Portrait customization (PC) has recently garnered significant attention due to its potential applications. However, existing PC methods lack precise identity (ID) preservation and face control. To address these tissues, we propose Diff-PC, a diffusion-based framework for zero-shot PC, which generates realistic portraits with high ID fidelity, specified facial attributes, and diverse backgrounds. Specifically

The ν support vector machine (ν-SVM) is an enhanced algorithm derived from support vector machines using parameter ν to replace the original penalty coefficient C. Because of the narrower range of ν compared with the infinite range of C, ν-SVM generally outperforms the standard SVM. Granular ball computing is an information fusion method that enhances system robustness and reduces uncertainty. To further

Large language models (LLMs) cannot see or understand graphs. The current Graph LLM method transform graph structures into a format LLMs understands, utilizing LLM as a predictor to perform graph-learning task. However, these approaches have underperformed in graph-learning tasks. The issues arise because these methods typically rely on a fixed neighbor hop count for the target node set by expert experience

The multi-sensor data fusion perception technology, as a pivotal technique for achieving complex environmental perception and decision-making, has been garnering extensive attention from researchers. To date, there has been a lack of comprehensive review articles discussing the research progress of multi-sensor fusion perception systems for embodied agents, particularly in terms of analyzing the agent’s

Accurate diagnosis of monkeypox is challenging due to the limitations of current diagnostic techniques, which struggle to account for skin lesions’ complex visual and structural characteristics. This study aims to develop a novel hybrid model that combines the strengths of Vision Transformers (ViT), ResNet50, and AlexNet with Graph Convolutional Networks (GCN) to improve monkeypox diagnostic accuracy

The large size of whole slide images (WSIs) in pathology makes it difficult to obtain fine-grained annotations. Therefore, multi-instance learning (MIL) methods are typically utilized to classify histopathology WSIs. However, current models overly focus on local features of instances, neglecting connection between local features and global features. Additionally, they tend to recognize simple instances

Heterogeneous graph representation learning (HGRL), as one of powerful techniques to process the heterogeneous graph data, has shown superior performance and attracted increasing attention. However, existing HGRL methods still face issues to be addressed: (i) They capture the consistency among different meta-path-based views to induce expensive computation costs and possibly cause dimension collapse

Clustering algorithms aim to analyze data structures and properties, grouping the data based on their underlying structural characteristics. Traditional multi-view clustering algorithms focus on combining data shared by multiple views to perform cluster analysis, and such algorithms typically limit the completeness of the data in each view. In real-world applications, it is common that the samples

Predicting urban metro ridership holds significant practical value for optimizing operational scheduling and guiding individual travel planning. Understanding the complexity of metro ridership influenced by temporal and spatial factors and modeling the intrinsic correlation between station inflow and outflow are current research focuses and challenges. To address these issues, we develop a Dynamic

Hyperspectral image (HSI) restoration is a critical task for remote sensing. The high dimensionality of HSIs poses significant challenges for restoration techniques. Existing methods often involve transforming the image into a lower-dimensional space to address the problem. However, most of these constructed spaces either require handcrafted prior assumptions or ignore utilizing the prior knowledge

Traditional studies of urban functions often rely on static classifications, failing to capture the inherently dynamic nature of urban environments. This paper introduces the Spatio-temporal Graph for Dynamic Urban Functions (STG4DUF), a novel framework that combines multimodal data fusion and self-supervised learning to uncover dynamic urban functionalities without ground truth labels. The framework

The objective of infrared–visible image fusion (IVIF) is to generate composite images from multiple modalities that enhance visual representation and support advanced vision tasks. However, most existing IVIF methods primarily focus on enhancing visual effects, while high-level task-driven approaches are constrained by specific perception networks and complex training strategies, leading to limited

Data-level methods often suffer from mode collapse when the minority class has multiple distribution patterns. Some studies have tried addressing the problem using similarity measurement or local dynamic information adjustment strategies but struggle with performance when the minority class exhibits intra-class imbalance. This paper proposes a multimodal data generation method with dual-discriminator

Visual object tracking has made significant contributions in many practical applications, but it remains a great challenge when the camera moves/shakes or the target is occluded. Various solutions leveraging deep-learning (DL) techniques have been introduced to address these challenging factors. However, these DL-based methods can hardly be implemented on an edge computing platform due to its limited

Traditionally, privacy and fairness have been recognized as having different goals in federated learning. Privacy requires data features to be as undetectable as possible, pursuing data ambiguity. Fairness, on the other hand, requires fair aggregation of the global model through the features of the data. So most existing researches has separately addressed these two ethical concepts. It is crucial

