Search

Thermal imaging detection has been applied in many scenarios. However, its security has not been fully explored. We propose a physical attack method with small bulbs on a board to fool thermal imaging pedestrian detectors. We first designed an optimized Gaussian-function-based patch that caused the average precision (AP) of YOLOv3 to drop by 64.12% in the digital world, while a patch with randomly placed Gaussian functions and a blank patch caused the AP to drop by only 33.01% and 29.69%, respectively. We then manufactured a physical board and attacked YOLOv3 in the real world. In recorded videos, an optimized physical board caused the AP of YOLOv3 to drop by 34.48%, while a board with randomly placed bulbs and a blank board caused the AP to drop by only 17.06% and 14.91%, respectively. With the ensemble attack techniques, the designed physical board attack had good transferability to unseen CNN-based detectors. Furthermore, we successfully evaded the pedestrian detectors working on both visible light images and thermal images by covering printed adversarial paper on the manufactured board. Finally, we tested five typical methods to defend our bulb-based attack but achieved limited success. The results indicated the effectiveness of the attack method. [ABSTRACT FROM AUTHOR]

Steganography and steganalysis are two interrelated aspects of the field of information security. Steganography seeks to conceal communications, whereas steganalysis aims to discover or, if possible, recover the data they contain. These two areas have garnered significant interest, especially among law enforcement agencies. Cybercriminals and even terrorists often employ steganography to avoid detection while in possession of incriminating evidence, even when that evidence is encrypted, since cryptography is prohibited or restricted in many countries. Therefore, a deep understanding of cutting-edge techniques for uncovering concealed information is essential in exposing illegal activities. Over the last few years, a number of strong and reliable steganography and steganalysis techniques have been introduced in the literature. This review paper provides a comprehensive overview of deep learning-based steganalysis techniques used to detect hidden information within digital media. The paper covers all types of cover in steganalysis, including image, audio, and video, and discusses the most commonly used deep learning techniques. In addition, the paper explores the use of more advanced deep learning techniques, such as deep transfer learning (DTL) and deep reinforcement learning (DRL), to enhance the performance of steganalysis systems. The paper provides a systematic review of recent research in the field, including data sets and evaluation metrics used in recent studies. It also presents a detailed analysis of DTL-based steganalysis approaches and their performance on different data sets. The review concludes with a discussion on the current state of deep learning-based steganalysis, challenges, and future research directions. • Detect covert messages through neural nets, enhancing steganalysis accuracy. • Steganalysis can benefit from auto-encoders, DNN, CNN, RNN, LSTM, GNN, DBN, and DRN. • Reinforcement learning, transfer learning, and adversarial-based methods are effective to steganalysis. • Transform domain, attention layer, and noise-based features empower steganalysis schemes. • Unsupervised learning extracts nuanced patterns from multimedia for detection. [ABSTRACT FROM AUTHOR]

Low computational cost artificial intelligence (AI) models are vital in promoting the accessibility of real-time medical services in underdeveloped areas. The recent Once-For-All (OFA) network (without retraining) can directly produce a set of sub-network designs with Progressive Shrinking (PS) algorithm; however, the training resource and time inefficiency downfalls are apparent in this method. In this paper, we propose a new OFA training algorithm, namely the Progressive Expansion (ProX) to train the medical image analysis model. It is a reversed paradigm to PS, where technically we train the OFA network from the minimum configuration and gradually expand the training to support larger configurations. Empirical results showed that the proposed paradigm could reduce training time up to 68%; while still being able to produce sub-networks that have either similar or better accuracy compared to those trained with OFA-PS on ROCT (classification), BRATS and Hippocampus (3D-segmentation) public medical datasets. The code implementation for this paper is accessible at: https://github.com/shin-wl/ProX-OFA. [ABSTRACT FROM AUTHOR]

In this paper, the exponential synchronization in mean square (ESMS) of complex networks (CNs) under intermittent dynamic event-triggered control strategy (IE-TCS) is discussed. Compared with the existing literature, the intermittent control strategy (ICS) proposed is awakened when a certain situation occurs rather than periodically, which can better improve the control efficiency. The average control rate in this paper is more flexible. Furthermore, we give a positive lower bound for the event-triggered intervals to ensure that Zeno behavior does not occur. Combining the graph-theoretic approach with the Lyapunov method, some criteria for ESMS are obtained. In particular, we also discuss the ESMS of non-strongly connected CNs under IE-TCS. Besides, we combine the self-triggered control strategy (S-TCS) with the ICS, which is called the intermittent S-TCS, to study the ESMS of CNs. For practicability, the theoretical results are applied to research the ESMS of the microgrid system, and some relevant sufficient conditions are derived. Eventually, numerical simulations are put forward to verify the effectiveness of theoretical results. [ABSTRACT FROM AUTHOR]

This paper introduces a novel feature selection method, called Feature Selection based on Importance Measures (FS-IM), to enhance the forecasting of crude oil returns. FS-IM innovatively combines active learning with the application of Gaussian noise to input features and selects the most relevant features using an optimal threshold value. The paper applies a ridge regression (RR) model based on FS-IM (FS-RR) to identify the factors that have important information for crude oil return forecasting. The paper compares FS-IM with other dimension reduction methods such as Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), and Independent Component Analysis (ICA). The results show that FS-IM can significantly improve model accuracy, demonstrating its effectiveness in finding key features. Moreover, FS-IM is more stable and consistent than other dimension reduction methods in enhancing the prediction accuracy in different scenarios, indicating its superior capability in capturing complex relationships between input and output variables. Furthermore, this study compares FS-RR model with other 13 prediction models by conducting experiments using a series of evaluation metrics, different statistical tests, and different step-ahead predictions and training sets. The results confirm that the RR model based on FS-IM can consistently outperform other model in terms of predictive performance and economic value, proving its effectiveness and robustness. This study contributes to the literature on crude oil price forecasting by addressing the challenges of high-dimensional and complex data, and by providing a robust, practical tool for professionals in energy economics and finance. • A new feature selection method for crude oil forecasting using importance scores and Gaussian noise is proposed. • The method selects the most relevant features based on the prediction errors of a base forecasting model. • The method enhances the accuracy and value of ridge regression model compared to other methods. • The method handles high-dimensional and complex data without losing information or interpretability. [ABSTRACT FROM AUTHOR]

In personal identity recognition systems, detecting a person's age, gender, and language using voice signal characteristics is a crucial issue, especially because of the importance of security considerations. Age, gender, and language classification problems are important in signal processing because they are used to analyze and understand human behavior, interactions, and preferences. This can be especially useful in the fields of human-computer interaction, psychology, and social science research. In this paper, a new system for detecting a speaker's age, gender, and language based on deep learning models is presented. Deep learning models have shown great efficacy in various fields of signal processing. For this paper, a range of deep models were tested, including convolutional neural networks (CNNs), recurrent neural network (RNN), and a fine-tuning ResNet34 architecture. Additionally, techniques such as transfer learning were applied to improve the efficiency of the proposed system. The input voice signals are preprocessed by applying the spectro-temporal transform to obtain additional features that can be fed to the ResNet34 model, which is designed specifically for the task of voice signal processing. The dataset used in this paper was sourced from the Mozilla common voice initiative, which is dedicated to advancing speech recognition and language identification technologies. The performance of the proposed algorithm was evaluated in the presence of Gaussian noise to determine its robustness. The experimental results demonstrated that the proposed algorithm significantly outperformed basic algorithms and other deep neural networks in terms of age and gender recognition from voice signals. [ABSTRACT FROM AUTHOR]

