Math problems are an important knowledge carrier and evaluation means in personalized teaching. Their high cost of manual compilation promotes the research of math problem generation. Many previous studies have focused on the generation of math word problems, which are difficult to meet the real teaching needs due to the single task-objective orientation and small differences in generation results

This paper introduces a novel framework for augmenting explainability in the interpretation of point cloud data by fusing expert knowledge with counterfactual reasoning. Given the complexity and voluminous nature of point cloud datasets, derived predominantly from LiDAR and 3D scanning technologies, achieving interpretability remains a significant challenge, particularly in smart cities, smart agriculture

Incomplete multi-view clustering (IMC) is a pivotal task within the area of machine learning, encompassing several unresolved challenges, such as representation of objects, relations of various views, discriminative of features, and data restoration. To address these challenges, we propose a novel Adaptive Structural-guided Multi-level representation Learning with Graph Contrastive algorithm for IMC

Healthcare systems worldwide face persistent challenges in efficiency, accessibility, and personalization. Modern artificial intelligence (AI) has shown promise in addressing these issues through precise predictive modeling; however, its impact remains constrained by limited integration into clinical workflows. Powered by modern AI technologies such as multimodal large language models and world models

Data can be represented by multiple sets of features, where each semantically coherent set of features is called a view. For example, an image can be represented by multiple sets of features that measure textures, shapes, edge features, etc. Collecting multiple views of data is generally easier than annotating it with the help of experts. Thus, the unsupervised exploration of data in consultation with

Medical data analysis has emerged as an important driving force for smart healthcare with applications ranging from disease analysis to triage, diagnosis, and treatment. Text data plays a crucial role in providing contexts and details that other data types cannot capture alone, making its analysis an indispensable resource in medical research. Natural language processing, a key technology for analyzing

Multimodal medical image fusion technology enhances medical representations and plays a vital role in clinical diagnosis. However, fusing medical images remains a challenge due to the stochastic nature of lesions and the complex structures of organs. Although many fusion methods have been proposed recently, most struggle to effectively establish global context dependency while preserving salient semantic

Domain generalization refers to training a model with annotated source domain data and making it generalize to various unseen target domains. It has been extensively studied in classification, but remains challenging in object detection. Existing domain generalization object detection methods mainly rely on generative or adversarial data augmentation, which increases the complexity of training. Recently

Automatic emotion recognition has attracted significant interest in healthcare, thanks to remarkable developments made recently in smart and innovative technologies. A real-time emotion recognition system allows for continuous monitoring, comprehension, and enhancement of the physical entity’s capacities, along with continuing advice for enhancing quality of life and well-being in the context of personalized

Map construction task plays a vital role in providing precise and comprehensive static environmental information essential for autonomous driving systems. Primary sensors include cameras and LiDAR, with configurations varying between camera-only, LiDAR-only, or camera-LiDAR fusion, based on cost-performance considerations. While fusion-based methods typically perform best, existing approaches often

Clinical decision support systems for pathology, particularly those utilizing computational pathology (CPATH) for whole slide image (WSI) analysis, face significant challenges due to the need for high-quality annotated datasets. Given the vast amount of information contained in WSIs, creating such datasets is often prohibitively expensive and time-consuming. Multiple Instance Learning (MIL) has emerged

Traditional convolutional operations primarily concentrate on local feature extraction, which can result in the loss of global features. However, current fusion methods for extracting global features exhibit high time complexity and have difficulties in capturing long-range dependencies. In this paper, a dual-graph convolutional neural network is constructed to perform cross-modal graph inference based

Images captured in extreme environments, including deep-earth, deep-sea, and deep-space exploration sites, often suffer from significant degradation due to complex visual factors, which adversely impact visual quality and complicate perceptual tasks. This survey systematically synthesizes recent advancements in visual perception and understanding within these challenging contexts. It focuses on the

Outlier explanation methods based on outlying subspace mining have been widely used in various applications due to their effectiveness and explainability. These existing methods aim to find an outlying subspace of the original space (a set of features) that can clearly distinguish a query outlier from all inliers. However, when the query outlier in the original space are linearly inseparable from inliers

Hybrid brain–computer interfaces (BCI) have garnered attention for the capacity to transcend the constraints of single-modality BCI. It is essential to develop innovative fusion methodologies to exploit the high temporal resolution of electroencephalography (EEG) and the high spatial resolution of functional near-infrared spectroscopy (fNIRS). We propose an end-to-end Spatial–Temporal Alignment Network