Entity resolution (ER) is the task of determining the equivalence between two entity descriptions. In traditional settings, the testing data and training data come from the same domain, e.g., sharing the same attribute structure. Nevertheless, in practical situations, the testing and training data often span different domains, hence calling for the study of the cross-domain ER problem. To tackle the

The exponential increase of multi-label data over various domains demands the development of effective feature selection methods. However, current sparse-learning-based feature selection methods that use LASSO-norm and l2,1-norm fail to handle two crucial issues for multi-label data. Firstly, LASSO-based methods remove features with zero-weight values during the feature selection process, some of which

The massive number of edge-connected IoT devices currently in SD-AIoT can be weaponized to launch Distributed Denial of Service attacks. Nevertheless, centralized DDoS defense schemes that excessively rely on up-to-date labeled training data are significantly inefficient due to the scarcity of such datasets. The privacy of these datasets and the widespread emergence of adversarial attacks make it difficult

Personalized Federated Learning (PFL) aims to train machine learning models on decentralized, heterogeneous data while preserving user privacy. This research survey examines the core communication challenges in PFL and evaluates optimization strategies to address key issues, including data heterogeneity, high communication costs, model drift, privacy vulnerabilities, and device variability. We provide

Individual preferences are formed within intricate social relationships and would be influenced by others’ opinions, especially in large-scale groups, resulting in social network large-scale group decision-making (SNLGDM). As the bridges for the interaction of decision makers (DMs), trust relationships should dynamically evolve with opinions during the decision-making process. However, traditional

For better explore the relations of inter-modal and inner-modal, even in deep learning fusion framework, the concept of decomposition plays a crucial role. However, the previous decomposition strategies (base & detail or low-frequency & high-frequency) are too rough to present the common features and the unique features of source modalities, which leads to a decline in the quality of the fused images

Multi-sensor, multi-source information fusion presents significant challenges in complex real-world applications such as power consumption prediction, where existing methods often have limitations in capturing both spatio-temporal features and fully exploit complex relationships among multi-variate features simultaneously. In real-world scenarios, such as complex electrical power system settings, capturing

This paper proposes a fusion-based extended social force model specifically designed to simulate collective behavior in bidirectional pedestrian flow. By integrating the social force model with the classic Vicsek model, the research not only examines adjustments in individuals’ desired speeds but also introduces a correction mechanism for alignment effects, aiming to enhance the model’s representation

Optical imaging and vision technology have become crucial research topics in the field of underwater and ocean scenes. These technologies play a vital role in advancing underwater exploration, scientific research, and smart aquaculture. Despite their importance, optical systems face substantial challenges in complex water environments, especially in turbid conditions where light absorption and scattering

Cancer subtype identification aims to partition the cancer patients into different subgroups with distinct clinical phenotypes, which is important for accurate diagnosis and treatment planning. The recent surge in multi-omics data has spurred research into integrative subtype identification, and multi-view clustering is widely used for identifying the underlying potential subtypes in an unsupervised

Accurate train travel time (T-t) is crucial for the quality and reliability of rail transport services, particularly for China–Europe Railway Express (CRE), which occupies an important position in the global transportation network. Despite transfer learning being a useful technique to address the limited data in CRE train travel time prediction, it struggles with some insurmountable problems, such

Causal discovery task (CDT) in time series become considerable challenging when encountering missing data, as certain crucial information is lost. Therefore, it is necessary to perform missing data imputation task (MDT) to provide more information support for CDT. Essentially, CDT and MDT are two mutually facilitating tasks, because each contains beneficial information for the other. However, most

Multi-view subspace clustering has attracted much attention because of its effectiveness in unsupervised learning. The high time consumption and hyper-parameters are the main obstacles to its development. In this paper, we present a novel method to effectively solve these two defects. First, we employ the bisecting k-means method to generate anchors and construct the hierarchical bipartite graph, which

Incomplete multivariate time series (MTS) clustering is a prevalent research topic in time series analysis, aimed at partitioning MTS containing missing data into distinct clusters. Contrastive learning-based multi-view clustering methods are a promising approach to address this issue. However, existing methods are typically not designed for time series. Specifically, most of these methods struggle

Multi-sensor Fusion (MSF) algorithms are critical components in modern autonomous driving systems, particularly in localization and AI-powered perception modules, which play a vital role in ensuring vehicle safety. The Error-State Kalman Filter (ESKF), specifically employed for localization fusion, is widely recognized for its robustness and accuracy in MSF implementations. While existing studies have

