Article
Computer Science, Information Systems
Weixing Wang, Angyan Tu, Fredrik Bergholm
Summary: This study proposes a new method for image segmentation based on graph theory and guided feathering. It effectively addresses the challenges posed by intertwined objects and backgrounds, vague boundaries, and similar textures, resulting in improved segmentation accuracy for images with variable targets.
KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Mehrnaz Niazi, Kambiz Rahbar, Mansour Sheikhan, Maryam Khademi
Summary: This paper investigates entropy-based kernel graph cut image segmentation and proposes a method that incorporates a 2-layer feature space to improve segmentation performance. The proposed method is particularly effective in dealing with non-textural and complex textural images. Experimental results demonstrate the superior performance of the proposed method in energy-based image segmentation.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Lei Zhu, Xuejing Kang, Lizhu Ye, Anlong Ming
Summary: This paper proposes an ENCUT model that establishes a balanced graph model by adopting a meaningful-loop and a k-step random walk to enhance small object segmentation. The model is further improved by adding a new RWRT that adds local attention to the segmentation of twigs. Experimental results show that the model achieves state-of-the-art performance among NCut-based segmentation models.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Mathematics, Applied
Fengming Dong, Jun Ge, Zhangdong Ouyang
Summary: The number of spanning trees in a connected multi-graph can be calculated using the Matrix-Tree Theorem and Tutte's deletion-contraction formula, but this note presents an alternative method based on vertex degrees.
APPLIED MATHEMATICS AND COMPUTATION
(2022)
Article
Engineering, Biomedical
Hongming Xu, Lina Liu, Xiujuan Lei, Mrinal Mandal, Cheng Lu
Summary: This study introduces a new unsupervised method, TisCut, for assisting tissue image segmentation and annotations, showing comparative performance with U-Net models in necrosis and melanoma detections.
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS
(2021)
Article
Psychiatry
Huibin Jia, Xiangci Wu, Zhiyu Wu, Enguo Wang
Summary: Through analyzing the altered functional connectivity in the autistic brain, researchers found that individuals with ASD exhibited lower and more volatile information exchange efficiencies within the default mode network compared to typical developing participants, which may be closely related to the severity of autistic symptoms.
FRONTIERS IN PSYCHIATRY
(2022)
Article
Computer Science, Artificial Intelligence
Petr Taborsky, Laurent Vermue, Maciej Korzepa, Morten Morup
Summary: The article introduces a novel Bayesian probabilistic model for graph cutting, providing an effective solution to separating community structures in complex networks. The method demonstrates excellent performance on real social networks and image segmentation problems, while also learning the parameter space.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
P. Karthick, S. A. Mohiuddine, K. Tamilvanan, S. Narayanamoorthy, S. Maheswari
Summary: Image segmentation plays a vital role in image analysis and vision-based systems, especially for color images. However, the diversity of color and intensities in color images makes segmentation challenging. This study proposes a shape priority and connectivity measure approach using a normalized fuzzy graph cut measure based on the common S membership function to improve color image segmentation. The proposed method effectively handles structural imperfections in color images and achieves better accuracy compared to other existing techniques.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Information Systems
Lukasz Galka, Pawel Karczmarek, Mikhail Tokovarov
Summary: Modern technologies have made it possible for researchers and practitioners to explore large datasets, highlighting the importance of anomaly detection methods in fixing or deleting unwanted records. The Isolation Forest algorithm is considered one of the fastest and most effective methods in anomaly detection, based on the construction of isolation binary trees through random split of dataset elements. This manuscript proposes an innovative approach that modifies the Isolation Forest technique by replacing random divisions with divisions based on Minimal Spanning Tree clustering. The evaluation process is also improved through the introduction of a two-component score function, which takes into account the level of the test element in the isolation tree as well as the distance between specific points in the last split node.
