The global aging population presents an urgent challenge in ensuring the safety and well-being of senior adults. This paper proposes an innovative Fuzzy Neural Network (FNN)-enhanced Image-based Action Recognition (FIAR) system in Microverse, an edge-scale Internet of Medical Things (IoMT) Metaverse designed for the Department of Homeland Security (DHS). Using adaptive FNNs, FIAR enhances the adaptability of the multisensor fusion process to accommodate varying input modes and quantities of input sources, thus reducing decision uncertainty and learning fuzzy relationships among multiple data streams. An experimental study confirms the feasibility of the Microverse framework and the ability of FIAR to deliver accurate and rapid responses, validating its effectiveness in safeguarding the independent living of elderly individuals.

Deep contrastive multi-view clustering has attracted considerable attention for its ability to extract shared representations across heterogeneous views. Despite its effectiveness, existing approaches usually assume full cross-view alignment, an assumption often violated in practice due to sensor noise, transmission loss, or inconsistent data augmentation. This partial view alignment substantially degrades performance, while current solutions relying on fixed pair selection or uniform weighting fail to resolve the semantic ambiguity of unaligned samples. Consequently, latent cross-view semantic relationships remain underutilized, while erroneous positive pairs unduly dominate the contrastive objective, compromising robustness under low alignment rates or noisy conditions. To address these challenges, we propose Dynamic Weight-Enhanced InfoNCE (DW-InfoNCE), a contrastive learning framework designed for partially view-aligned clustering. The framework introduces a cross-view positive pair mining strategy that iteratively identifies reliable pairs from unaligned samples through quantile-adaptive thresholds and uniqueness constraints, enabling recovery of latent semantic structures obscured by incomplete alignment. In addition, an adaptive faulty pair suppression mechanism is developed to identify semantically inconsistent pairs via temporal loss smoothing and global statistics, while attenuating their impact with Gaussian-based adaptive weights. Extensive experiments on five benchmarks demonstrate DW-InfoNCE consistently outperforms state-of-the-art methods across alignment rates, with significant gains under severe misalignment. The code of DW-InfoNCE can be publicly downloaded at https://github.com/qiuyu99627/ DWInfoNCE.git.

Multi-view clustering (MVC) has emerged as a powerful tool for analyzing complex datasets by leveraging consistent and complementary information from multiple sources. However, MVC faces three critical challenges in real-world scenarios: (1) Sample-level misalignment due to unknown cross-view correspondence, which introduces noisy correlations, (2) Feature-level heterogeneity from divergent dimensional spaces across views obscuring shared discriminative patterns, and (3) Dynamic-view inefficiency when integrating sequentially arriving data under privacy or sensor constraints. These challenges collectively hinder the clustering performance of existing studies, thus giving rise to a unified framework. To bridge this gap, we propose ASIA-MVC, an anchor-guided sample-and-feature incremental alignment framework for MVC, which is the first attempt in incremental learning on sample-unpaired multi-view data. First, the sample alignment module dynamically maps unpaired samples across views via anchor-based bipartite graphs. Second, the feature-aligned module employs an orthogonal decomposition strategy to unify heterogeneous feature spaces while preserving discriminative structures. Third, the novel incremental fusion framework integrates the dual-aligned modules under the guidance of shared anchors, enabling efficient cross-view representation learning. Furthermore, to solve the resulting problem, we develop a novel three-step alternate optimization algorithm with guaranteed convergence. Finally, the proposed method is validated in extensive experiments and achieves leading cluster efficiency and an outstanding sample-aligned effect.

