applied to host status detection, and we provide a new scheme that VM placement policy based on resource utilization and varying energy consumption to search most suitable host and VM selection policy called AUMT selecting VM with low average CPU utilization and migration time. Extensive experimental results based on the cloudsim simulator demonstrate that proposed approach enables to achieve the objectives reducing energy consumption, number of migrations, SLAV and ESV by an average of 56.07%, 79.21%, 91.01% and 84.34% compared with the benchmark methods and the AUMT can reduce energy consumption, the number of migrations and ESV by an average of 15.46%, 28.11% and 3.96% compared with the state-of-the-art method.

Data in the natural open world tends to follow a long-tailed class distribution, leading deep models trained on such datasets to frequently exhibit inferior performance on the tail classes. Although existing approaches improve a model’s performance on tail categories through strategies such as class rebalancing, they often sacrifice the deep features that the model has already learned. In this paper, we propose a new joint distillation framework called JWAFD (Joint weighted knowledge distillation and multi-scale feature distillation) to address the long-tailed recognition problem from the perspective of knowledge distillation. The framework comprises two effective modules. Firstly, the weighted knowledge distillation module, which uses a category prior to adjust the weights of each category. By doing so, the training process becomes more balanced across all categories. Then, the multi-scale feature distillation module, which helps to further optimize the feature representation, thus solving the problem of under-learning of features encountered in previous studies. Compared with previous studies, the proposed framework significantly improves the performance of rare classes while maintaining the performance of head classes recognition. Extensive experiments on three benchmark datasets(CIFAR-100-LT, ImageNet-LT and iNaturalist2018) have demonstrated that the proposed novel distillation framework achieves comparable performance to the state-of-the-art long-tailed recognition methods. Our code is available at: https://github.com/xiaohe6/JWAFD .

Click-through rate prediction is one of the hot topics in the recommendation and advertising systems field. The existing click-through rate prediction models can be classified into feature interactions and behavior sequences. Feature interaction models form new feature combinations by fusing different features. The behavior sequence models capture the user’s interests by considering the historical behavior and using an attention mechanism to model the relationship between the target item and the behavior sequence. However, the existing click-through rate prediction techniques either ignore both aspects or only consider one, limiting prediction performance. In order to solve the above problems, we propose a click-through prediction model (CFIBS) that combines feature interaction and behavioral sequence in this paper. Firstly, the Global-Local Gate Module and Post-LN Informer are proposed to extract the user’s interests from user behavior sequences to improve training efficiency. In addition, we introduce auxiliary losses to supervise the extraction of user interest features. Secondly, in the interest update layer, we introduce an attention mechanism based gated recurrent unit to enhance the relationship between interest representation and the target item. Finally, for non-temporal features, we propose a Multi-Cross Layer to increase the nonlinear ability of the model. Experiments show that our model can effectively improve the click-through rate prediction accuracy of advertisements. The codes will be available at https://github.com/jihuiqin2/sequence_ctr .

Short-term traffic forecasting is an important part of intelligent transportation systems. Accurately predicting short-term traffic trends can avoid traffic congestion and plan travel routes, which is of great significance to urban management and traffic scheduling. The difficulty of short-term urban traffic forecasting is that the traffic flow is random and will be dynamically changed by the traffic conditions of nearby nodes. In order to solve this problem, this paper proposes a model based on Dynamic Diffusion Spatial-Temporal Graph Convolutional Network. It first combines the dynamic generation matrix and the static distance matrix to grasp real-time traffic conditions, and then introduces the diffusion random walk strategy to capture the correlation of spatial nodes. Finally, the convolutional LSTM module is used to mine the spatiotemporal dependence of traffic data to improve the accuracy of traffic prediction. Compared to several baseline models, the experimental results show that the model is 7% better than other models on several metrics and demonstrates the necessity of the module through ablation experiments.

As a fluid-based precise processing method, soft abrasive flow processing has been widely used in advanced electromechanical systems, complex mold manufacturing, and other engineering fields. Because of the low volume fraction of abrasive particles and micro-force/cutting removal characteristics, there exists a potential improvement in terms of processing efficiency and uniformity. In view of the above problems, this article presents an ultrasonic-assisted soft abrasive flow processing method. Based on the realizable k–ε turbulence model and the mixture flow model, an ultrasonic coupling enhancement dynamic model for soft abrasive flow is set up, and the kinetic energy transport equation of realizable k–ε turbulence model can be revised. Using particle image velocimetry technology, an on-line observation experimental platform for ultrasonic-assisted soft abrasive flow is developed to conduct the real-time acquisition of abrasive flow state and particle distribution in a constrained flow passage. An ultrasonic-assisted soft abrasive flow processing experimental platform is established to complete the processing experiment. The experimental results show that the ultrasonic excitation vibration can effectively enhance the turbulence intensity and distribution uniformity of the abrasive flow, the average processing time can be shortened by more than 6 h, and a better surface quality can be obtained.