INFORMATION SCIENCES
(2023)
Article
Operations Research & Management Science
Francesco Carrabs, Raffaele Cerulli, Rosa Pentangelo, Andrea Raiconi
Summary: The paper presents a branch-and-cut approach to solve the minimum spanning tree problem with conflicting edge pairs, demonstrating its superiority over previous algorithms through computational tests on benchmark instances and newly proposed ones.
ANNALS OF OPERATIONS RESEARCH
(2021)
Article
Mathematics, Applied
Xia Hong, Wei Feng
Summary: For a graph G, if there exist k spanning trees T-1, T-2, ..., T-k, such that the paths from any two vertices u, v in these k trees are pairwise openly disjoint, then these k trees are completely independent. Hasunuma proved that there are two completely independent spanning trees in any 4-connected maximal planar graph, and the problem of deciding whether there exist two completely independent spanning trees in a given graph G is NP-complete. This paper investigates the number of completely independent spanning trees in some Cartesian product graphs.
Article
Computer Science, Interdisciplinary Applications
Michael Segal, Oren Tzfaty
Summary: The bounded-diameter minimum spanning tree problem seeks to find a minimum weight spanning tree on a connected, weighted, undirected graph G with a diameter no more than D. A new algorithm has been developed that can handle graphs with non-negative weights and has been proven to have a certain performance ratio. The algorithm's performance has been evaluated empirically as well.
COMPUTERS & OPERATIONS RESEARCH
(2022)
Article
Computer Science, Interdisciplinary Applications
Wei Wei, Qiuyuan Hu, Weidong Yang
Summary: This article proposes a new approximation algorithm for the minimum cut (min-cut) problem in undirected graphs, which can accelerate existing methods by up to 6 orders of magnitude with limited preprocessing overhead. By checking and recording the cut values of various traversal trees, the algorithm estimates the upper bound of the min-cut value between any pair of nodes. Experimental results show that even the serial implementation of the algorithm achieves a larger acceleration ratio compared to existing methods.
ADVANCES IN ENGINEERING SOFTWARE
(2022)
Article
Geochemistry & Geophysics
Hao Zhang, Peimin Zhu, Zhiying Liao, Zewei Li
Summary: This study proposes a novel deep-learning-based interactive segmentation method for extracting salt boundaries. By transforming interaction points into Euclidean distance maps and training a CNN model with seismic images, this method achieves more accurate and robust salt boundary extraction. The results are further improved using a graph cut algorithm.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Interdisciplinary Applications
G. H. Shirdel, B. Vaez-Zadeh
Summary: This paper introduces a method to transform a hypergraph into a graph, with the presentation of two corresponding graphs called the Clique graph and the Persian graph. These graphs have simpler structures and are easier to work with. The main objective of the paper is to find the minimal spanning hypertree for the hypergraph.
JOURNAL OF COMBINATORIAL OPTIMIZATION
(2022)
Article
Computer Science, Artificial Intelligence
Hao Zhang, Yajie Zou, Xiaoxue Yang, Hang Yang
Summary: This study adopts a novel architecture called TFT to predict freeway speed, which can capture short-term and long-term temporal dependence and improve prediction accuracy by incorporating various types of inputs.