This paper proposes a super-resolution algorithm for reconstructing license plate images based on generative adversarial networks (GAN) for improving the recognition rate of low-resolution license plate images. To this end, this paper first designs a new image degradation model, called the n-stage random combination degradation model (n-RCD), which extends the traditional degradation model horizontally and vertically to better simulate the features of low-resolution license plate images in natural scenes. Subsequently, to address the problem that existing GAN models cannot adapt to the complex degradation space in natural scenes, this paper proposes a new network structure called LPSRGAN, which optimizes the SRGAN model from the generator and discriminator to improve its super-resolution capability. In addition, this paper also proposes a perceptual optical character recognition (OCR) loss for license plate images, which defines the connectionist temporal classification (CTC) loss of the output of the OCR network with character label values to better preserve the character details and features of the license plate images. Finally, the experiments reported in this paper show that the proposed algorithm improves the recognition rate of the original low-resolution license plate image by 12.48%, and the recognition rate of the reconstructed image reaches 93.90%. Based on this, this paper also tests the algorithm on actual captured data, and the results show that it performs well in natural scenes, demonstrating the algorithm has broad application prospects. • A novel image degradation model called n-RCD has been designed. • A powerful license plate image super-resolution algorithm, LPSRGAN, is designed. • A downstream task-based perceptual OCR loss is introduced for license plate images. [ABSTRACT FROM AUTHOR]

This paper develops a novel online nearly optimal control (ONOC) method for unknown continuous-time (CT) nonaffine nonlinear systems without recovering unknown systems. First, a dynamic control law is proposed for CT nonaffine nonlinear systems using parallel control. To achieve the proposed dynamic control law, an affine augmented system (AAS) is constructed according to the original system, and an augmented performance index (API) is constructed on the basis of the original performance index (OPI). Then, the stability relationship between the original system and the AAS is provided, and it is proven that, by selecting a suitable parameter in the API, optimal control of the AAS with the API is equivalent to near-optimal control of the original system with the OPI. Subsequently, based on the proposed dynamic control law, we extend integral reinforcement learning (IRL) to completely unknown CT nonaffine systems, and it is further proved that closed-loop signals are uniformly ultimately bounded (UUB) without the assumption that the input dynamics are bounded. Furthermore, the OPI can be set to an arbitrary positive-definite form, and the UUB bound for the state vector can be predetermined. Lastly, simulations are offered to exhibit the correctness of the developed ONOC method. Source code of this paper is available at: https://github.com/lujingweihh/Adaptive-dynamic-programming-algorithms/tree/main/model_free_integral_reinforcement_learning. [ABSTRACT FROM AUTHOR]

Dialogue Machine Reading Comprehension requires language models to effectively decouple and model multi-turn dialogue passages. As a dialogue development goes after the intentions of participants, its topic may not remain constant throughout the whole passage. Hence, it is non-trivial to detect and leverage the topic shift in dialogue modeling. Topic modeling, although has been widely studied in plain text, deserves far more utilization in dialogue reading comprehension. This paper proposes to model multi-turn dialogues from a topic-aware perspective. This paper starts with a dialogue segmentation algorithm to split a dialogue passage into topic-concentrated fragments in an unsupervised way. Then these fragments are used as topic-aware language processing units in further dialogue comprehension. On one hand, the split segments indict specific topics rather than mixed intentions, thus showing convenience on in-domain topic detection and location. For this task, this paper designs a clustering system with a self-training auto-encoder, and two constructed datasets are built for evaluation. On the other hand, the split segments are an appropriate element of multi-turn dialogue response selection. For this purpose, this paper further presents a novel model, Topic-Aware Dual-Attention Matching (TADAM) Network, which takes topic segments as processing elements and matches response candidates with a dual cross-attention. Empirical studies on three public benchmarks show great improvements over baselines. Our work continues the previous studies on document topic, and brings the dialogue modeling to a novel topic-aware perspective with exhaustive experiments and analyses. [ABSTRACT FROM AUTHOR]

This paper is devoted to the multistability problem for complex-valued recurrent neural networks (CVRNNs) with a specific class of piecewise nonlinear activation functions. Firstly, a general class of piecewise nonlinear activation functions is presented to facilitate further analysis. Then, by resorting to the fixed point theorem and Lagrange's mean value theorem, sufficient criteria are established which ascertain that the existence of (2 k + 1) 2 n equilibrium points. Meanwhile, it also verifies that (k + 1) 2 n equilibrium points of the considered CVRNNs with a piecewise nonlinear activation function are stable, where k stands for a positive real number, which is associated with the frequency of sine and cosine functions. Moreover, the utilization of the activation functions provides a larger storage capacity in associative memory application. In the end of paper, three numerical examples are presented to demonstrate the feasibility and validity of the achieved theoretical results. [ABSTRACT FROM AUTHOR]

In March 2020, the World Health Organization (WHO) declared COVID-19 a global epidemic, caused by the SARS-CoV-2 virus. Initially, COVID-19 was diagnosed using real-time reverse transcription–polymerase chain reaction (RT-PCR) tests with a turnaround time of 2–3 days. To enhance diagnostic accuracy, medical professionals use medical imaging alongside RT-PCR. A positive result on both RT-PCR and medical imaging confirms a COVID-19 diagnosis. Imaging modalities like chest X-ray (CXR), computed tomography (CT) scans, and ultrasound are widely utilized for rapid and precise COVID-19 diagnoses. However, interpreting COVID-19 from these images is time-consuming and susceptible to human error. Therefore, leveraging artificial intelligence (AI) methods, particularly deep learning (DL) models, can deliver consistent, high-performance results. Unlike conventional machine learning (ML), DL models automate all stages of feature extraction, selection, and classification. This paper presents a comprehensive review of using DL techniques for diagnosing COVID-19 from medical imaging. The introduction provides an overview of diagnosing the coronavirus using medical imaging, highlighting associated challenges. Subsequently, the paper delves into key aspects of Computer-Aided Diagnosis Systems (CADS) based on DL methods for diagnosing COVID-19, covering segmentation, classification, explainable AI (XAI), and predictive research. Additionally, it reviews the rehabilitation systems such as the Internet of Medical Things (IoMT) in the context of COVID-19. In another section, uncertainty quantification (UQ) research is showcased, focusing on DL models for the diagnosis of Covid-19. Crucial challenges and future research directions are outlined in another section. Finally, discussion and conclusion sections are also provided at the end of the paper. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has been shown to be very effective for many application domains of machine learning (ML), including image classification, voice recognition, natural language processing, and bioinformatics. The success of DL techniques is directly related to the availability of large amounts of training data. However, in many cases, the data are sensitive to the users and should be protected to preserve the privacy. Privacy-preserving deep learning (PPDL) has thus become a very active research field to ensure the training process and use of DL models are productive without exposing or leaking information about the data. This paper aims to provide a comprehensive survey of PPDL. We concentrate on the risks that affect data privacy in DL and conduct a detailed investigation into the models that ensure privacy. Finally, we propose a set of evaluation criteria, detailing the advantages and disadvantages of the solutions. Based on the analyzed strengths and weaknesses, the paper has highlighted some important research problems and application cases that have not been studied and these point to certain open research directions. [ABSTRACT FROM AUTHOR]