Existing Multiple Kernel Clustering (MKC) algorithms commonly utilize the Nyström method to handle large-scale datasets. However, most of them employ uniform sampling for kernel matrix approximation, hence failing to accurately capture the underlying data structure, leading to large approximation errors. Additionally, they often use the same landmark points for all kernel matrix approximations, reducing kernel diversity. Moreover, in scenarios where approximate kernel matrices emerge over time, these methods require storing historical kernel information and recalculating, resulting in inefficient resource utilization. To address these issues, we propose a novel MKC algorithm, termed Incremental Nyström-based Multiple Kernel Clustering (INMKC). Specifically, leverage score sampling is utilized to reduce kernel approximation errors and enhance kernel diversity. Furthermore, we employ a consensus clustering structure that aligns with the newly emerged base kernel matrix for updates, avoiding recalculating previous kernel matrices, thus saving substantial computational resources. Additionally, we tackle the challenge of aligning incremental approximate kernels with different landmark points. Extensive experiments on the proposed INMKC demonstrate its effectiveness and efficiency compared to state-of-the-art methods.

Multi-view clustering is a long-standing hot topic in machine learning communities, due to its capability of integrating data information from multiple sources and modalities. By utilizing tensor Singular Value Decomposition (t-SVD) technique with the tensor rotation trick, recent advances have achieved remarkable improvements on clustering performance. However, we find this is attributed to the inadvertent use of sequential information of sorted data samples, i.e. inadvertent label use, which violates the unsupervised learning setting. On the other hand, existing large-scale approaches are mostly developed on the basis of matrix factorization or anchor techniques, thereby fail to consider the similarities among all data samples, preventing from further performance improvement. To address the above issues, we first analyze the tensor rotation trick and recommend to remove it from tensor clustering. On its basis, a novel large-scale multi-view tensor clustering method is developed by incorporating the pair-wise similarities with implicit linear kernel function. To solve the resultant optimization problem, we design an efficient algorithm of linear complexity. Moreover, extensive experiments are conducted and corresponding results well support the aforementioned finding and validate the effectiveness and efficiency of the proposed method.

The emergence of the Metaverse as a virtual extension of our social and professional lives has amplified concerns about identity, security, and authenticity. Advanced Deepfake technologies enable malicious actors to create highly realistic but fraudulent avatars, posing significant risks such as identity theft, misinformation, and erosion of trust within virtual communities. In sensitive applications such as virtual healthcare, these risks can have severe consequences. This paper proposes to Secure Avatars via Environmental Fingerprints (SAVE), a novel method for detecting Deepfake avatars leveraging unique environmental information in the physical world, including Electric Network Frequency (ENF) signals and device-specific sensor readings, to establish an authentication framework that is challenging for impostors to replicate. To evaluate the effectiveness of our SAVE scheme, we conducted a case study within a virtual healthcare application: a Microverse-based nursing home designed to monitor the safety of seniors living alone. Our experimental results demonstrate that SAVE achieves a high detection rate with minimal false positives. Our findings highlight the potential of physical environmental fingerprints as a robust layer of security in virtual worlds, especially in critical applications like virtual healthcare.

In this paper, we address the problem of novel class discovery (NCD), which aims to cluster novel classes by leveraging knowledge from disjoint known classes. While recent advances have made significant progress in this area, existing NCD methods face two major limitations. First, they primarily focus on single-view data (e.g., images), overlooking the increasingly common multi-view data, such as multi-omics datasets used in disease diagnosis. Second, their reliance on pseudo-labels to supervise novel class clustering often results in unstable performance, as pseudo-label quality is highly sensitive to factors such as data noise and feature dimensionality. To address these challenges, we propose a novel framework named Intra-view and Inter-view Correlation Guided Multi-view Novel Class Discovery (IICMVNCD), which is the first attempt to explore NCD in multi-view setting so far. Specifically, at the intra-view level, leveraging the distributional similarity between known and novel classes, we employ matrix factorization to decompose features into view-specific shared base matrices and factor matrices. The base matrices capture distributional consistency among the two datasets, while the factor matrices model pairwise relationships between samples. At the inter-view level, we utilize view relationships among known classes to guide the clustering of novel classes. This includes generating predicted labels through the weighted fusion of factor matrices and dynamically adjusting view weights of known classes based on the supervision loss, which are then transferred to novel class learning. Experimental results validate the effectiveness of our proposed approach.

