The anchor similarity matrix, widely used for efficient clustering, exhibits an imbalance between its rows and columns - only the rows are typically constrained by probabilistic properties, unlike the regular similarity matrix where both dimensions are regulated. This paper addresses the critical question of how to impose meaningful constraints on the columns to better capture the data structure. We propose a novel method, termed Multi-view Clustering via Bilaterally constrained anchor Graph (MCBG), which learns a fused anchor similarity matrix with bilateral constraints. To ensure consistency across views, we quantitatively assess their contributions and integrate them into a unified model. By applying distinct constraints to rows and columns, MCBG promotes a balanced and expressive anchor similarity distribution, avoiding degenerate cases. Furthermore, a rank constraint on the Laplacian matrix of an anchor-pairwise graph is incorporated, ensuring a one-step post-processing-free multi-view clustering framework. An efficient alternating iterative optimization algorithm is developed, adapted to the natural properties of the target problem. Extensive experiments validate the superiority of the proposed method.

Salient object detection in optical remote sensing images (ORSI-SOD) faces unique challenges due to complex backgrounds, diverse scales, and multi-directional objects. Existing methods primarily rely on visual features, often struggling to distinguish salient objects from visually similar backgrounds. To address this limitation, we leverage large language models (LLMs) to expend existing ORSI-SOD datasets with detailed textual annotations, creating a more comprehensive benchmark for image-text ORSI-SOD. Building upon this foundation, we propose the Frequency Meets Semantics Network (FMS-Net), a novel framework that integrates text-visual fusion with directional spectral enhancement for ORSI-SOD. FMS-Net consists of two key innovations: the Hierarchical Multi-Modal Dual-Channel Fusion (HMDF) module and the Adaptive Directional Spectral Enhancement (ADSE) module. The HMDF module enables bidirectional interactions between visual and textual features via parallel global-local attention mechanisms, progressively enriching visual representations with semantic context. Meanwhile, the ADSE module enhances feature representations in the frequency domain, capturing directional patterns and boundary details critical for accurate saliency detection. Extensive experiments on two public datasets, ORSSD and EORSSD, demonstrate that FMS-Net outperforms state-of-the-art methods, particularly in complex scenes with ambiguous boundaries. Our work paves the way for integrating multi-modal and frequency-based approaches in the interpretation of optical remote sensing images (ORSI).

Graph clustering typically involves a two-step process: relaxation followed by post-processing. However, it often leads to significant information loss during relaxation and solution deviation in post-processing. Additionally, traditional graph clustering faces computational challenges due to regular graph construction and spectral decomposition, and binary indicators hinder interpretability in uncertain scenarios. We propose a novel method termed Fast Fuzzy Graph Cut (FFGC) to overcome key issues in graph clustering by: preventing information loss by tackling the original graph cut problem; eliminating solution deviation by directly solving for the target variable; alleviating computational burdens by employing anchor graphs in place of regular graphs; and enhancing flexibility by incorporating a regularization term to soften the cluster indicator. The use of a fuzzy cluster indicator within the graph cut framework expands FFGC's applicability to a wider range of real-world data, increasing both its adaptability and interpretability. In addition, we develop two efficient optimization algorithms to solve the resulting objective problem. Extensive experimental evaluations validate the superior efficiency and effectiveness of FFGC in clustering tasks. The code is available athttps://github.com/caccode/FFGC.

Summary As the development of chip manufacturing technology slows down, high‐performance processors often have high energy consumption and high heat generation. Therefore, heterogeneous multi‐core processors become more and more popular, and the heterogeneous multi‐core processors is adopted to execute programs. At present, the general program consists of multiple threads. To reach goals of accelerating program execution and reducing energy consumption and heat generation of system, a suitable thread scheduling algorithm for heterogeneous multi‐core processors is needed. In this article, a thread scheduling algorithm based on multiple critical scheduling factors is proposed. First, a prediction model of thread performance and energy consumption is used to predict the core sensitivity of threads. Then, critical threads are judged and accelerated by collecting the synchronization information between threads. Finally, the load balancing method based on the computing power of cores and the core sensitivity of threads is employed to perform system load balancing, which ensures the fairness of the scheduling. Several experiments are provided, and the results show that the proposed algorithm can obtain better performance of thread schedule.