This paper primarily addresses the problems of passivity and robust passivity of impulsive inertial neural networks (IINNs) with proportional delays. By constructing the Lyapunov functional directly on the original system using the non-reduced order approach, some passivity and robust passivity criteria for IINNs are addressed. In comparison with the order reduction method utilized in the existing articles, the non-reduced order method is more in line with real requirements and can better analyze the dynamic behavior of inertial neural networks (INNs). Meanwhile, the results in this paper are all in algebraic form, which are easy to verify. To demonstrate the effectiveness of the results derived, numerical examples are presented at the end. [ABSTRACT FROM AUTHOR]

Zero-shot relational triplet extraction is a vital solution to the problem of fact extracted from unstructured text without labeled training data. In the task, the data is divided into seen and unseen relations for training and prediction, respectively. A strategy that trains a generative model based on seen data first and generates training samples for unseen data has been shown to be effective in solving this task. However, this strategy is severely limited by error propagation caused by generated noisy data. To address this issue, prompts may provide a feasible route since they have been widely utilized in cross-domain tasks. In this paper, three preliminary experiments reveal the effectiveness of prompts for the task of triplet extraction and its internal mechanism. Specifically, the method using prompts can control the domain. 1 1 The term is quite loosely used in NLP. In this paper, domain is used to represent which relations may be associated with the given sentence. For more detailed information, please refer to Appendix A. Further, we propose a simple but effective model for zero-shot relational triplet extraction, which leverages zero-shot text classification to first determine the prompts of unseen relations aiming to optimize both its domain and length, and then extracts triplets via prompt-driven strategy. Extensive experiments are conducted on two public datasets, demonstrating that the proposed model achieves a better performance than baselines. • Prompts are able to control the output domain, guiding the extraction of unseen triplets. • Potential relations can be determined according to semantic matching between sentences and relation description text. • A two-stage framework is proposed to effectively improve the performance of zero-shot relational triplet extraction task. [ABSTRACT FROM AUTHOR]

This paper considers the multi-label thoracic abnormality classification with chest X-ray images. In clinical settings, Chest X-ray imaging is a general diagnostic tool applied to visualize numerous thoracic pathological changes. While deep learning techniques have been extensively tested in this field, certain challenges persist. The data in existing thoracic abnormality datasets is insufficient, and some diseases are extremely imbalanced. Meanwhile, the dependencies between different labels are often ignored. To tackle these issues head-on, this paper introduces two crucial modules: the group-wise spatial attention (GWSA) module and the label co-occurrence dependency (LCD) module, integrated with DenseNet121 backbone. Specifically, GWSA enhances the spatial features within distinct groups while keeping the between-group feature discrimination. LCD models the correlations between different thoracic abnormalities to refine the predicted probabilities. In conjunction with the DenseNet121 backbone, these two modules reach an average AUC score of 0.818 on Chest X-ray14 dataset, achieving state-of-the-art. Source code is available at https://github.com/YujiaKCL/Chest-Xray14-GWSA-LCD. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) has emerged as a powerful paradigm for training Machine Learning (ML), particularly Deep Learning (DL) models on multiple devices or servers while maintaining data localized at owners' sites. Without centralizing data, FL holds promise for scenarios where data integrity, privacy and security and are critical. However, this decentralized training process also opens up new avenues for opponents to launch unique attacks, where it has been becoming an urgent need to understand the vulnerabilities and corresponding defense mechanisms from a learning algorithm perspective. This review paper takes a comprehensive look at malicious attacks against FL, categorizing them from new perspectives on attack origins and targets, and providing insights into their methodology and impact. In this survey, we focus on threat models targeting the learning process of FL systems. Based on the source and target of the attack, we categorize existing threat models into four types, Data to Model (D2M), Model to Data (M2D), Model to Model (M2M) and composite attacks. For each attack type, we discuss the defense strategies proposed, highlighting their effectiveness, assumptions and potential areas for improvement. Defense strategies have evolved from using a singular metric to excluding malicious clients, to employing a multifaceted approach examining client models at various phases. In this survey paper, our research indicates that the to-learn data, the learning gradients, and the learned model at different stages all can be manipulated to initiate malicious attacks that range from undermining model performance, reconstructing private local data, and to inserting backdoors. We have also seen these threat are becoming more insidious. While earlier studies typically amplified malicious gradients, recent endeavors subtly alter the least significant weights in local models to bypass defense measures. This literature review provides a holistic understanding of the current FL threat landscape and highlights the importance of developing robust, efficient, and privacy-preserving defenses to ensure the safe and trusted adoption of FL in real-world applications. The categorized bibliography can be found at: https://github.com/Rand2AI/Awesome-Vulnerability-of-Federated-Learning. [ABSTRACT FROM AUTHOR]

This paper focuses on the distributed online optimization problem in multi-agent systems considering privacy preservation. Each agent exchanges local information with neighboring agents on the strongly connected time-varying directed graphs. Since the process of information transmission is prone to information leakage, a distributed push-sum dual averaging algorithm based on the differential privacy mechanism is proposed to protect the privacy of the data. In addition, to handle situations where the gradient information of the node cost function is unknown, the one-point gradient estimation is designed to calculate the true gradient information and guide the update of the decision variables. With the appropriate choice of the stepsizes and the exploration parameters, the algorithm can effectively protect the privacy of agents while achieving sublinear regret with the convergence rate O (T 3 4 ). Furthermore, this paper also explores the effect of one-point estimation parameters on the regret in the online setting and investigates the relation between the convergence effect of individual regret and differential privacy levels. Finally, several federated learning experiments were conducted to verify the efficacy of the algorithm. [ABSTRACT FROM AUTHOR]

With the increasing data size of multi classification problems, the running efficiency of classical algorithms is seriously affected. In the paper, in order to improve the implementation efficiency of the algorithm, we propose a quantum-enhanced solution method for multi classification problems. The method mainly introduces the quantum-enhanced technology into the classical algorithm. Aiming at the two steps of solving Euclid distance and kernel function in the classical algorithm, the paper relates the classical inner product principle with the amplitude evolution of quantum states. On the basis of quantizing the sample data, a general quantum circuit that can calculate the inner product is designed and constructed. The circuit can make full use of the advantages of quantum parallel computing to achieve exponential acceleration of computing efficiency. Aiming at solving linear equations in the classical algorithm, a quantum circuit based on the quantum singular value estimation is designed and constructed. The circuit makes use of the acceleration advantage of quantum computing in matrix computing to achieve polynomial acceleration of matrix computing. The experimental results show that the method can not only find the optimal solution for multi classification problems, but also greatly improve the operation efficiency of the algorithm. Compared with the classical methods, the method has at least polynomial improvement in time complexity and spatial complexity. [ABSTRACT FROM AUTHOR]

