Drones have become increasingly widely applied in surveillance systems due to their mobility, making aerial video anomaly detection methods more crucial. Anomalies in aerial videos often present as semantic conflicts, such as the presence of unexpected objects or unusual behaviors that do not align with the context. Previous approaches often relied on manually crafted knowledge graphs to detect such conflicts, which suffer from poor scalability. Recently, owing to their sufficient alignment training, multimodal large language models (MLLMs) have emerged as a generalized solution for semantic understanding. However, the direct application of MLLMs does not yield satisfactory anomaly detection performance in aerial videos. First, aerial videos often manifest platform-induced pseudo-motion, which obscures the true motion of objects and exacerbates detection errors. Second, without sufficient labeled data for fine-tuning, generic MLLMs often lack scene-level semantic guidance to reliably distinguish abnormal events that include contextually inappropriate behaviors. To address these challenges, we propose SemAero, an MLLM-based framework to address these challenges by: 1) designing an ego-motion reduction module to enhance model perception on object movement, 2) generating scene-specific prompts adaptively with step-by-step guidance for reasonable output, and 3) refining scores with dual-stream consistent feature for better domain-specific anomaly detection. Evaluated across 8 diverse aerial scenes and 73 sub-datasets, SemAero achieves a 3.09% improvement in AUC-ROC over the second-best model, demonstrating its ability in aerial video anomaly detection.

It is difficult for existing Internet of Things (IoT) intrusion detection systems to simultaneously identify and classify network anomalies, especially when the classification of unknown attacks is required, which brings great risks to the use of IoT devices. This article applies transformers to decouple false associations by causal reasoning to obtain an intelligent interpretable IoT detection system that can classify known attacks and identify unknown attacks. To achieve these goals, a causal transformer-based intelligent detection system for IoT devices is proposed. The system is divided into three main modules. First, training is conducted based on known traffic types with prior knowledge, and then the detection samples containing unknown attack types are classified into known traffic types. Second, the causal feature distribution of known traffic types is learned based on causal attention, and the causal feature distribution differences between normal and abnormal traffic samples are amplified with the minimax strategy to distinguish their types. Then, all traffic samples different from the known types are integrated into unknown types for causal transformer classification until there is only one type. Validation is performed on three broad and representative IoT datasets, and the results show that the causal transformer detection system can not only correctly classify known attacks but also achieve a 100% success rate in identifying cyberattacks on IoT datasets. In addition, more than 99% of unknown attack types can be effectively identified and classified, providing timely and effective guidance for cybersecurity defense.

With the continuous development of Internet of Things (IoT) technology, an increasing number of devices are connected to the internet, generating large amounts of highdimensional redundant information. Moreover, significant environmental and device heterogeneity leads to nonindependent and identically distributed (N-IID) samples. These challenges compromise the stability and causal interpretability of existing IoT detection methods, limiting their effectiveness in providing actionable insights for network security defense. To address these limitations, we propose a causal interpretabilitydriven IoT abnormal traffic detection approach. Central to this method is the adoption of structural causal models (SCMs), which are chosen for their ability to explicitly model direct causal linkages, suppress confounding effects, ensure robust cross-deployment detection, and enable counterfactual reasoning for precise attack attribution. The approach first eliminates spurious feature associations via Fourier transformation, then constructs and prunes SCMs using causal effect analysis, KNN, and counterfactual diagnosis to restore genuine causal relationships between anomalies and traffic features. Experiments on CI-CIDS2019, ToNIoT, and NSL-KDD datasets demonstrate effective noise reduction, redundancy elimination, and causal relationship recovery. Notably, detection accuracy improves by >19% on NSL-KDD data under polluted conditions, while maintaining stability and providing clear causal explanations for IoT network anomalies.