Deep Neural Networks (DNNs) have demonstrated exceptional recognition capabilities in traditional computer vision (CV) tasks. However, existing CV models often suffer a significant decrease in accuracy when confronted with out-of-distribution (OOD) data. In contrast to these DNN models, human can maintain a consistently low error rate when facing OOD scenes, partly attributed to the rich prior cognitive

This work focuses on the problem of Generalized Category Discovery (GCD), a more realistic and challenging semi-supervised learning setting where unlabeled data may belong to either previously known or unseen categories. Recent advancements have demonstrated the efficacy of both pseudo-label-based parametric classification methods and representation-based non-parametric classification methods in tackling

Decoding speech from brain signals has been a long-standing challenge in neuroscience and brain–computer interface research. While significant progress has been made in English speech decoding, cross-subject Chinese speech decoding remains understudied, despite its potential applications and unique linguistic characteristics. Chinese, with its logographic writing system and tonal nature, presents unique

Automatic segmentation of medical images plays a crucial role in assisting doctors with diagnosis and treatment planning. Among them, multi-scale vision transformer has become a powerful tool for medical image segmentation. However, due to its overly aggressive self-attention design leads to issues such as insufficient local feature extraction and lack of detailed feature information. To address these

Alzheimer’s disease (AD) is a prevalent neurodegenerative disorder with high incidence and significant mortality among the elderly worldwide. Nevertheless, early and accurate diagnosis and treatment of the disease could delay its progression to evolve into more severe phases. Traditional methods, which are largely binary in classification, often struggle with the complexity of multi-classification

We propose a probabilistic framework for attitude estimation using the matrix Fisher distribution on the special orthogonal group SO(3). To be specific, a deep neural network is first designed to estimate the attitude probability distributions over SO(3), i.e., the unconstrained parameters of matrix Fisher distribution. The network takes common inertial measurements as input and overcomes the challenge

Accurate anomaly detection is essential for ensuring the reliability of microservice systems. Current approaches typically analyze system anomaly patterns using single-modal data (i.e., traces, metrics, and logs) while neglecting the class imbalance between normal and abnormal samples, which can easily lead to misjudgment. This paper propose AMulSys, a graph-based anomaly detection approach, which

Image denoising is a vital computer vision task that aims to remove noise from images. Deep learning techniques have made remarkable progress in this field in recent years. This survey provides a comprehensive overview of efficient deep learning-based image denoising methods. Unlike previous reviews, it focuses exclusively on models based on efficient deep learning and examines the latest developments

Visual navigation requires the agent reasonably perceives the environment and effectively navigates to the given target. In this task, we present a Multimodal Adaptive Graph (MAG) for learning and grounding the visual clues based on the object relationships. MAG consists of key navigation elements: object relative position relationships, previous navigation actions, past training experience, and target

In recent years, the integration of hyperbolic geometry with Graph Neural Networks (GNNs) has garnered significant attention due to its effectiveness in capturing complex hierarchical structures, particularly within real-world graphs and scale-free networks. Although hyperbolic neural networks have shown strong performance across various domains, most existing models rely on static graph structures

Since the normal patterns of time series change dynamically over time, unsupervised time series anomaly detection methods have to face the overfitting problem. Although some approaches based on contrastive learning try to solve this problem, these methods ignore the complex intrinsic correlations within the given time series and may face the representation collapse problem. As the result, the normal

In contemporary industrial applications, predictive models have been pivotal in bolstering production efficiency, product quality, scalability, and cost-effectiveness while promoting sustainability. These predictive models can be constructed solely based on domain-specific knowledge, exclusively on observational data, or by amalgamating both approaches. They are commonly referred to as Full-, Zero-

Image to point cloud global localization is crucial for robot navigation in GNSS-denied environments and has become increasingly important for multi-robot map fusion and urban asset management. The modality gap between images and point clouds poses significant challenges for cross-modality fusion. Current cross-modality global localization solutions either require modality unification, which leads

Infrared sensing is a core method for supporting unmanned systems, such as autonomous vehicles and drones. Recently, infrared sensors have been widely deployed on mobile and stationary platforms for detection and classification of objects from long distances and in wide field of views. Given its success in the vision image analysis domain, deep learning has also been applied for object recognition

Inspired by the recent success of large language models (LLMs) in the general domain, many large multimodal models, such as vision–language models, have been developed to tackle problems across modalities.