In numerous domains, there is ample evidence indicating that a significant portion of real-world data exhibits temporal variations, such as medical research and meteorological studies. Particularly in the era of big data, not only does the size of data change dynamically but also its dimensions at an unprecedented pace. Consequently, employing traditional methods to handle such dynamic data becomes highly impractical. To address this limitation, this paper proposes an incremental feature selection algorithm tailored for dynamic feature variations. For scenarios involving an increase in features, the novel algorithm efficiently identifies a target subset with effective features. In order to showcase the efficacy of the proposed algorithm, this paper conduct experiments using four commonly used classifiers and five UCI data sets. The experimental results further validate both the feasibility and efficiency of the new approach. [ABSTRACT FROM AUTHOR]

In this paper, for the multi-agent system, the Nash equilibrium (NE) search problem for non-cooperative game with state constraints under false data injection (FDI) attack is studied. The FDI attack can directly destroy the connectivity between agents, resulting in the performance degradation or even failure for most NE search algorithms. We propose a new distributed NE search method to improve the performance of NE algorithms under FDI attacks. The NE algorithm is designed to find the solution of NE under network attack and make the system recover after the attack. However, most of the existing results only studied the NE algorithm of the non-attacking system, and the existing results rarely take into account whether the system state exceeds the safety limit, which can cause the system to crash. This paper solves the state constraints problem of the multi-agent game under the FDI attack. Finally, the reliability of the algorithm is verified by a numerical result. [ABSTRACT FROM AUTHOR]

This paper focuses on the problem of input-to-state stability (ISS) of stochastic complex networks (SCNs). In this paper, an aperiodically intermittent control strategy based on sampled control is designed. By means of graph theory and Lyapunov method, two stability criteria on ISS are derived in this paper. After giving the estimate between E ∑ i = 1 m | x i (t) − x i (δ (t)) | 2 and E ∑ i = 1 m | x i (t) | 2 , a stability criterion is proposed on ISS of the SCN under aperiodically intermittent sampled control (AISC). When AISC degenerates into sampled control, another stability criterion on ISS of SCN is acquired. Finally, a numerical example is utilized to illustrate the effectiveness and feasibility of the proposed results. [ABSTRACT FROM AUTHOR]

Every day, enormous amounts of biomedical texts discussing various biomedical topics are produced. Revealing strong semantic connections hidden in those unstructured data is essential for many interesting applications such as knowledge base development for the biomedical domain as well as drug repurposing and drug–disease associations. Literature based discovery (LBD) is a well-known paradigm that refers to the issues of finding new hidden knowledge in scientific literature by connecting pieces of semantically-related information belonging to independent documents. This challenging research area has been extensively investigated by the research community and different proposals adopting natural language processing, text mining, machine learning and recently deep learning have been developed. This paper exploits a very focused task, it surveys a collection of research papers published in the recent years that have adopted Deep Learning for literature based discovery as an effective technique to discover new relationships between existing knowledge in biomedical domain. The study provides an analysis of the key characteristics of each work surveyed, including the Literature based discovery application area, the deep learning method used, the type of analyzed data, and the results obtained. Recognizing the significance of Pre-trained Language Models (PLMs), another primary aim of this paper is to offer an extensive overview of the latest developments in pre-trained language models within the field of biomedicine. This focus will primarily be on how they are applied to downstream tasks associated with Literature-Based Discovery in the biomedical domain. Additionally, the survey highlights the key drawbacks of the current state-of-the-art proposals, as well as the challenges that require further study by the research community. [ABSTRACT FROM AUTHOR]

Recent deep learning models have exhibited impressive performance in the area of 3D skull landmark detection, but most of them aimed to detect a fixed number of landmarks. This paper focuses on automatically detecting an arbitrary number of landmarks on CT volumes, which meets the real clinical needs. To achieve robust performance for detecting arbitrary molar landmarks, we propose a novel 3D landmark detection model named Anchor Ball Regression Model (ABRM), which combines landmark detection and landmark classification losses for network training. For landmark detection, a novel landmark regression loss is proposed by predicting offsets to anchor balls instead of directly predicting landmarks. For landmark classification, an online hard negative mining loss is used to reduce absent landmarks' learning errors, and a small regularization constraint loss is performed for voxels outside the anchor balls. The network backbone of ABRM is obtained by manually pruning popular 3D-CNNs. We also present an available large-scale benchmark dataset in this paper, which, to the best of our knowledge, is the largest dataset for 3D skull landmark detection. The dataset comprises of 658 CT volumes, with 14 landmarks labeled by two junior and one senior doctors. The ABRM presents a good robust performance and outperforms other models on this dataset. The codes and dataset are accessible at https://github.com/ithet1007/mmld_code. [ABSTRACT FROM AUTHOR]

Deep learning techniques have led to remarkable breakthroughs in the field of object detection and have spawned a lot of scene-understanding tasks in recent years. Scene graph has been the focus of research because of its powerful semantic representation and applications to scene understanding. Scene Graph Generation (SGG) refers to the task of automatically mapping an image or a video into a semantic structural scene graph, which requires the correct labeling of detected objects and their relationships. In this paper, a comprehensive survey of recent achievements is provided. This survey attempts to connect and systematize the existing visual relationship detection methods, to summarize, and interpret the mechanisms and the strategies of SGG in a comprehensive way. Deep discussions about current existing problems and future research directions are given at last. This survey will help readers to develop a better understanding of the current researches. [Display omitted] • A comprehensive review of 138 papers on scene graph generation is presented. • We analyze 2D scene graph generation, focusing on feature representation. • A review of typical datasets for 2D, spatio-temporal and 3D scene graph generation is presented. [ABSTRACT FROM AUTHOR]

Camouflaged object detection (COD) aims to search and identify disguised objects that are hidden in their surrounding environment, thereby deceiving the human visual system. As an interesting and challenging task, COD has received increasing attention from the community in the past few years, especially for image-level camouflaged object segmentation task. So far, some advanced image-level COD models have been proposed, mainly dominated by deep learning-based solutions. To have an in-depth understanding of existing image-level COD methods in the deep learning era, in this paper, we give a comprehensive review on model structure and paradigm classification, public benchmark datasets, evaluation metrics, model performance benchmark, and potential future development directions. Specifically, we first review 96 existing deep COD algorithms. Subsequently, we summarize and analyze the existing five widely used COD datasets and evaluation metrics. Furthermore, we benchmark a set of representative models and provide a detailed analysis of the comparison results from both quantitative and qualitative perspectives. Moreover, we further discuss the challenges of COD and the corresponding solutions. Finally, based on the understanding of this field, future development trends and potential research directions are prospected. In conclusion, the purpose of this paper is to provide researchers with a review of the latest COD methods, increase their understanding of COD research, and gain some enlightenment. [ABSTRACT FROM AUTHOR]