In the field of information management, effective event intelligence management is crucial for its development. With the continuous evolution of events, predicting future events has become a key task in information management. Event Prediction aims to predict upcoming events based on given contextual information. This requires modeling events and their relationships in the context to infer the structure

Kernel extreme learning machine (KELM), as a natural extension of ELM to kernel learning, has been successfully applied to solve various multivariate time series prediction (MTSP) tasks. Nevertheless, the high-dimensional and nonlinear properties of prediction information against the background of big data bring great challenges to the application of KELM. Recognizing these challenges, this paper develops

Most Bilingual Lexicon Induction (BLI) methods retrieve word translation pairs by finding the closest target word for a given source word based on cross-lingual word embeddings (WEs). However, we find that solely retrieving translation from the source-to-target perspective leads to some false positive translation pairs, which significantly harm the precision of BLI. To address this problem, we propose

Marine snow, caused by the aggregation of small organic and inorganic particles, creates a visual effect similar to drifting snowflakes. Traditional methods for removing marine snow often use median filtering, which can blur the entire image. Although deep learning approaches attempt to address this issue, they typically only work in the spatial domain and still struggle with blurring and residual

Quantum social network analysis (QSNA) is a recent advancement in the interdisciplinary field of quantum computing and social network analysis. This manuscript comprehensively reviews QSNA, emphasizing its methodologies, implementation strategies, challenges, and potential applications. It explores the conceptual foundation of key social network analysis research problems, including link prediction

In the realm of the Internet of Things (IoT), there has been a notable increase in the development and efficacy of Intrusion Detection Systems (IDS) that leverage machine learning (ML). Specifically, Federated Learning-based IDSs (FL-based IDS) have witnessed significant growth. These systems aim to mitigate data privacy breaches and minimize the communication overhead associated with dataset collection

Spatio-temporal fusion has become a popular technology for generating remote sensing images with high spatial and high temporal resolutions, thus providing valuable data support for remote sensing monitoring applications, such as environmental monitoring and city planning. Currently, deep learning-based methods have garnered a significant amount of attention, and they mostly employ the fine image at

Rapid and non-destructive techniques for fruit quality evaluation are widely concerned in modern agro-industry. Spectroscopy is one of the most commonly used techniques in this field. With the growing popularity of various spectroscopic instruments, it is indeed worthwhile to explore modeling with multi-source spectral data to achieve more accurate predictions. Nonetheless, a major challenge is acquiring

Underwater salient object detection (USOD) has garnered increasing attention due to its superior performance in various underwater visual tasks. Despite the growing interest, research on USOD remains in its nascent stages, with existing methods often struggling to capture long-range contextual features of salient objects. Additionally, these methods frequently overlook the complementary nature of multimodal

Shape from polarization (SfP) is a powerful passive three-dimensional imaging technique that enables the reconstruction of surface normal with dense textural details. However, existing deep learning-based SfP methods only focus on the polarization prior, which makes it difficult to accurately reconstruct targets with rich texture details under complicated scenes. Aiming to improve the reconstruction

The graph-based incomplete multi-view clustering aims at integrating information from multiple views and utilizes graph models to capture the global and local structure of the data for reconstructing missing data, which is suitable for processing complex data. However, ordinary graph learning methods usually only consider pairwise relationships between data points and cannot unearth higher-order relationships

Traffic prediction is a vital aspect of Intelligent Transportation Systems with widespread applications. The main challenge is accurately modeling the complex spatial and temporal relationships in traffic data. Spatial–temporal Graph Neural Networks (GNNs) have emerged as one of the most promising methods to solve this problem. However, several key issues have not been well addressed in existing studies

Graph convolutional network (GCN) has garnered significant attention and become a powerful tool for learning graph representations. However, when dealing with compositional data prevalent in various fields, the traditional GCN faces theoretical challenges due to the intrinsic constraints of such data. This paper generalizes the spectral graph theory in simplex space, aiming to address the graph structures

Multi-spectral vehicle Re-identification (Re-ID) aims to incorporate complementary visible and infrared information to tackle the challenge of re-identifying vehicles in complex lighting conditions. However, in harsh environments, the discriminative cues in RGB (visible) and NI (near infrared) modalities are significantly lost by the strong flare from vehicle lamps or the sunlight. To handle this problem

Probabilistic linguistic term set (PLTS) provides a flexible and comprehensive approach to reflecting qualitative information about decision makers (DMs) by fusing linguistic terms and probability distributions. This fusion makes PLTS an important focus of fuzzy decision theory. Dealing with uncertainty and ambiguity has always been a major challenge in the group decision-making (GDM) process, and