Recent advancements have significantly benefited in salient object detection for optical remote sensing images (ORSI-SOD). Given the varying spatial resolutions and complex scenes characteristic of optical remote sensing images (ORSI), leveraging and integrating features across scales is vital. However, excessive feature integration can introduce significant noise and result in inaccurate saliency mapping. To address this issue, we propose the Multi-scale and Multi-dimensional Weighted Network for ORSI-SOD (WeightNet). The network adopts a two-stage design where the first stage generates multi-scale weighted information, and the second stage conducts indirect multi-scale feature weighted fusion. This design skillfully avoids the lack of scale adaptation and noise interference that may arise from direct multi-scale feature fusion. Furthermore, to enhance feature fusion and target localization precision, we introduce the Multi-Scale Weighted Feature Aggregation Module (MWFAM) and the Multi-Dimensional Feature Guidance Module (MDFGM). MWFAM facilitates multi-scale feature fusion while minimizing noise from cross-layer interactions. MDFGM specializes in precise target localization and enhancement of detail and edge information. Additionally, the introduction of a Multi-Scale Parallel Decoder (MPD) significantly boosts the decoder’s capability in identifying targets across various scales. Extensive qualitative and quantitative evaluations on three public ORSI datasets demonstrate the effectiveness and superiority of WeightNet over contemporary state-of-the-art models.

In most existing graph-based multi-view clustering methods, the eigen-decomposition of the graph Laplacian matrix followed by a post-processing step is a standard configuration to obtain the target discrete cluster indicator matrix. However, we can naturally realize that the results obtained by the two-stage process will deviate from that obtained by directly solving the primal clustering problem. In addition, it is essential to properly integrate the information from different views for the enhancement of the performance of multi-view clustering. To this end, we propose a concise model referred to as Multi-view Discrete Clustering (MDC), aiming at directly solving the primal problem of multi-view graph clustering. We automatically weigh the view-specific similarity matrix, and the discrete indicator matrix is directly obtained by performing clustering on the aggregated similarity matrix without any post-processing to best serve graph clustering. More importantly, our model does not introduce an additive, nor does it has any hyper-parameters to be tuned. An efficient optimization algorithm is designed to solve the resultant objective problem. Extensive experimental results on both synthetic and real benchmark datasets verify the superiority of the proposed model.

Clustering is one of the most important techniques in the field of data mining. It partitions data points into different groups based on the similarity of information provided. Many clustering methods calculate similarity matrix before clustering as a separated step. They ignore the fact that embedded subspace can better reveal the spatial distribution of the original data since practical data always exist in a large scale. In this paper, we proposed a model called Adaptive Projected Clustering with Graph Regularization (APCGR) where the similarity matrix calculating and clustering process are conducted simultaneously. To achieve a desirable clustering result, we impose a rank constraint on the Laplacian matrix of the similarity matrix to ensure that the number of the connected components are exactly that same as the clustering number. The proposed clustering framework is indeed executed on an optimal subspace where more accurate and reasonable solutions can be provided. Augmented Lagrangian Method (ALM) will be applied in the optimizing procedure to effectively solve the potential problems and show the clustering results explicitly. Experimental results on both synthetic and benchmark datasets exhibit the superior performance of the proposed method.

Multi-view semi-supervised learning (SSL) has attracted great attention due to its effectiveness in information utilization of multiple views and labeled and unlabeled data to solve practical problems. However, most existing methods exhibit high computational complexity. Effective integration of the information on different views to achieve enhanced performance remains a challenging task. In this study, we combine an anchor-based approach with multi-view semi-supervised learning to address these problems. A novel multi-view SSL method called fast multi-view SSL (FMSSL) based on learned graph is proposed. Starting from the affinity graphs constructed by using an anchor-based strategy, FMSSL learns an optimal multi-view consensus graph by using feature and label information. The learned graph can jointly consider the relation of multiple views to approximate the manifold structure. The learned graph is then introduced into the SSL model as the weight matrix of a bipartite graph to simultaneously perform separate classification on the original samples and anchors. Accordingly, multi-view SSL can be efficiently performed, and the computational complexity can be significantly reduced. We propose an effective algorithm to optimize the objective function. Extensive experimental results on different real-world datasets demonstrate the effectiveness and efficiency of the proposed algorithm.