With the enhancement of people's security awareness, transmitting secret information securely has gradually become a demand for the public. Steganography is a technology of representing secret information within another carrier, aiming at transmitting secret information without causing suspicion. Most of the traditional steganographic algorithms hide secret information by modifying the statistical characteristics, which will leave traces to the carriers. Although these modifications are too tiny to be distinguished by human eyes, they can be detected by steganalysis algorithms. Differently, coverless steganography, also written as steganography without embedding, accomplish the process of information hiding by constructing the relationship between secret information and carriers. Due to no modification to the carriers, all of the steganalysis algorithms are expired. In this paper, more than 90 papers are included to provide a review in coverless steganographic algorithms, covering the major development process of coverless image and video steganographic algorithms. The main contribution of the existing methods is summarized. Besides, the current general issues of capacity, robustness, and security are discussed adequately for both image and video algorithms. Especially, the security of coverless steganography is discussed for the first time from theoretical analysis to actual investigation in this review. [ABSTRACT FROM AUTHOR]

Integrating Internet of Things (IoT) technologies in the healthcare industry represents a transformative shift with tangible benefits. This paper provides a detailed examination of IoT adoption in healthcare, focusing on specific sensor types and communication methods. It underscores successful real-world applications, including remote patient monitoring, individualized treatment strategies, and streamlined healthcare delivery. Furthermore, it delves into the intricate challenges to realizing the full potential of IoT in healthcare. This includes addressing data security concerns, ensuring seamless interoperability, and optimizing the use of IoT-generated data. The paper seeks to inspire practitioners and researchers by highlighting the practical implications of IoT in healthcare, emphasizing the ways IoT can enhance patient care, resource allocation, and overall healthcare efficiency. • More than 103 references from top journals are analyzed. • A systematic theoretical analysis of IoT applications in healthcare is provided. • General works on IoT applications in healthcare are well summarized. • Future challenges of IoT applications in healthcare are analyzed from several standpoints. [ABSTRACT FROM AUTHOR]

Quantization methods for convolutional neural network models can be broadly categorized into post-training quantization (PTQ) and quantization aware training (QAT). While PTQ offers the advantage of requiring only a small portion of the data for quantization, the resulting quantized model may not be as effective as QAT. To address this limitation, this paper proposes a novel quantization function named Attention Round. Unlike traditional quantization function that map 32 bit floating-point value w to nearby quantization levels, Attention Round allows w to be mapped to all possible quantization levels in the entire quantization space, expanding the quantization optimization space. The possibilities of mapping w to different quantization levels are inversely correlated with the distance between w and the quantization levels, regulated by a Gaussian decay function. Furthermore, to tackle the challenge of mixed precision quantization, this paper introduces a lossy coding length measure to assign quantization precision to different layers of the model, eliminating the need for solving a combinatorial optimization problem. Experimental evaluations on various models demonstrate the effectiveness of the proposed method. Notably, for ResNet18 and MobileNetV2, the PTQ approach achieves comparable quantization performance to QAT while utilizing only 1024 training data and 10 min for the quantization process. • Attention Round quantization function expands the quantization optimization space. • Mixed precision allocation method improves mixed precision quantization efficiency. • Enriched lightweight CNNs contribute to applications in resource-limited scenarios. [ABSTRACT FROM AUTHOR]

The complexity of reality has driven the evolution of Fuzzy-Set Theory from the initial proposal made by Zadeh in 1965, towards more complex models. Moving from a quick survey of the evolution of Fuzzy-Set Theory, this paper highlights the aspects that are common to many Fuzzy-Set Models, in order to define a meta-model that is capable of providing a unified view to a wide variety of fuzzy-set models. In particular, this work focuses the attention on the family of "Multi-grade Fuzzy Sets", which are fuzzy sets characterized by more than one degree. The lack of tools capable of querying the large amount of data that are nowadays available in NoSQL databases, has pushed us to devise the J-CO Framework: it is a platform-independent tool that is capable to manage, transform and query collections of JSON documents; the J-CO Framework relies on J-CO-QL + , which is a high-level, general-purpose language with soft-querying capabilities. The latest advancements of J-CO-QL + allow for defining and exploiting user-defined Multi-grade Fuzzy-Set Models and Operators. In the paper, a case-study demonstrates the effectiveness of the J-CO Framework in performing a non-trivial soft query based on a Multi-grade Fuzzy-Set Model defined by the user. [ABSTRACT FROM AUTHOR]

This paper studies the stabilization analysis problem of a class of incommensurate fractional-order memristor-based neural networks with multiple time-varying delays (IFOMNNs-MTDs). In previously published studies of IFOMNNs-MTDs, the controller is usually designed as a general delay-independent feedback controller. Due to the simple form of the feedback controller, less system information is used and less adjustable parameters are considered, which limits the flexibility and control effect of controller. Specially, the use of delay information is insufficient in the existing results, which will make the controller insensitive to the influence of delay factors and affect the control performance. Thereby, the accurate analysis of the dynamic characteristics of IFOMNNs-MTDs by designing appropriate controller needs further study. This paper aims to propose a new delay-dependent controller to improve the stabilization analysis of IFOMNNs-MTDs. Firstly, a delay-dependent distributed controller with distributed control gain and time-delay state summation term is proposed, which accords with the transmission law of activation function weights and is helpful to consider the historical information (i.e., time delay factors) of system. Thereby, the flexibility and control effect of controller are improved by adding control parameters and improving the use of system information. Secondly, a new less-conservatism stabilization criterion of IFOMNNs-MTDs is established by using the designed controller. Moreover, the controller gain can be searched in a large range by using the established criterion. Finally, a numerical simulation is provided to verify the validity of the obtained results. [ABSTRACT FROM AUTHOR]

In this paper, we present an event-triggered critic learning impedance control algorithm for a lower limb rehabilitation exoskeleton robot in an interactive environment, where the control objective is specified by a desired impedance model. In comparison to many other traditional impedance controller design algorithms, in this paper, the impedance control problem is transformed into an optimal control problem. Firstly, the interactive environment accounts for the interaction between the exoskeleton, the human, and the environment, and is modeled by a linear time-invariant exogenous system. Secondly, in contrast to time-triggered control design mechanisms, the event-triggered controller is updated only when the system states deviate from prescribed threshold values. To obtain the event-triggered optimal controller, a critic neural network is developed through the framework of reinforcement learning. A modified gradient descent method is introduced to update the weights of the critic network with an additional stable term employed to eliminate the need for an initial admissible control. Meanwhile, with the simultaneous application of historical and transient state data to the critic neural network, the persistent excitation conditions are relaxed. The Lyapunov method is used to rigorously demonstrate the stability of the overall system. Finally, the effectiveness of the proposed algorithm is demonstrated via simulation. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of analyzing the performance of 3D face alignment (3DFA), or facial landmark localization. This task is usually supervised, based on annotated datasets. Nevertheless, in the particular case of 3DFA, the annotation process is rarely error-free, which strongly biases the results. Alternatively, unsupervised performance analysis (UPA) is investigated. The core ingredient of the proposed methodology is the robust estimation of the rigid transformation between predicted landmarks and model landmarks. It is shown that the rigid mapping thus computed is affected neither by non-rigid facial deformations, due to variabilities in expression and in identity, nor by landmark localization errors, due to various perturbations. The guiding idea is to apply the estimated rotation, translation and scale to a set of predicted landmarks in order to map them onto a mathematical home for the shape embedded in these landmarks (including possible errors). UPA proceeds as follows: (i) 3D landmarks are extracted from a 2D face using the 3DFA method under investigation; (ii) these landmarks are rigidly mapped onto a canonical (frontal) pose, and (iii) a statistically-robust confidence score is computed for each landmark. This allows to assess whether the mapped landmarks lie inside (inliers) or outside (outliers) a confidence volume. An experimental evaluation protocol, that uses publicly available datasets and several 3DFA software packages associated with published articles, is described in detail. The results show that the proposed analysis is consistent with supervised metrics and that it can be used to measure the accuracy of both predicted landmarks and of automatically annotated 3DFA datasets, to detect errors and to eliminate them. Source code and supplemental materials for this paper are publicly available at https://team.inria.fr/robotlearn/upa3dfa/. [ABSTRACT FROM AUTHOR]