Article
Computer Science, Artificial Intelligence
Xindi Yang, Hao Zhang, Zhuping Wang
Summary: This article introduces a data-based distributed control algorithm to address the consensus control problem in multiagent systems, successfully overcoming the challenges of asynchronous learning. By incorporating an actor-critic structure and neural networks, the algorithm achieves convergence and optimality in both synchronous and asynchronous cases.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Zhichen Li, Yu Zhao, Huaicheng Yan, Hao Zhang, Lu Zeng, Xiaolei Wang
Summary: This paper investigates the time-varying formation tracking control problem for multi-agent systems (MASs). The main objective is to achieve asymptotic convergence of formation tracking error despite nonparametric and nonvanishing uncertainties. A fuzzy extended state observer (FESO) based on event-triggered mechanism is proposed to estimate unmodeled dynamics and external disturbances. Furthermore, a distributed control law is developed using neighborhood formation tracking errors, and total disturbance compensation is introduced to attenuate uncertainty influence in real time. The effectiveness of the proposed control protocol is demonstrated using a numerical example on unmanned aerial vehicle swarm system.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Computer Science, Artificial Intelligence
Hang Wang, Youtian Du, Yabin Zhang, Shuai Li, Lei Zhang
Summary: This paper proposes a novel one-stage approach called VRR-TAMP, which formulates the task of VRR as an end-to-end bounding box regression problem by effectively integrating Transformers and an adaptive message passing mechanism. Experimental results demonstrate that our approach significantly outperforms its one-stage competitors and achieves competitive results with the state-of-the-art multi-stage methods.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Automation & Control Systems
Min Xue, Huaicheng Yan, Hao Zhang, Xisheng Zhan, Kaibo Shi
Summary: This article discusses compensation-based output feedback control for Takagi-Sugeno fuzzy Markov jump systems subject to packet losses. Utilizing single exponential smoothing as a compensation scheme, an asynchronous output feedback controller is designed with stochastic stability and strict dissipativity. Novel sufficient conditions for controller existence based on mode-dependent Lyapunov function are derived, along with an algorithm for determining the optimal smoothing parameter. Simulation results demonstrate the validity and advantages of the design approach.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Automation & Control Systems
Bo Qin, Huaicheng Yan, Hao Zhang, Yueying Wang, Simon X. Yang
Summary: This paper proposes a control method based on an enhanced reduced-order extended state observer for precise motion control in mobile robot systems. The method reduces energy consumption by estimating unknown state error and negative disturbance and uses a simple state-feedback-feedforward controller to track the reference signal and compensate for negative disturbance.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Automation & Control Systems
Xindi Yang, Hao Zhang, Zhuping Wang, Huaicheng Yan, Changzhu Zhang
Summary: This article presents a model-free predictive control algorithm for real-time systems that improves system performance through data-driven multi-step policy gradient reinforcement learning. By learning from offline and real-time data, the algorithm avoids the need for knowledge of system dynamics in its design and application. Cooperative games are used to model predictive control as multi-agent optimization problems and ensure the optimal predictive control policy. Neural networks are employed to approximate the action-state value function and predictive control policy, with weights determined using weighted residual methods. Numerical results demonstrate the effectiveness of the proposed algorithm.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Automation & Control Systems
Zhichen Li, Huaicheng Yan, Hao Zhang, Simon X. Yang, Mengshen Chen
Summary: This article investigates the design problem of an extended state observer (ESO) for uncertain nonlinear systems subject to limited network bandwidth. A dynamic event-triggered communication protocol is proposed for rational information exchange scheduling, achieving a desirable tradeoff between observation performance and communication resource efficiency. A novel paradigm of event-triggered Takagi-Sugeno fuzzy ESO is introduced, and the TSFESO design approach is derived to carry out exponential convergence for estimation error dynamics under the dynamic event-triggered mechanism. The effectiveness of the proposed method is verified through numerical examples, expanding the application scope of ESO with improved event-triggered strategies.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Xiaoming Li, Shiguang Zhang, Shangchen Zhou, Lei Zhang, Wangmeng Zuo
Summary: This paper proposes a blind face restoration method that explicitly memorizes generic and specific features through dual dictionaries to improve the performance of blind face restoration. By learning generic and specific dictionaries and combining the dictionary transform module and multi-scale dictionaries, the restoration results are improved.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Jianqi Ma, Shi Guo, Lei Zhang
Summary: This paper proposes a method to improve the resolution and visual quality of scene text images by embedding text recognition prior into the super-resolution model, which also boosts the performance of text recognition. Experimental results show that this method effectively improves the visual quality of scene text images and significantly enhances the text recognition accuracy.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Kai Zhang, Qi Liu, Hao Qian, Biao Xiang, Qing Cui, Jun Zhou, Enhong Chen
Summary: This paper proposes a novel model called EATN for accurately classifying sentiment polarities towards aspects in multiple domains in sentiment analysis tasks. The model incorporates a Domain Adaptation Module (DAM) to learn common features and uses multiple-kernel selection method to reduce feature discrepancy among domains. Additionally, EATN includes an aspect-oriented multi-head attention mechanism to capture the direct associations between aspects and contextual sentiment words. Extensive experiments on six public datasets demonstrate the effectiveness and universality of the proposed method compared to current state-of-the-art methods.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaoming Li, Chaofeng Chen, Xianhui Lin, Wangmeng Zuo, Lei Zhang
Summary: Designing proper training pairs is crucial for superresolving real-world low-quality images. Previous methods focus on modeling degradation with limited improvement. This study uses real-world low-quality face images to model complex degradation and transfers it to natural images to synthesize realistic low-quality counterparts. The results show that this method can effectively learn the real degradation process and improve the quality of non-facial areas.