In this study, our goal is to enhance consensus efficiency in complex decision-making scenarios by constructing a large-scale group decision-making (LSGDM) method that integrates dynamic social network (DSN) and opinion dynamics. To this end, we design a model that can effectively cluster experts and dynamically adjust the network structure to more accurately reflect the diversity and complexity of

Multimodal sentiment analysis aims to combine information from different modalities to enhance the understanding of emotions and achieve accurate prediction. However, existing methods face issues of information redundancy and modality heterogeneity during the fusion process, and common multimodal sentiment analysis datasets lack unimodal labels. To address these issues, this paper proposes a multimodal

Advanced image fusion techniques aim to synthesise fusion results by integrating the complementary information provided by the source inputs. However, the inherent differences in the way distinct modalities capture and represent the same scene pose significant challenges for designing a robust and controllable fusion process. We argue that incorporating high-level semantic information from the text

Hyperspectral image (HSI) and Multispectral Image (MSI) fusion aims at combining a high-resolution MSI (HR MSI) with a low-resolution HSI (LR HSI), resulting in a fused image that contains the spatial resolution of the former and the spectral resolution of the latter. This approach offers a cost-effective alternative to directly acquiring high-resolution HSIs (HR HSIs). In this survey, we offer an

Privacy preservation is a critical concern in Federated Learning (FL). However, traditional Local Differential Privacy (LDP) methods face challenges in balancing FL model accuracy with noise strength. To address this, we propose a novel adaptive differential privacy method with feedback regulation, FedFR-ADP. First, we employ Earth Mover’s Distance (EMD) to measure the data heterogeneity of each client

The rapid development of artificial intelligence has constantly reshaped the field of intelligent healthcare and medicine. As a vital technology, multimodal learning has increasingly garnered interest because of data complementarity, comprehensive information fusion, and great application potential. Currently, numerous researchers are dedicating their attention to this field, conducting extensive studies

The performance of semi-supervised semantic segmentation models is significantly influenced by pseudo-label. To enhance the quality of pseudo-labels, we propose the Hybrid Architectures Ensemble Learning (HAEL) method. Specifically, we observe that different network architectures excel in specific tasks. CNN-based models are adept at capturing fine-grained features, whereas ViT-based models excel in

The emergence of vision-language models, particularly Contrastive Language-Image Pre-Training (CLIP), has significantly improved the performance of numerous visual tasks, demonstrating notable zero-shot transfer abilities. CLIP’s remarkable generalization ability offers substantial innovation potential for smart manufacturing and public safety surveillance, potentially accelerating the advancement

The BEV perceptual integrity depends on the ability to accurately capture multi-scale targets. However, the detection of multi-scale targets, especially small targets, is often affected by perceptual noise, information sparsity, and target occlusion, which subsequently affecting the accuracy of BEV perception and causing certain hidden danger to driving safety. To address these issues, we propose a

Seamless indoor/outdoor (IO) positioning is crucial for enabling smart cities and the Internet of Things (IoT). While various systems, such as the Global Navigation Satellite System (GNSS) and Ultra Wide Band (UWB), are commonly used for positioning indoors and outdoors. However, the transition between these environments presents significant challenges due to weak satellite signals and difficulties

Recent advancements in deep learning have significantly improved visual quality inspection and predictive maintenance within industrial settings. However, deploying these technologies on low-resource edge devices poses substantial challenges due to their high computational demands and the inherent complexity of Explainable AI (XAI) methods. This paper addresses these challenges by introducing a novel

Multi-view clustering has attracted widespread attention because of its capability to identify the common semantics shared by the data captured from different views of data, objects or phenomena. This is a challenging problem but with the emergence of deep auto-encoder networks, the performance of multi-view clustering methods has considerably improved. However, it is notable that most existing methods

For social network-based large-scale group decision-making scenarios, it is important to consider the willingness of decision-makers (DMs) in the consensus-reaching process (CRP). The bounded confidence (BC) value reflects decision-makers’ willingness. However, the BC value is usually set as a fixed value, ignoring that people's psychological acceptance changes dynamically in the CRP, which may lead

Distributed state estimation has been a significant research topic in recent years due to its applications for multi-robot and large-scale systems. Several approaches have been proposed in the context of continuous-time systems with stochastic noise, with limitations regarding observability, assumptions on the noise bounds, or requirements to pre-compute auxiliary global information offline. Moreover

Molecular representation learning (MRL) is essential in certain applications including drug discovery and life science. Despite advancements in multiview and multimodal learning in MRL, existing models have explored only a limited range of perspectives, and the fusion of different views and modalities in MRL remains underexplored. Besides, obtaining the geometric conformer of molecules is not feasible