In the field of Transfer Learning, Source-Free Unsupervised Domain Adaptation (SFUDA) emerges as a practical and novel task that enables a pre-trained model to adapt to a new unlabeled domain without access to the original training data. The advancement of SFUDA has profoundly reshaped the algorithmic design of domain adaptation methods. Given the novelty and limited exploration of SFUDA, conducting a comprehensive survey is imperative to showcase methodological advancements, identify existing gaps, and uncover potential trends in this field. This paper provides an extensive review of SFUDA, encompassing methods and applications. First, based on the learning objectives during adaptation, different SFUDA methods fall into three categories: (i) Self-Tuning , (ii) Feature Alignment , and (iii) Sample Generation , with further sub-categorization within each category. Additionally, the strengths and limitations of each category are discussed, and various application areas where SFUDA can yield significant benefits are summarized. Finally, drawing from extensive observations and insights, potential future directions for SFUDA research are analyzed, with a focus on identifying emerging trends and key areas for further exploration. • A Comprehensive Review of SFUDA : The paper offers a review of SFUDA, to fill the gaps left by previous studies. • Critical Discussions on SFUDA : Based on the review, critical discussions are highlighted to deepen the understandings. • Future Directions for SFUDA : The paper outlines research directions for SFUDA, providing guidance to future advancements. [ABSTRACT FROM AUTHOR]

Intrusion detection technology can actively detect abnormal behaviors in the network and is important to the security of Industrial Internet of Things (IIOT). However, there are some issues with the current intrusion detection technology for IIOT, such as extreme imbalance in the number of samples of different classes in the dataset, redundant and meaningless features in the samples, and the inability of traditional intrusion detection methods to meet the requirements of detection accuracy in the increasingly complex IIOT. In view of the extreme imbalance of classes, this paper applies the hierarchical clustering algorithm to the under-sampling technology, which reduces the number of majority samples while reducing the loss of information of majority samples, and solves the problem of missing detection and false detection of minority samples caused by sample imbalance. In order to avoid feature redundancy and interference, this paper proposes an optimal feature selection algorithm based on greedy thought. This algorithm can obtain the optimal feature subset of each type of data in the data set, thus eliminating redundant and interfering features. Aiming at the problem of insufficient detection ability of traditional detection methods, this paper proposes a deep neural network intrusion detection model based on the parallel connection of global and local subnetworks. This model obtains the overall benchmark detection of the dataset through the deep neural network, and then strengthens the detection effect of each subclass through the parallel connection of subnetworks, greatly improving the performance of the intrusion detection algorithm. The experimental results show that the method described in this paper can improve the intrusion detection for IIOT. [ABSTRACT FROM AUTHOR]

This paper solves the practical consensus tracking control problem for networked Euler–Lagrange (EL) systems using the uncertainty and disturbance estimator (UDE) in combination with the radial basis function (RBF) neural network. An integrated consensus algorithm is proposed for the networked EL systems, where the RBF neural network is first utilized to generate online estimation of the uncertain EL dynamics for enhancing the system adaptability, and then the UDE is applied to compensate external disturbances dynamically for improving the system robustness. Furthermore, a unified analysis framework for the closed-loop control system is established through performing the proper filter design and Lyapunov-like analysis. The proposed consensus tracking algorithm possesses a simple system structure for implementation and has a good robust performance in dealing with both uncertainties and disturbances. Numerical simulations are used to verify the effectiveness of the developed integrated consensus scheme. [ABSTRACT FROM AUTHOR]

In this paper, a novel population robustness-based switching response framework (PR-SRF) is proposed to develop effective dynamic multi-objective optimization algorithm (DMOA), which integrates different response strategies to comprehensively cope with the dynamic behaviors. In particular, the population robustness is described by the quantification of how severely the environmental changes affect current population, which is timely graded as three levels of weak, strong, and normal to enable the adaptive switch of three different responses of diversity-enhancement, diversity-maintenance, and the knowledge-transfer, respectively. In this way, associations between the adopted responses and the changing environments are successfully established, thereby facilitating more intelligent decision when handling the dynamic behaviors. According to the benchmark evaluation results, the proposed PR-SRF-DMOA yields better comprehensive performance than several other DMOAs with popular response strategies, and it also outperforms another three DMOAs with hybrid responses, which demonstrates the great competitiveness of our algorithm. In addition, ablation study proves that the proposed PR-SRF can sufficiently exploit the merits of different responses, which effectively alleviates the negative knowledge transfer in extremely fluctuating environments, thereby providing valuable references for the development of evolutionary transfer optimization (ETO) algorithms. [ABSTRACT FROM AUTHOR]

The problem of class imbalance is prevalent in many real-world data sets, causing learning models to skew towards the majority class and resulting in biased performance. Data augmentation methods, such as the well-known Synthetic Minority Over-sampling Technique (SMOTE), are commonly employed to address class imbalance by generating synthetic samples. However, the generation mechanism of SMOTE is relatively constrained resulting in insufficient diversity in synthetic samples. To overcome this limitation, this paper expands the classical SMOTE and introduces a novel generalized version, namely Multi-vector Stochastic Exploration Oversampling (MSEO). It broadens the set of mapping synthetic samples, originally formed by the determined direction vectors and scaling vectors through the neighboring samples, to a collection obtained through mappings with random direction vectors and scaling vectors. This allows the generated samples to escape the original linear interpolation region, facilitating a more flexible exploration of the sample space. We extensively evaluated the method on various types of datasets, including artificially generated datasets, multi-class real-world datasets, and the engineering dataset. The results indicate that MSEO exhibits significant advantages in enhancing classification performance and promoting diversity in synthetic samples. [ABSTRACT FROM AUTHOR]

