The proliferation of immersive applications such as Virtual, Augmented, and Mixed Reality (VR/AR/MR) imposes stringent low-latency and reliability requirements that challenge conventional O-RAN slicing mechanisms. Existing frameworks often fail to anticipate rapid XR traffic fluctuations driven by user motion and gaze dynamics, leading to inefficient resource utilization and SLA violations. To overcome these limitations, we propose a cross-layer intelligent control framework that integrates traffic prediction and reinforcement learning-based slice orchestration across the Non-RT and Near-RT RIC. By coupling long-term foresight with short-term adaptability, the proposed design enables proactive, SLA-aware scheduling under highly dynamic conditions. We further develop a trace-driven network emulator to reproduce realistic 5G behaviors and validate system robustness. Extensive experiments demonstrate that our framework consistently achieves over 95% SLA compliance, below 2% latency violations, and up to 30% latency reduction compared with state-of-the-art baselines, confirming its effectiveness and scalability for next-generation immersive networks.

Identifying and blocking malicious domains is one of the most direct and effective ways to combat malicious websites. In recent years, tools and technologies such as domain registration services, code repositories, and Domain-Flux have been exploited to generate malicious websites, enabling them to quickly "reincarnate" after being identified and shut down. Detecting methods for such malicious website domains are gradually shifting from the Belief Propagation (BP) algorithm to the Graph Neural Network (GNN) algorithm because the latter excels at aggregating neighboring node information to integrate node representations and graph embeddings. However, cloud services, Content Delivery Network (CDN), and Carrier-Grade Network Address Translation (CGNAT) often lead to benign-malicious co-location for domains, causing miscommunication in messages passing based on domain association relationships, thus reducing detection accuracy. To overcome this limitation, this paper proposes a malicious website domain detection algorithm based on one Multi-Message Passing Heterogeneous Neural Network (HMPN) framework. We apply this method to real-world network traffic scenarios and find that it achieves a Macro-Average F1 score of 91.70%, outperforming the baselines. We further conduct a measurement and analysis of the malicious websites’ industrial characteristics to better explore and detect malicious websites.

With the rapid development of cloud services, service providers increasingly rely on a dependable storage system equipped with large-capacity disks to ensure data availability. The primary source of unreliability in such storage systems attributes to disk failures. In recent years, some proactive methods base on machine learning models have emerged, aiming to predict impending disk failures by leveraging the SMART attributes of disks. These methods enable service providers to timely back up storage data. While the methods prove more effective and efficient in disk failure prediction, they still face challenges, such as inadequate mining of abnormal information and imbalanced classification. In this paper, we mainly analyzed the change of data distribution in hard disks. From the data analysis, we observed that the distribution change in the failed disk is obvious during the period before the disk damage, while that in the healthy disk is insignificant during running time. Motivated by the observation, we propose a novel framework namedSiaDFP, based on Siamese neural network, designed to predict impending disk failures by capturing the distribution changes in failed disks. Additionally, we observed that the failed disks exhibit some change points as an abnormal feature by analyzing the disk data trend. To fully mining abnormal information inhere in failed disks, we propose CP-MAP mechanism and 2D-Attention mechanism. Furthermore, we present a subsampling approach named Region Balanced Sampling to address the challenge of imbalanced classification. Experiments on the real-world dataset Backblaze and Baidu demonstrate that the performance ofSiaDFPis outstanding in the task of disk failure prediction.

Increased needs for social security promote the development of video surveillance, appealing to the exigency of real-time detection of anomalous events. Considering the rarity and unpredictability of anomalous events, a classical strategy is to model normal data and detect outliers to the model. As a fundamental generative model for time series data, Hidden Markov models (HMM) have been employed in various fields such as speech recognition and video analysis. In this paper, we propose the use of Bayesian HMMs with Dirichlet mixtures which are arrayed along patched frames with Dirichlet distributions as emission probability functions. These spatially-aligned HMMs evolve in parallel, significantly reducing inference time. Learning algorithm based on Stochastic Variational Inference and Discrete Variable Enumeration is applied to our model for fast and robust inference. Experiments over the public UCSD dataset demonstrate the validity of this approach.

Due to fixed convolution kernel structure, it is intractable for Convolutional Neural Networks (CNN) to adequately deal with intact instance geometric transformations, which may paralyze the CNN’s paradigmatic feature extraction. Inspired by Deformable Convolutional Networks, in this work, we introduce stochastic deformatble kernels, where kernel shape is assumed to be random vaiable. Stochastic deformable kernels may extract non-local alienated structural features, which slightly condones geometric transformations. Variational learning of the model based on two approximate posteriors is derived. And experiments over transformed MNIST dataset demonstrate the validity of this approach.

Event detection in crowded surveillance videos is a challenging yet important problem. In this paper, we present our eSur (Event detection system on SURveillance video) system, which is derived from TRECVid'12 surveillance tasks. Currently, eSur attempts to detect two categories of events: 1) pair-wise events (e.g., PeopleMeet, PeopleSplitUp and Embrace); 2) action-like events (e.g., ObjectPut, CellToEar, PersonRuns and Pointing). In eSur system, we first employ people detection and tracking algorithms to locate target persons in 3D space-time domain. Then the video sequences in which target persons occur are partitioned into several spatio-temporal cubes. Visual features (i.e. cubic feature and MoSIFT) are computed over these cubes. After that, a sequence learning method, (namely SVM with dynamic time alignment kernel), is employed to infer the existence of an event for the video sequence. According to the TRECVid SED formal evaluation, eSur has yielded fairly encouraging results on TRECVid'12 dataset.

Event detection in crowded surveillance videos is a challenging yet important problem. This paper focuses on pair-wise events that involve the interaction of two persons (e.g., people embrace, meet or split) in crowded videos. To detect such an event accurately, we should build an effective representation model that can characterize the sequential properties of two persons' interaction. Towards this end, we propose a novel pair-wise event detection approach using cubic features and sequence discriminant learning. A video sequence is first partitioned into several spatio-temporal cubes, and multiple features (e.g., statistics of trajectories, bag of spatio-temporal interest points) are extracted on these cubes and then fused to form a cubic feature descriptor under multiple kernel learning (MKL) framework. After that, the SVM with dynamic time alignment kernel is used to infer the existence of an event in the video sequence. Experimental results show that the proposed approach achieves the encouraging performance on TRECVid SED dataset.

In this paper, we present our detection, tracking and event recognition methods and the results for PETS 2012. First, ROIs (Regions of Interest) based on geometric constraints are utilized in single view detection to eliminate the negative influence of clutter environment. Then, an optimized observation model is applied to address the ID switching or tracking drifting problem in single view tracking. Third, we introduce the multi-view Bayesian network (MBN) to reduce the "phantom" phenomena which frequently happen in general multi-view detection tasks. At last, a motion-based event recognition method is proposed to handle the event recognition task. Experimental results on the PETS 2012 dataset indicate that our methods are very promising.

Content-based video copy detection over large corpus with complex transformations is important but challenging. It is not surprising that most existing methods fall short of either sufficient robustness to detect severely deformed copies or high accuracy to localize copy segments. In this paper, we propose a video copy detection approach which exploits complementary audio-visual features and sequential pyramid matching (SPM). Several independent detectors first match visual key frames or audio clips using individual features, and then aggregate the frame level results into video level results with SPM, which calculates video similarities by sequence matching at multiple granularities. Finally, detection results from basic detectors are fused and further filtered to generate the final result. Excellent performance evaluated on TRECVid 2010 copy detection task demonstrates the effectiveness of our approach.