To address many of the deficiencies in optical neuroimaging technologies, such as poor tempo-spatial resolution, low penetration depth, contact-based measurement, and time-consuming image reconstruction, a novel, noncontact, portable, time-resolved laser speckle contrast imaging (TR-LSCI) technique has been developed for continuous, fast, and high-resolution 2D mapping of cerebral blood flow (CBF) at different depths of the head. TR-LSCI illuminates the head with picosecond-pulsed, coherent, widefield near-infrared light and synchronizes a fast, high-resolution, gated single-photon avalanche diode camera to selectively collect diffuse photons with longer pathlengths through the head, thus improving the accuracy of CBF measurement in the deep brain. The reconstruction of a CBF map was dramatically expedited by incorporating convolution functions with parallel computations. The performance of TR-LSCI was evaluated using head-simulating phantoms with known properties and in-vivo rodents with varied hemodynamic challenges to the brain. TR-LSCI enabled mapping CBF variations at different depths with a sampling rate of up to 1 Hz and spatial resolutions ranging from tens/hundreds of micrometers on rodent head surfaces to 1-2 millimeters in deep brains. With additional improvements and validation in larger populations against established methods, we anticipate offering a noncontact, fast, high-resolution, portable, and affordable brain imager for fundamental neuroscience research in animals and for translational studies in humans.

Fine-grained visual categorization (FGVC) relies on hierarchical features extracted by deep convolutional neural networks (CNNs) to recognize closely alike objects. Particularly, shallow layer features containing rich spatial details are vital for specifying subtle differences between objects but are usually inadequately optimized due to gradient vanishing during backpropagation. In this article, hierarchical self-distillation (HSD) is introduced to generate well-optimized CNNs features for accurate fine-grained categorization. HSD inherits from the widely applied deep supervision and implements multiple intermediate losses for reinforced gradients. Besides that, we observe that the hard (one-hot) labels adopted for intermediate supervision hurt the performance of FGVC by enforcing overstrict supervision. As a solution, HSD seeks self-distillation where soft predictions generated by deeper layers of the network are hierarchically exploited to supervise shallow parts. Moreover, self-information entropy loss (SIELoss) is designed in HSD to adaptively soften intermediate predictions and facilitate better convergence. In addition, the gradient detached fusion (GDF) module is incorporated to produce an ensemble result with multiscale features via effective feature fusion. Extensive experiments on four challenging fine-grained datasets show that, with neglectable parameter increase, the proposed HSD framework and the GDF module both bring significant performance gains over different backbones, which also achieves state-of-the-art classification performance.

Brain signal visualization has emerged as an active research area, serving as a critical interface between the human visual system and computer vision models. Diffusion-based methods have recently shown promise in analyzing functional magnetic resonance imaging (fMRI) data, including the reconstruction of high-quality images consistent with original visual stimuli. Nonetheless, it remains a critical challenge to effectively harness the semantic and silhouette information extracted from brain signals. In this paper, we propose a novel approach, termed as Controllable Mind Visual Diffusion Model (CMVDM). Specifically, CMVDM first extracts semantic and silhouette information from fMRI data using attribute alignment and assistant networks. Then, a control model is introduced in conjunction with a residual block to fully exploit the extracted information for image synthesis, generating high-quality images that closely resemble the original visual stimuli in both semantic content and silhouette characteristics. Through extensive experimentation, we demonstrate that CMVDM outperforms existing state-of-the-art methods both qualitatively and quantitatively. Our code is available at https://github.com/zengbohan0217/CMVDM.

3D face reconstruction aims at generating high-fidelity 3D face shapes and textures from single-view or multi-view images. However, current prevailing facial texture generation methods generally suffer from low-quality texture, identity information loss, and inadequate handling of occlusions. To solve these problems, we introduce an Identity-Conditioned Latent Diffusion Model for face UV-texture generation (UV-IDM) to generate photo-realistic textures based on the Basel Face Model (BFM). UV-IDM leverages the powerful texture generation capacity of a latent diffusion model (LDM) to obtain detailed facial textures. To preserve the identity during the reconstruction procedure, we design an identity-conditioned module that can utilize any in-the-wild image as a robust condition for the LDM to guide texture generation. UV-IDM can be easily adapted to different BFM-based methods as a high-fidelity texture generator. Furthermore, in light of the limited accessibility of most existing UV-texture datasets, we build a large-scale and publicly available UV-texture dataset based on BFM, termed BFM-UV. Extensive experiments show that our UV-IDM can generate high-fidelity textures in 3D face reconstruction within seconds while maintaining image consistency, bringing new state-of-the-art performance in facial texture generation.