Referring image segmentation is guided by natural language descriptions to separate the target objects in an image. This task is different from semantic segmentation and instance segmentation in that it involves unique challenges such as multimodal information fusion, variability of natural language expressions, and model robustness. In recent years, the emergence of deep learning techniques has led to innovative ideas and methods for solving these problems. We systematically analyze the main challenges of referring image segmentation and summarize the existing solutions. These include strategies such as multimodal fusion, expression query, multimodal pre-training, and robustness. In addition, we provide an overview of several datasets commonly used in referring image segmentation and analyze the performance of various representative approaches in comparison to different datasets, visual backbone models and threshold settings. Our focus also extends to the challenges and future developments in the field of referring image segmentation. Our survey paper will provide a comprehensive technical reference for future researchers. • Examine the challenges associated with referring image segmentation and encapsulate the corresponding solutions. • Based on the constraints of current methods, scrutinize the avenues for further enhancements. • Summarise the existing findings to provide an important reference for future research. [ABSTRACT FROM AUTHOR]

Rumors circulating on social media platforms have consistently represented a substantial threat to societal security and stability. Both academia and the industry have dedicated heightened focus to addressing the issue of rumor detection. Recent research has made significant progress in using deep neural networks to model the textual content and propagation structure of rumors. However, these methods model rumor-related features at a coarse-grained level and do not take full advantage of the various contextual information associated with rumors. In this paper, we propose a new model called Hybrid Rumor Detection Model with Co-Attention Mechanisms(CoAHRD), which utilizes the original tweet content, social context information, and user information for rumor detection. First, we use the Fine-Grained Feature Learning(FGFL) algorithm to extract fine-grained features from the tweets. Based on this, we use the Graph Convolutional Network(GCN) to learn the Multi-relation graph propagation structure features of rumors. Next, we combine FGFL features with temporal encoding information to model the temporal structure of rumors. Then, we introduce a User Feature-Based Co-Attention Network(UFCoAN) to learn the tendency of different users to spread rumors. Finally, we fuse the above features through a fully connected layer and perform rumor detection. Extensive experiments on two publicly available datasets, PHEME and TWITTER15, show that our method outperforms the current mainstream methods. In particular, in terms of accuracy, our model improves by 0.9% and 1.6% over the best baseline method on the Twitter15 and PHEME datasets, respectively. • BERTWeet and saliency learning for fine-grained modelling of rumour text. • Using attention mechanisms to learn the temporal structure of rumours. • As a complementary task to rumour detection, segmentation of users into different groups using a user attention network. [ABSTRACT FROM AUTHOR]

The fusion of RGB and thermal data for dense prediction tasks has been demonstrated to be an effective and robust approach in autonomous driving. Nevertheless, the challenge lies in fusing features from different modalities, as a simple fusion strategy may lead to redundant or conflicting semantic information. In this paper, we delve into the hierarchical connections between multi-modal features and propose a novel fusion paradigm termed DHFNet, which decouples multi-modal features into similar global long-distance and discrepant local detail features for hierarchical feature fusion. At each fusion stage, a Lightweight Global Self-attention (LGSA) module is designed to decouple the global long-distance features with cheap computational complexity cost, and a Cross Modal Long-distance Feature Fusion (CMLFF) module is designed to eliminate redundant features by facilitating information interaction between different modalities. During the process of decoupling local detail features, a Cross Modal Deformable Convolution (CMDC) module is proposed to dynamically extract effective local features and capture misaligned features between different modalities. Finally, the fused global long-distance and local detail features are recoupled to achieve efficient hierarchical fusion. The results on RGB-T semantic segmentation and object detection tasks demonstrate the effectiveness of proposed method. The code will be available at: https://github.com/donggaomu/DHFNet. [ABSTRACT FROM AUTHOR]

Distributed optimization, combining cooperative control and optimization objectives, is vital for practical applications. While current research predominantly focuses on linear multi-agent systems, the real-world demands often involve nonlinear systems with finite or fixed time constraints. This paper addresses the finite-time/fixed-time distributed optimization for nonlinear multi-agent systems with time-varying cost function. Under appropriate assumptions, we propose a finite-time distributed protocol and a fixed-time distributed protocol for the nonlinear multi-agent systems to ensure all agents achieve consensus and minimize the time-varying cost function, relaxing the conditions for strong convexity and bounded gradient difference of the cost function. Simulation experiments validate the effectiveness of these distributed protocols. [ABSTRACT FROM AUTHOR]

Modeling the epistemic uncertainty, Bayesian convolutional neural networks (Bayesian-CNNs) place a probability distribution on the kernel of convolutional neural networks (CNNs) to overcome problems of over-fitting and incapability of quantifying the prediction confidence. However, compared with CNNs with point estimates, Bayesian-CNNs have a limited improvement over classification performance. Some experiments show that the closer to the input layer, the larger the variances of the parameters in those layers of Bayesian-CNNs, which means the parameters of the low-level layers are not well-trained. Therefore, it is possibly inappropriate to model the epistemic uncertainty of the parameters in the layers close to the input. In this paper, the question of "where to model the epistemic uncertainty of Bayesian-CNNs" is studied by analyzing the performances by putting randomness over different convolutional groups. For this unique structure by combining certain and uncertain layers, a novel objective function is proposed which consists of KL loss for the uncertain parameters and cross-entropy loss for certain parameters. For the special objective function, a training scheme that updates these two kinds of parameters alternately is proposed. Partial-Bayesian-CNNs (P-Bayesian-CNNs) that model the epistemic uncertainty over the parameters of the last convolutional group are recommended because they bring the highest classification accuracy gain according to the experimental analysis. Compared to the traditional Bayesian-CNNs, P-Bayesian-CNNs increase the accuracy by 3.8% and 3.7% on CIFAR-10 and RAF-DB respectively. Besides, the experimental results by taking Res2Net and Xception as backbones also show performance improvement, which verifies the scalability of the P-Bayesian-CNNs. • P-Bayesian-CNNs that only model the parameters of the last convolutional group can achieve the best accuracy. • A novel objective function is proposed for the P-Bayesian-CNNs by combining KL loss and the cross-entropy loss. • A training scheme is proposed for P-Bayesian-CNNs, which update two kinds of parameters alternately. [ABSTRACT FROM AUTHOR]

Cooperation in human interactions often involves voluntary participation rather than obligatory requirements. This paper investigates the impact of voluntary exit strategies on cooperation within scale-free networks, employing spatial prisoner's dilemma games as the framework. We analyze three distinct exit strategies: leader priority exit, fringe priority exit, and random exit, across varying dilemma strengths. Our findings reveal that in scenarios of weak dilemma strength, leader priority exit significantly diminishes cooperation, particularly when only a small subset of players is granted exit rights. In contrast, under strong dilemma strength conditions, both leader priority and random exits serve to unexpectedly bolster cooperation. This enhancement is primarily facilitated by high-degree nodes opting out, thereby enabling low-degree nodes to establish stable cooperation. Furthermore, our study underscores the pivotal role of network structure. In assortative networks, random exit emerges as the most effective strategy in promoting cooperation. On the other hand, disassortative networks exhibit a substantial increase in cooperation levels when employing leader priority exit. These results highlight the intricate interplay between exit strategies, dilemma strength, and network topology, offering critical insights for promoting cooperation in varied social contexts. • Study on leaders' priority exit's impact on cooperation dynamics. • Cooperation affected by leader priority exit varies with dilemma strength and network type. • Leader priority exit boosts cooperation in disassortative networks. • Random exit boosts cooperation in assortative networks. [ABSTRACT FROM AUTHOR]