Multiview clustering thrives in applications where views are collected in advance by extracting consistent and complementary information among views. However, it overlooks scenarios where data views are collected sequentially, i.e., real-time data. Due to privacy issues or memory burden, previous views are not available with time in these situations. Some methods are proposed to handle it but are trapped in a stability-plasticity dilemma. In specific, these methods undergo a catastrophic forgetting of prior knowledge when a new view is attained. Such a catastrophic forgetting problem (CFP) would cause the consistent and complementary information hard to get and affect the clustering performance. To tackle this, we propose a novel method termed contrastive continual multiview clustering with filtered structural fusion (CCMVC-FSF). Precisely, considering that data correlations play a vital role in clustering and prior knowledge ought to guide the clustering process of a new view, we develop a data buffer to store filtered structural information and utilize it to guide the generation of a robust partition matrix via contrastive learning. Additionally, to address the high complexity involved in acquiring and storing structural information, we propose a sampling strategy called clustering then sample. Furthermore, we theoretically connect CCMVC-FSF with semisupervised learning and knowledge distillation. Extensive experiments exhibit the excellence of the proposed method. Our code is publicly available at https://github.com/wanxinhang/CCMVC-FSF/.

The rapid development of multi-media techniques boosts the emergence of multi-view data, and how to uncover its intrinsic structure and utilize it to conduct the subsequent downstream tasks is crucial in data analysis. Multi-view clustering is representative of handling multi-view data. The anchor-based method has received widespread attention for excellent performance and low time complexity. However, existing methods encounter two drawbacks, cutting down their performance, i.e., the assumption of the availability of all views and limited interaction of anchor generation among views. In some scenes, views arrive sequentially, and storing them is challenging owing to the limited space/privacy considerations, and the existing anchor-based MVC is unsuitable for this. Additionally, recent works fail to generate anchors with the guidance of other views, and it is tough to align the anchor graphs. To this end, we propose A Lightweight Anchor-Based Incremental Framework for Multi-view Clustering. Specifically, we first initialize an anchor graph with the assistance of k-means when a new view arrives. Then, the consensus one of the anchor graph is updated by the newly collected view with a permutation matrix. Our proposed method is more capable of anchor alignment because, in incremental MVC, the anchor graphs of previous views could be listed as a reference to guide the generation of anchor graphs of the coming view. Furthermore, we design a three-step iterative and convergent algorithm to address the resultant problem. Notably, the proposed algorithm shows outstanding effectiveness and time/space efficiency in extensive experiments.

Ancient Chinese brings the wisdom and spirit culture of the Chinese nation. Automatic translation from ancient Chinese to modern Chinese helps to inherit and carry forward the quintessence of the ancients. However, the lack of large-scale parallel corpus limits the study of machine translation in ancient–modern Chinese. In this article, we propose an ancient–modern Chinese clause alignment approach based on the characteristics of these two languages. This method combines both lexical-based information and statistical-based information, which achieves 94.2 F1-score on our manual annotation Test set. We use this method to create a new large-scale ancient–modern Chinese parallel corpus that contains 1.24M bilingual pairs. To our best knowledge, this is the first large high-quality ancient–modern Chinese dataset. Furthermore, we analyzed and compared the performance of the SMT and various NMT models on this dataset and provided a strong baseline for this task.

Incorporating prior knowledge like lexical constraints into the model's output to generate meaningful and coherent sentences has many applications in dialogue system, machine translation, image captioning, etc. However, existing auto-regressive models incrementally generate sentences from left to right via beam search, which makes it difficult to directly introduce lexical constraints into the generated sentences. In this paper, we propose a new algorithmic framework, dubbed BFGAN, to address this challenge. Specifically, we employ a backward generator and a forward generator to generate lexically constrained sentences together, and use a discriminator to guide the joint training of two generators by assigning them reward signals. Due to the difficulty of BFGAN training, we propose several training techniques to make the training process more stable and efficient. Our extensive experiments on three large-scale datasets with human evaluation demonstrate that BFGAN has significant improvements over previous methods.