Sentiment Analysis (SA) is the process to identify, extract, and quantify subjective information from text data, such as opinions, attitudes, emotions, and sentiments. Traditional approaches to sentiment classification primarily relied on utilizing raw data, which may not fully capture the detail insights within the dataset. Here, we propose an approach that seeks to enhance sentiment classification

Electrocardiogram (ECG) classification is pivotal in diagnosing and monitoring cardiovascular diseases (CVDs). However, existing methods predominantly rely on hand-crafted features or specific signal representations, often leading to incomplete and suboptimal analysis of ECG data. This paper addresses these limitations by identifying a significant research gap in the comprehensive utilization of ECG

In the context of information overload, leveraging online reviews for product ranking can enhance consumers’ decision-making efficiency and facilitate informed purchasing decisions. However, previous studies have mainly focused on online review data from a single source and do not capture consumer psychology behavior for scientific and reasonable product ranking. Therefore, this study proposes a multi-source

Spatio-temporal graph neural networks (STGNNs) have garnered considerable attention for their promising performance across various applications. While existing models have demonstrated superior performance in exploring the interpretability of graph neural networks (GNNs), the interpretability of STGNNs is constrained by their complex spatio-temporal correlations. In this paper, we introduce a novel

Vision-Language Model (VLM) is a kind of multi-modality deep learning model that aims to fuse visual information with language information to enhance the understanding and analysis of visual content. VLM was originally used to integrate multi-modality information and improve task accuracy. Then, VLM was further developed in combination with zero-shot and few-shot learning to solve the problem of insufficient

The consequences of crowd behavior in high-density pedestrian flows, especially in response to exacerbating incidents, can result in tragic outcomes such as trampling and crushing, making the active monitoring of crowd motion crucial, to provide timely danger warnings and implement preventive measures. This paper proposes a novel approach for crowd behavior monitoring and prediction of bridge loads

In recent years, generative artificial intelligence has gained momentum and created extremely realistic synthetic multimedia content that can spread misinformation and mislead society. Deepfake detection is a technique consisting of frameworks, algorithms and approaches to predict manipulated contents namely, image, audio and video. To this end, we have analyzed and explored various deepfake detection

Visible-infrared person re-identification (VI-ReID) remains a challenging task due to the inconsistencies in data distribution and semantic inconsistency between heterogeneous modalities. Some visible-infrared person re-identification methods that leverage auxiliary modalities have achieved significant progress. However, these methods merely apply pixel-level augmentation to the original images and

Knowledge-based Visual Question Answering (KB-VQA) expands traditional VQA by utilizing world knowledge from external sources when the image alone is insufficient to infer a correct answer. Existing methods face challenges due to low recall rates, limiting the ability to gather essential information for accurate answers. While increasing the amount of retrieved knowledge entries can enhance recall

Integrating multimodal knowledge into large language models (LLMs) represents a significant advancement in dialogue generation capabilities. However, the effective incorporation of such knowledge in zero-resource scenarios remains a substantial challenge due to the scarcity of diverse, high-quality dialogue datasets. To address this, we propose the Visual Implicit Knowledge Distillation Framework (VIKDF)

IEEE 802.11–2016 proposed the Wi-Fi Fine Time Measurement (FTM) protocol, aiming at providing meter or sub-meter level ranging function between smart terminals and Wi-Fi access points (APs). Compared with other indoor positioning technologies for instance, Bluetooth, acoustic, visible light, Ultra-wideband, etc., Wi-Fi has been characterized by low cost, no deployment, and potentially high positioning

To address spectral distortion and the loss of spatial detail information caused by full-resolution pansharpening, this study proposes an unsupervised method combining compressed sensing (CS) and a deeper attention-based network architecture (L-PNN), namely CSLP. First, in the compressed sensing module, we apply sparse theory for image compression and reconstruction to reduce detail loss and enhance

Deep neural networks enable a sentence to be transformed into different multimodalities such as a token sequence representation (a one-dimensional semantic representation) or a semantic plane (a two-dimensional semantic representation). Sequence representation has the advantage of learning sequential dependencies of a sentence. Semantic plane is built by organizing all spans of a sentence, which is

Electronic Health Records (EHRs) have transformed healthcare by digitally consolidating patient medical history, encompassing structured data (e.g., demographic data, lab results), and unstructured textual data (e.g., clinical notes). These data hold significant potential for predictive modelling, and recent studies have dedicated efforts to leverage the different modalities in a cohesive and effective

Non-cooperative behaviors will lead to consensus failure in group decision making problems. As a result, managing non-cooperative behavior is a significant challenge in group consensus reaching processes, which involves two main research questions:(1) How to define non-cooperative behavior? (2) How to design an appropriate model to manage non-cooperative behavior? Existing studies often overlook the