Existing work generally classifies news headlines as a matter of short text classification. However, due to the strong domain nature and limited text length of news headlines, their classification results are usually determined by several specific keywords, which makes the traditional short text classification method ineffective. In this paper, we propose a new method to identify keywords in news headlines and expand their features from sentence level and word level respectively, and finally use convolutional neural networks (CNN) to extract and classify their features. The proposed model was tested on the Sogou News Corpus dataset and achieved 93.42 % accuracy.

Existing self-representation models based on multilayer perceptrons (MLPs) have gained widespread attention for their outstanding clustering performance in subspace clustering. However, when images contain rich spatial information, the use of fully connected neural networks that only accept vector inputs results in a significant loss of spatial information, thereby greatly reducing the clustering performance of the models. To address the clustering problem of data with rich spatial information, this paper proposes a multichannel subspace clustering method based on a self-representation network (CGSNet). This method incorporates modules capable of mining spatial features into the self-representation network to highlight different data characteristics and supplement the spatial information lost by the MLP. CGSNet successfully uncovers the latent features within the input data samples and extracts the spatial relationships among different image features by employing channel and spatial attention modules. Additionally, static parameterized channel mapping and spatial mapping are used to refine and filter the obtained spatial information, further enhancing the quality of self-representation. Finally, by leveraging the self-representation network, the clustering task is completed by learning the affinity matrix. The experimental results demonstrate that CGSNet outperforms the self-expressive network (SENet), achieving improvements of 1.5%, 3.3%, 0.9%, and 4.4% in terms of the clustering accuracy with the MNIST, FashionMNIST, CIFAR-10, and EMNIST datasets, respectively. CGSNet achieves the highest accuracy among competitive clustering methods, including EnSC, SENet, and 14 others.

NACHT, LRR, and PYD domains-containing protein 3 (NLRP3) inflammasome activation and effects during ribonucleic acid (RNA) viral infection are the focus of a wide range of research currently. Both the pathogen-associated molecule pattern derived from virions and intracellular stress molecules involved in the process of viral infection lead to activation of the NLRP3 inflammasome, which in turn triggers inflammatory responses for antiviral defense and tissue healing. However, aberrant activation of the NLRP3 inflammasome can instead support viral pathogenesis and promote disease progression. Here, we summarize and expound upon the recent literature describing the molecular mechanisms underlying the activation and effects of the NLRP3 inflammasome in RNA viral infection to highlight how it provides protection against RNA viral infection.

Hybrid Broussonetia papyrifera shows great promise for use in antibiotic-free feed, potentially contributing to the green and sustainable development of the animal husbandry industry. In this study, we investigated the impact of Broussonetia papyrifera silage on the intestinal health of Kazakh sheep. Forty healthy male Kazakh sheep, aged 5 months and weighing an average of 28.28 ± 1.14 kg, were randomly assigned to either a control or an experimental group, each comprising four replicates, with five sheep per replicate. The control group was fed a basal diet, while the experimental group received a diet supplemented with 20% Broussonetia papyrifera silage (dry matter basis). The 70-day experiment included a 10-day adaptation phase followed by a 60-day feeding trial. The results showed that there was no significant difference in growth performance or apparent nutrient digestibility between the experimental and control groups ( p  > 0.05). However, the experimental group exhibited significantly greater total antioxidant capacity, alongside higher contents of superoxide dismutase, catalase, glutathione peroxidase, immunoglobulins A, M, and G, and interleukins-2, −6, and −8 in the intestinal mucosa; in contrast, malondialdehyde and interleukin-4 contents were significantly reduced ( p  < 0.01). Furthermore, the dietary inclusion of Broussonetia papyrifera silage resulted in a reduction in the relative abundance of the bacterial genera Turicibacter and Romboutsia ( p  < 0.05). In conclusion, the feeding of Broussonetia papyrifera silage to Kazakh sheep significantly enhanced immune function, increased antioxidant capacity, and reduced the relative abundance of potentially pathogenic bacteria in the sheep without negatively impacting their growth or nutrient digestion, thus supporting the overall health of the animals.