COMPUTER VISION - ECCV 2022, PT XVIII
(2022)
Article
Computer Science, Artificial Intelligence
Kai Zhang, Yawei Li, Wangmeng Zuo, Lei Zhang, Luc Van Gool, Radu Timofte
Summary: Recent works have shown that using a denoiser as the image prior can improve the performance of plug-and-play image restoration methods. However, existing methods are limited by the lack of suitable denoiser priors. In this study, we propose a deep denoiser prior that significantly outperforms other state-of-the-art model-based and learning-based methods for various image restoration tasks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Yunkai Lv, Hao Zhang, Zhuping Wang, Huaicheng Yan
Summary: This article focuses on the real-time localization problem in dynamic multi-agent systems with measurement and communication noises under directed graphs. It introduces barycentric coordinates to describe the relative position between agents and proposes a novel robust distributed localization estimation algorithm based on iterative learning. The algorithm uses a relative-distance unbiased estimator constructed from historical iterative information to suppress measurement noise, and a designed stochastic approximation method with two iterative-varying gains to inhibit communication noise. The asymptotic convergence of the proposed methods is derived under certain conditions of zero-mean and independent distribution of measurement and communication noises. Numerical simulations and robot experiments are conducted to test and verify the effectiveness and practicability of the proposed methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Binghui Chen, Weihong Deng, Biao Wang, Lei Zhang
Summary: This article emphasizes the importance of generalization ability in deep metric learning for zero-shot image retrieval and clustering tasks. It proposes a confusion-based metric learning framework that uses energy confusion and diversity confusion regularization terms to optimize a robust metric. The framework confuses the learned model in an adversarial manner and serves as an efficient regularization for deep metric learning. Experimental results demonstrate the significance of learning an embedding/metric with good generalization.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang
Summary: This article introduces a novel image retrieval method that improves retrieval performance by using sublimated deep features. The method incorporates orientation-selective features and color perceptual features, effectively mimicking these mechanisms to provide a more discriminating representation.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi
Summary: RGB-Thermal (RGB-T) semantic segmentation is an emerging task that aims to improve the robustness of segmentation methods under extreme imaging conditions by using thermal infrared modality. The challenges of foreground-background distinguishment and complementary information mining are addressed by proposing a cross modulation process with two collaborative components. Experimental results show that the proposed method achieves state-of-the-art performances on current RGB-T segmentation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao
Summary: This paper proposes a novel automatic prompt generation method called F-SCP, which focuses on generating accurate prompts for low-accuracy classes and similar classes. Experimental results show that our approach outperforms state-of-the-art methods on six multi-domain datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong
Summary: Adverse weather conditions present challenges for computer vision tasks, and image de-weathering is an important component of image restoration. This paper proposes a multi-patch skip-forward structure and a Residual Deformable Convolutional module to improve feature extraction and pixel-wise reconstruction.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schonlieb, Matthew Thorpe, Konstantinos C. Zygalakis
Summary: The transportation LP distance (TLP) is a generalization of the Wasserstein WP distance that can be applied directly to color or multi-channelled images, as well as multivariate time-series. TLP interprets signals as functions, while WP interprets signals as measures. Although both distances are powerful tools in modeling data with spatial or temporal perturbations, their computational cost can be prohibitively high for moderate pattern recognition tasks. The linear Wasserstein distance offers a method for projecting signals into a Euclidean space, and in this study, we propose linear versions of the TLP distance (LTLP) that show significant improvement over the linear WP distance in signal processing tasks while being several orders of magnitude faster to compute than the TLP distance.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Haitao Tian, Shiru Qu, Pierre Payeur