The proliferation of Internet-connected devices and the complexity of modern network environments have led to the collection of massive and high-dimensional datasets, resulting in substantial information redundancy and sample imbalance issues. These challenges not only hinder the computational efficiency and generalizability of anomaly detection systems but also compromise their ability to detect rare attack types, posing significant security threats. To address these pressing issues, we propose a novel causal genetic network-based anomaly detection method, the CNSGA, which integrates causal inference and the nondominated sorting genetic algorithm-III (NSGA-III). The CNSGA leverages causal reasoning to exclude irrelevant information, focusing solely on the features that are causally related to the outcome labels. Simultaneously, NSGA-III iteratively eliminates redundant information and prioritizes minority samples, thereby enhancing detection performance. To quantitatively assess the improvements achieved, we introduce two indices: a detection balance index and an optimal feature subset index. These indices, along with the causal effect weights, serve as fitness metrics for iterative optimization. The optimized individuals are then selected for subsequent population generation on the basis of nondominated reference point ordering. The experimental results obtained with four real-world network attack datasets demonstrate that the CNSGA significantly outperforms existing methods in terms of overall precision, the imbalance index, and the optimal feature subset index, with maximum increases exceeding 10%, 0.5, and 50%, respectively. Notably, for the CICDDoS2019 dataset, the CNSGA requires only 16-dimensional features to effectively detect more than 70% of all sample types, including 6 more network attack sample types than the other methods detect. The significance and impact of this work encompass the ability to eliminate redundant information, increase detection rates, balance attack detection systems, and ensure stability and generalizability. The proposed CNSGA framework represents a significant step forward in developing efficient and accurate anomaly detection systems capable of defending against a wide range of cyber threats in complex network environments.

Image super-resolution (SR) has attracted increasing attention due to its widespread applications. However, current SR methods generally suffer from over-smoothing and artifacts, and most work only with fixed magnifications. This paper introduces an Implicit Diffusion Model (IDM) for high-fidelity continuous image super-resolution. IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework, where the implicit neural representation is adopted in the decoding process to learn continuous-resolution representation. Furthermore, we design a scale-adaptive conditioning mechanism that consists of a low-resolution (LR) conditioning network and a scaling factor. The scaling factor regulates the resolution and accordingly modulates the proportion of the LR information and generated features in the final output, which enables the model to accommodate the continuous-resolution requirement. Extensive experiments validate the effectiveness of our IDM and demonstrate its superior performance over prior arts. The source code will be available at https://github.com/Ree1s/IDM.

Face animation, one of the hottest topics in computer vision, has achieved a promising performance with the help of generative models. However, it remains a critical challenge to generate identity preserving and photo-realistic images due to the sophisticated motion deformation and complex facial detail modeling. To address these problems, we propose a Face Neural Volume Rendering (FNeVR) network to fully explore the potential of 2D motion warping and 3D volume rendering in a unified framework. In FNeVR, we design a 3D Face Volume Rendering (FVR) module to enhance the facial details for image rendering. Specifically, we first extract 3D information with a well designed architecture, and then introduce an orthogonal adaptive ray-sampling module for efficient rendering. We also design a lightweight pose editor, enabling FNeVR to edit the facial pose in a simple yet effective way. Extensive experiments show that our FNeVR obtains the best overall quality and performance on widely used talking-head benchmarks.

Fine-grained visual categorization (FGVC) aims to automatically recognize objects from different sub-ordinate categories. Despite attracting considerable attention from both academia and industry, it remains a challenging task due to subtle visual differences among different classes. Cross-layer feature aggregation and cross-image pairwise learning become prevailing in improving the performance of FGVC by extracting discriminative class-specific features. However, they are still inefficient to fully use the cross-layer information based on the simple aggregation strategy, while existing pairwise learning methods also fail to explore long-range interactions between different images. To address these problems, we propose a novel Alignment Enhancement Network (AENet), including two-level alignments, Cross-layer Alignment (CLA) and Cross-image Alignment (CIA). The CLA module exploits the cross-layer relationship between low-level spatial information and high-level semantic information, which contributes to cross-layer feature aggregation to improve the capacity of feature representation for input images. The new CIA module is further introduced to produce the aligned feature map, which can enhance the relevant information as well as suppress the irrelevant information across the whole spatial region. Our method is based on an underlying assumption that the aligned feature map should be closer to the inputs of CIA when they belong to the same category. Accordingly, we establish Semantic Affinity Loss to supervise the feature alignment within each CIA block. Experimental results on four challenging datasets show that the proposed AENet achieves the state-of-the-art results over prior arts.