Addressing the reproducibility crisis in artificial intelligence through the validation of reported experimental results is a challenging task. It necessitates either the reimplementation of techniques or a meticulous assessment of papers for deviations from the scientific method and best statistical practices. To facilitate the validation of reported results, we have developed numerical techniques capable of identifying inconsistencies between reported performance scores and various experimental setups in machine learning problems, including binary/multiclass classification and regression. These consistency tests are integrated into the open-source package mlscorecheck , which also provides specific test bundles designed to detect systematically recurring flaws in various fields, such as retina image processing and synthetic minority oversampling. [ABSTRACT FROM AUTHOR]

The main goal of this paper is to attain accurate and automatic detection of brain tumors in gray magnetic resonance images using reducing the local dimensions. We propose a novel model called Improved Mixtures of Factor Analyzers based on Dynamic Co-Clustering (IMFADCC) for the detection and localization of brain tumors. After image preprocessing and enhancement, the optimal numbers of row clusters and column clusters corresponding to each row cluster, alongside other model parameters, are determined concurrently based on the size of the tumor by our model. Then, using the optimal values obtained, the image is co-clustered by simultaneously clustering rows and columns until the block containing the tumor is identified. The output image is divided into a certain number of blocks, one of which contains the tumor. For post-processing, the identified block is binarized using minimum error thresholding. The proposed model accurately detects and locates the block binarized within the original image while considering the remainder of the image as background. The effectiveness of the proposed method was assessed by evaluating its accuracy, Dice, intersection on union, geometric mean, receiver operating characteristic curve, specificity, and sensitivity criteria on the BraTS2018, BraTS2019, and BraTS2020 datasets. The results show that our method has significant performance and is highly accurate in detecting tumors of different sizes in complex and high-size images. Moreover, our method outperforms the existing diagnostic methods. [ABSTRACT FROM AUTHOR]

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the class-specific text description is matched against the whole image. We recognize that this image-scale matching is not effective since images from the same class often contain a set of different semantic objects, and an object further consists of a set of semantic parts or concepts. Individual semantic parts or concepts may appear in image samples from different classes. To address this issue, in this paper, we develop a new method called cross-model concept learning and inference (CCLI). Using the powerful text-image correlation capability of CLIP, our method automatically learns a large set of distinctive visual concepts from images using a set of semantic text concepts. Based on these visual concepts, we construct a discriminative representation of images and learn a concept inference network to perform downstream image classification tasks, such as few-shot learning and domain generalization. Extensive experimental results demonstrate that our CCLI method is able to improve the performance of the current state-of-the-art methods by large margins, for example, by up to 8.0% improvement on few-shot learning and by up to 1.3% for domain generalization. [ABSTRACT FROM AUTHOR]

3D object detection, whose task is to perceive the surrounding environment, plays a significant role in autonomous driving. In this study, we propose a new BEV-FePNet 3D detection model, which can effectively fuse multi-modal information in deeply abstract features. The BEV-FePNet has been validated experimentally on the nuScenes dataset, and the findings demonstrate that the proposed approach enhances the performance of the detector and obtains 71.6 % mAP detection performance. In addition, with the rapid development of the autonomous driving market, collecting a large amount of data for autonomous driving has become one of the important means to enhance 3D detecting models' efficiency. However, local national data security policies have to be considered when autonomous driving manufacturers collect data in different countries, so it is difficult to transmit data abroad. To solve this problem, the DP-DeceFL framework has been proposed in this paper that utilizes differential privacy processing to enable information exchange between different countries without revealing sensitive information. Through the verification of nuScenes data, our proposed framework is superior to some selected federated learning frameworks. [ABSTRACT FROM AUTHOR]

Multi-view clustering (MVC) technology performs unsupervised clustering on data collected from multiple sources, and has received intense attention in recent years. However, most existing MVC methods fail to consider retaining view-specific information when learning multi-view consistent representations. Besides, the feature and cluster structures of multi-view data cannot be fully leveraged in clustering. In this paper, we propose a structure-guided feature and cluster contrastive learning (SGFCC) for multi-view clustering. Specifically, SGFCC utilizes autoencoders to achieve view-specific information reconstruction in feature space, and extracts high-level features for multi-view consistent representation learning to eliminate the effects of view-specific information and noise on consistent representation. To fully capture the similar clustering structure of high-level features and semantic features of samples across different views, we adopt a structure-guided feature-level and cluster-level contrastive learning strategy in our SGFCC model. Furthermore, we design a clustering layer to explore the cluster structure of high-level features. Different from most existing MVC methods, our method applies a non-fusion scheme that aggregates the semantic information of all views to obtain the final semantic labels. Extensive experiments on public datasets demonstrate that our method outperforms other competitors in clustering tasks. [ABSTRACT FROM AUTHOR]

An important objective in computer vision is to analyze multiple images and subsequently reconstruct the shape and structure in 3D. Traditional multi-view 3D reconstruction techniques extract and match key features from images with known camera parameters. However, this approach is inefficient and fails to fully exploit the advantages of multi-view information. Advancements in deep learning have revolutionized multi-view 3D reconstruction by enabling end-to-end 3D shape inferencing without the need for sequential feature matching typically found in conventional algorithms. Recent rapid progress in this field necessitates a thorough review of current algorithms and provide insight into method of improving 3D reconstruction performance. This review classifies reconstruction algorithms according to their resultant model, including depth map, voxel, point cloud, mesh, and implicit surface. Additionally, this review encompasses the inclusion of frequently employed network training loss functions for network training, assessment metrics, and the incorporation of 3D datasets. Experimental results are also presented to assess the performance of different algorithms. Finally, the paper concludes with a summary, discussion of challenges, and potential future directions. [ABSTRACT FROM AUTHOR]

Neural networks and deep learning algorithms are designed to function similarly to biological synaptic structures. However, classical deep learning algorithms fail to fully capture the need for continuous learning; this has led to the advent of incremental learning. Incremental learning adds new challenges that are handled differently by modern state-of-the-art approaches. Some of these include: utilization of network memory as additional knowledge increases the size of the network, open-set recognition to be able to identify unrecognized information, and efficient knowledge distillation as most incremental learning algorithms are prone to catastrophic forgetting of previously learned knowledge. Recent advancements achieve incremental learning through a multitude of methods. Most methods are characterized by augmenting the normal algorithm of neural network training by both directly modifying the neural network structure and by adding additional learning steps. This paper analyzes and provides a comprehensive survey of existing methods and various techniques used for incremental learning. A novel categorization of the methods is also introduced based on recent trends of the state-of-the-art solutions. The study focuses on methods that provide incremental learning success as well as discusses emerging patterns in new research. [ABSTRACT FROM AUTHOR]