Summary: This paper proposes a method of target-dependent classifier, which optimizes the joint hypothesis of domain adaptation into a target-dependent hypothesis that better fits with the target domain clusters through an unsupervised fine-tuning strategy and the concept of meta-learning. Experimental results demonstrate that this method outperforms existing techniques in synthetic-to-real adaptation and cross-city adaptation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang
Summary: Deep learning-based methods have achieved remarkable results in the field of super-resolution. However, the limitation of paired training image sets has led researchers to explore self-supervised learning. However, the assumption of inaccurate downscaling kernel functions often leads to degraded results. To address this issue, this paper introduces KGSR, a kernel-guided network that trains both upscaling and downscaling networks to generate high-quality high-resolution images even without knowing the actual downscaling process.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Yifan Chen, Xuelong Li
Summary: Gait recognition is a popular technology for identification due to its ability to capture gait features over long distances without cooperation. However, current methods face challenges as they use a single network to extract both temporal and spatial features. To solve this problem, we propose a two-branch network that focuses on spatial and temporal feature extraction separately. By combining these features, we can effectively learn the spatio-temporal information of gait sequences.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Wei Shi, Wentao Zhang, Wei-shi Zheng, Ruixuan Wang
Summary: This article proposes a simple yet effective visualization framework called PAMI, which does not require detailed model structure and parameters to obtain visualization results. It can be applied to various prediction tasks with different model backbones and input formats.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Xiaobo Hu, Jianbo Su, Jun Zhang
Summary: This paper reviews the latest technologies in pattern recognition, highlighting their instabilities and failures in practical applications. From a control perspective, the significance of disturbance rejection in pattern recognition is discussed, and the existing problems are summarized. Finally, potential solutions related to the application of compensation on features are discussed to emphasize future research directions.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe
Summary: Convolutional neural networks are widely used in critical systems, and explainable artificial intelligence has proposed methods for generating high-level explanations. However, these methods lack the ability to determine the location of concepts. To address this, we propose a novel method for automatic concept extraction and localization based on pixel-wise aggregations, and validate it using synthetic datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Peng Bao, Jianian Li, Rong Yan, Zhongyi Liu
Summary: In this paper, a novel Dynamic Graph Contrastive Learning framework, DyGCL, is proposed to capture the temporal consistency in dynamic graphs and achieve good performance in node representation learning.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Summary: Research indicates that deep generative models perform poorly compared to linear interpolation-based methods for synthetic data generation on small, imbalanced tabular datasets. To address this, a new approach called ConvGeN, combining convex space learning with deep generative models, has been proposed. ConvGeN improves imbalanced classification on small datasets while remaining competitive with existing linear interpolation methods.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Khondaker Tasrif Noor, Antonio Robles-Kelly
Summary: In this paper, the authors propose H-CapsNet, a capsule network designed for hierarchical image classification. The network effectively captures hierarchical relationships using dedicated capsules for each class hierarchy. A modified hinge loss is utilized to enforce consistency among the involved hierarchies. Additionally, a strategy for dynamically adjusting training parameters is presented to achieve better balance between the class hierarchies. Experimental results demonstrate that H-CapsNet outperforms competing hierarchical classification networks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang
Summary: This study proposes a new agricultural image segmentation model called CS-Net, which uses Simple-Attention Block and Simpleformer to improve accuracy and inference speed, and addresses the issue of performance collapse of Transformers in agricultural image processing.
PATTERN RECOGNITION
(2024)