Due to its fast deployment and scalability, cloud computing has become a significant technology trend. Organizations with limited budgets can achieve great flexibility at a low price by outsourcing their data and query services to the cloud. Since the cloud is outside the organization's trusted domain, existing research suggests encrypting data before outsourcing to preserve user privacy. Two main problems that the cloud user faces while searching over encrypted data are how to achieve a fine-grained search authorization and how to efficiently update the search permission. The existing attribute-based keyword search (ABKS) scheme addresses the first problem, which allows a data owner to control the search of the outsourced encrypted data according to an access policy. This paper proposes a dynamic attribute-based keyword search (DABKS) scheme that incorporates proxy re-encryption (PRE) and a secret sharing scheme (SSS) into ABKS. The DABKS scheme, which allows the data owner to delegate policy updating operations to the cloud, takes full advantage of cloud resources. We conduct experiments on real data sets to validate the effectiveness and efficiency of our proposed scheme.

Big data has become a hot topic in many areas where the volume and growth rate of data require cloud-based platforms for processing and analysis. Due to open cloud environments with very limited user-side control, existing research suggests encrypting data before outsourcing and adopting Searchable Symmetric Encryption (SSE) to facilitate keyword-based searches on the ciphertexts. However, no prior SSE constructions can simultaneously achieve sublinear search time, efficient update and verification, and on-demand file retrieval, which are all essential to the development of big data. To address this, we propose a Verifiable Ranked Searchable Symmetric Encryption (VRSSE) scheme that allows a user to perform top-K searches on a dynamic file collection while efficiently verifying the correctness of the search results. VRSSE is constructed based on the ranked inverted index, which contains multiple inverted lists that link sets of file nodes relating a specific keyword. For verifiable ranked searches, file nodes are ordered according to their ranks for such a keyword, and information about a node's prior/following neighbor will be encoded with the RSA accumulator. Extensive experiments on real data sets demonstrate the efficiency and effectiveness of our proposed scheme.

Hadoop framework has been widely used in various clusters to build large scale, high performance systems. However, Hadoop distributed file system (HDFS) is designed to manage large files and suffers performance penalty while managing a large amount of small files. As a consequence, many web applications, like WebGIS, may not take benefits from Hadoop. In this paper, we propose an approach to optimize I/O performance of small files on HDFS. The basic idea is to combine small files into large ones to reduce the file number and build index for each file. Furthermore, some novel features such as grouping neighboring files and reserving several latest version of data are considered to meet the characteristics of WebGIS access patterns. Preliminary experiment results show that our approach achieves better performance.

Data collections often have inconsistencies that arise due to a variety of reasons, and it is desirable to be able to identify and resolve them efficiently. Similarity queries are commonly used in data cleaning for matching similar data. In this work we concentrate on the following problem of approximate string matching based on edit distance: from a collection of strings, how to find those strings similar to a given string, or the strings in another collection of strings with similarity greater than some threshold? We propose an NFA-based (nondeterministic finite-state automation) method for effective approximate string search. We model strings as a trie and construct an NFA on top of the trie. We identify the similar strings by running the NFA based on the tree automata theory. Moreover, we propose grouped trie to further improve the performance of similarity search by incorporating some effective pruning techniques. We have implemented our method and the experimental results show that our approach achieves high performance and out performs the existing state-of-the-art methods by orders of magnitude.

With the developments of network technologies, many mechanisms have been introduced to improve system performance in cluster systems by exploiting remote idle memory. However, none of them can satisfy the requirements from different applications. Most methods can only improve the performance of a particular type of applications but not for others. One important reason is they failed to provide unified interfaces. In this paper, we propose collaborative memory pool (CMP) to solve this problems. CMP brings scalability and high performance. It has five features: (1) Providing malloc-like interfaces, block device interfaces and kernel API for different applications, which benefit both user-level and kernel-level applications; (2) Retaining traditional VM mechanism, programmers and uses have the freedom to select CMP or not; (3) Improving kernel applications performance by eliminating remote swapping; (4) Avoiding loan while in debt problem with dynamic workload; (5) Providing optional memory servers to further improve performance. In our testbed with CMP-based swap devices, Qsort gets 83.28% improvement comparing with the case using disk-based swap devices.