Machine consciousness (MC) is the ultimate challenge to artificial intelligence. Although great progress has been made in artificial intelligence and robotics, consciousness is still an enigma and machines are far from having it. To clarify the concepts of consciousness and the research directions of machine consciousness, in this review, a comprehensive taxonomy for machine consciousness is proposed

Pansharpening is the task which reconstructs spatial–spectral properties during the fusion of high-resolution panchromatic (PAN) with low-resolution multi-spectral (LR-MS) images, to generate a high-resolution multi-spectral (HR-MS) image. Recent approaches typically model spatial and spectral properties and fuse them using end-to-end deep learning networks, which fail to take their crucial task-related

Accurate prediction of gas concentrations at longwall mining faces is critical for safety production, yet current methods still face challenges in interpretability and reliability. This study aims to enhance prediction accuracy and model interpretability by employing advanced feature selection techniques. We integrate Shapley Additive Explanations (SHAP) into feature selection process to identify and

Accurate traffic forecasting is the foundation of the intelligent transportation system (ITS). Among existing methods, researchers utilize deep neural networks to capture spatial–temporal correlations. While state-of-the-art methods have shown remarkable progress, they still have some limitations: (i) Most existing models struggle to make accurate prediction performance over longer time horizons due

Precise and timely disease diagnosis is essential for making effective treatment decisions and halting disease progression. Biomedical signals offer the potential for non-invasive diagnosis of diverse conditions, enhancing the ability to predict clinical outcomes and plan treatments more effectively. These signals have garnered significant attention, particularly in +conjunction with artificial intelligence

In multi-label feature selection (MLFS), pseudo-label learning techniques are often employed to mitigate the issue that the binary nature of ground-truth labels is incompatible with linear mappings. Existing studies have demonstrated that manifold learning and distance discrepancy are powerful facilities to well constrain pseudo-labels. However, there are still two weaknesses for the existing manifold

Emotion recognition in textual data is a rapidly evolving field with diverse applications. While the state-of-the-art (SOTA) models based on pre-trained large language models (LLMs) have demonstrated significant achievements, the existing approaches often overlook fine-grained emotional nuances within individual sentences and the influence of contextual information. Additionally, despite the growing

When light propagates through water, absorption and scattering effects lead to uneven brightness distribution and significant color deviation in underwater images. Existing methods struggle to compensate for light attenuation at each wavelength while simultaneously balancing luminance variations across different regions. To address these challenges, we propose the Luminance-Guided Transformer (LGT)

Existing multi-agent reinforcement learning (MARL) algorithms focus primarily on maximizing global game gains or encouraging cooperation between agents, often overlooking the weak ties between them. In multi-agent environments, the quality of the information exchanged is crucial for optimal policy learning. To this end, we propose a novel MARL framework that integrates weak-tie theory with graph modeling

Machine learning has contributed to the advancement of maintenance in many industries, including aviation. In recent years, many neural network models have been proposed to address the problems of failure identification and estimating the remaining useful life (RUL). Nevertheless, the black-box nature of neural networks often limits their transparency and interpretability. Interpretability (or explainability)

Traditional banks are increasingly challenged by FinTechs, particularly in leveraging advanced technologies to enhance operational efficiency. Our study addresses this by focusing on improving the efficiency of document-intensive business processes in banking. We review the landscape of business documents in the customer banking segment, which often includes text, layout, and visuals, indicating that

Repetition counting of multiple actions in sensor-based data is a critical task for human-centric applications like health monitoring and exercise training. Existing sensor-based repetition counting (SRC) methods are limited to single-action scenarios and predefined categories, which do not scale well in real-world scenarios. To address this, we introduce the Open Sensor Sequences Counting (OSSC) task

Multi-focus image fusion (MFIF) aims to generate an all-in-focus image from multiple partially focused images of the same scene captured with different focal settings. In this paper, we present a coupled convolutional sparse representation (CCSR) model for MFIF. Instead of being solved by an iterative thresholding algorithm, the proposed CCSR model is unfolded into a learnable neural network (termed

An affective brain-computer interface (aBCI) has demonstrated great potential in the field of emotion recognition. However, existing aBCI models encounter significant challenges in explainability and the effective fusion of multi-frequency and multi-region features, which greatly limits their practical applicability. To address these issues, this paper proposes an explainable multi-frequency and multi-region

The integration of multimodal capabilities into large models has unlocked unprecedented potential for tasks that involve understanding and generating diverse data modalities, including text, images, and audio. However, despite these advancements, such systems often suffer from hallucinations, that is, inaccurate, irrelevant, or entirely fabricated contents, which raise significant concerns about their