Generally, the existing graph-based multi-view clustering models consists of two steps: (1) graph construction; (2) eigen-decomposition on the graph Laplacian matrix to compute a continuous cluster assignment matrix, followed by a post-processing algorithm to get the discrete one. However, both the graph construction and eigen-decomposition are time-consuming, and the two-stage process may deviate from directly solving the primal problem. To this end, we propose Fast Multi-view Discrete Clustering (FMDC) with anchor graphs, focusing on directly solving the spectral clustering problem with a small time cost. We efficiently generate representative anchors and construct anchor graphs on different views. The discrete cluster assignment matrix is directly obtained by performing clustering on the automatically aggregated graph. FMDC has a linear computational complexity with respect to the data scale, which is a significant improvement compared to the quadratic one. Extensive experiments on benchmark datasets demonstrate its efficiency and effectiveness.

Faced with the increasing data diversity and dimensionality, multi-view dimensionality reduction has been an important technique in computer vision, data mining and multi-media applications. Since collecting labeled data is difficult and costly, unsupervised learning is of great significance. Generally, it is crucial to explore the complementarity or independence of different feature spaces in multi-view learning. How to find a low-dimensional subspace to preserve the intrinsic structure of original unlabeled high-dimensional multi-view data is still challenging. In addition, noises and outliers always appear in real data. In this study, we propose a novel model called flexible multi-view unsupervised graph embedding (FMUGE). A flexible regression residual term is introduced so that the strict linear mapping is relaxed, new-coming data and noises are better handled, and the raw data negotiate with the learned low-dimensional representation in the procedure. To ensure the consistency among multiple views, FMUGE adaptively weights different features and fuses them to get an optimal multi-view consensus similarity graph, which assists high-quality graph embedding. We propose an efficient alternating iterative algorithm to optimize the proposed model. Finally, experimental results on synthetic and benchmark datasets show the significant improvement of FMUGE over the state-of-the-art methods.

Object recognition is widely used in vision computing for various applications. Traditional CPU and application specific integrated circuit for vision computing cannot provide high performance and enough flexibility, which limit the use of vision systems. In this paper, a hierarchical and parallel pipelined heterogeneous chip for object recognition is proposed to achieve high flexibility, high performance, and area efficiency. In addition, a reformulation of 3D position estimation is proposed. The method uses single precision to achieve the short computing time and accuracy requirement. The hardware resource is small. Application-specific components, such as connected component information extractor and information extraction accelerator, are designed for high performance. Reconfiguration processors and application-specific instruction set processor are introduced to improve flexibility. These components are connected to hierarchical parallel buses. The chip is fabricated in 180-nm CMOS technology and occupies 72.25 mm2with 1.09M bits on-chip memory. It delivers 204 GOPS + 665M FLOPS operations. The results show that this hierarchical and parallel pipelined heterogeneous chip is suitable for embedded vision systems.

Haze removal is useful in computational photography and computer vision applications. Although many haze removal algorithms have been proposed, their computational efficiency requires improvement. A real-time haze removal method is presented in this paper. The method is based on the concept of a dark channel prior. To enhance the haze removal performance, an approximate method to estimate the atmospheric light and transmission is employed. For embedded system applications, a hardware architecture to perform real-time haze removal is proposed. The hardware can achieve 116 MHz on Stratix FPGA. The simulation results indicate that the hardware is highly efficient and performs well. It obtains good image recovery results and satisfies the real-time requirement even for large images.

Binary image processing is a powerful tool in many image and video applications. A reconfigurable processor is presented for binary image processing in this paper. The processor's architecture is a combination of a reconfigurable binary processing module, input and output image control units, and peripheral circuits. The reconfigurable binary processing module, which consists of mixed-grained reconfigurable binary compute units and output control logic, performs binary image processing operations, especially mathematical morphology operations, and implements related algorithms more than 200 f/s for a 1024 × 1024 image. The periphery circuits control the whole image processing and dynamic reconfiguration process. The processor is implemented on an EP2S180 field-programmable gate array. Synthesis results show that the presented processor can deliver 60.72 GOPS and 23.72 GOPS/mm2at a 220-MHz system clock in the SMIC 0.18-μm CMOS process. The simulation and experimental results demonstrate that the processor is suitable for real-time binary image processing applications.