Acupuncture, the core part of Traditional Chinese Medicine, relies on the accuracy of acupoint detection. But most of existing detection networks can’t achieve precise acupoint detection, whose challenges arise from posture-induced occlusion or edge effects, background clutter, and the lack of prominent surface cues for most acupoints. To address the issues, an Region-Aware Implicit Feature Extraction Network (RAIFE-Net) is proposed to enhance feature awareness and spatial reasoning for precise acupoint detection. RAIFE-Net has three fundamental components. Firstly, a Evolvable Gradient Convolution is designed to perceive gradient variations to refine edge features, which can motivate model to precisely recognize the acupoints appear near the edge of body. Secondly, the Saliency-Driven Feature Selector is able to highlight salient feature of acupoint regions by generating an attention mask which is available to suppress the interference of clutter background. At last, a Structured Position-Aware Relational Loss is developed to optimize spatial perception by constructing coordinate relationship for acupoint positions, enabling the network to accurately infer the relative positions among acupoints and improve detection precision. In the experiments, the proposed RAIFE-Net achieves state-of-the-art performance on the clinical acupoint dataset constructed for this study and public dataset.

The generative pre-training transformer (GPT) has been demonstrated to be remarkably effective in natural language processing. Motivated by advances in GPT, a geometric matching network with a generative pre-training transformer (GMNet) is proposed in this paper to provide high-quality automatic 3D object tracking for intelligent systems. Specifically, the characteristics of GMNet can be summarized as follows. First, a geometry-rebuild pre-training strategy is proposed to enhance the perception of incomplete geometry. Under this training strategy, the network is pre-trained on point cloud completion datasets to learn shape-inference capabilities and obtain a robust latent representation for tracking. After pre-training, the network is fine-tuned with the tracking data to achieve high-precision object tracking. Second, a shape reasoning module (SRM) with generative pre-training is designed to perform point cloud completion, aiming to refine geometric features by leveraging shape perception and reasoning abilities learned from geometry-rebuild pre-training. Third, an adaptive gated feature matching module (FMM) is designed to perform adaptive feature matching via a gate mechanism, which predicts the object’s location based on adaptively matched information derived from cosine similarity and SRM. Furthermore, extensive experiments demonstrate that the proposed GMNet outperforms state-of-the-art methods on KITTI, nuScenes, and Waymo open benchmarks.

Acupuncture plays an important role in the treatment of diseases, prevention, and health care. However, it is difficult to detect acupoints from the hand surface due to the complicated tasks: first, the acupoint regions are similar to the surrounding areas on the hand surface; second, the skin tone on the hand varies in depth. To address these challenges, an adaptive patch-correlation attention network (APCA-Net) is proposed for vision-based human hand acupoint detection in acupuncture, where the adaptive patch aware attention module is designed to distinguish acupoint from the surrounding skin tissue by capturing fine-grained features from small patches, while the adaptive correlation channel attention module is devised to detect acupoints of different skin tones by modeling channel correlation. Experiments on benchmarks show that the proposed APCA-Net can achieve the acupoint detection rate of 76.11% and 88.32% on the 11 K Hands Subset and Depth Hand datasets, respectively, outperforming other state-of-the-art approaches.

Nonnegative matrix factorization (NMF) is a powerful tool for signal processing and machine learning. Geometrically, it can be interpreted as the problem of finding a conic hull, which contains a cloud of data points and is embedded in the positive orthant. The separability assumption posits that the conic hull can be spanned by a small subset of the columns of the input data matrix. This assumption is equivalent to the 1-sparse condition. Many extreme-rays-based NMF methods are essentially based on the 1-sparse condition. However, the separability assumption or 1-sparse condition may not always be guaranteed for real applications. By analyzing the mathematical connection between the extreme-rays representation and the half-hyperplanes representation of a conic hull, we propose three novel NMF algorithms (i.e., HICHF, EnhancedHICHF, and ExtendedHICHF) based on the half-hyperplane identification. These algorithms can be efficiently implemented via eigenvalue decomposition (EVD). In contrast to the conventional extreme-rays-based NMF methods, the proposed methods can achieve better performance for the nonseparable NMF problems, where the 1-sparse condition is not well satisfied. Furthermore, the proposed algorithms are simple, yet efficient and more robust. Experiments on both synthetic data and real-world parts-based learning data, such as hyperspectral unmixing and facial parts learning, verify that the proposed algorithms considerably outperform the state-of-the-art algorithms.

Point cloud completion concerns the inference of the completed geometries for real-scanned point clouds that are sparse and incomplete due to occlusion, noise, and viewpoint. Previous methods usually learn a one-shot partial-to-complete mapping, which is incapable of generating fine structure details for the complex point cloud distributions. In this paper, a Hierarchical Geometry Generation point completion Network (HGG-Net) is proposed to hierarchically generate the fine-grained completed point cloud with a skeleton-to-details strategy, which consists of three fundamental modules, namely Transformer-enhanced Feature Encoder (TFE), Multi-level Geometry Representation Decoder (MGRD), and Hierarchical Dynamic Geometry Generator (HDG). Specifically, TFE first extracts geometry features of the incomplete input and obtains a coarse prediction via self-attention mechanism and edge convolution. Second, MGRD obtains the multi-level decoded geometry representations by Geometric Interactive Transformer (GIT) and Channel-Attention-based Geometry Features Fusion (CAGF), where GIT is proposed to decode the complete prompt by capturing the semantic relationship between geometry features of the incomplete and the decoded complete objects, and CAGF aims to fuse them for the high-quality representation. Third, HDG generates the complete points hierarchically from skeleton to details based on the Dynamic Graph Attention mechanism. Qualitative and quantitative experiments demonstrate that the proposed HGG-Net outperforms state-of-the-art methods on several point cloud completion datasets. Our code is available at https://github.com/haalexx/HGGNet.

Automatic segmentation of 3D dental models into individual teeth is an important step in orthodontic computer-aided design (CAD) systems. However, most existing methods rely on single-view dental models and ignore the intrinsic relationships between upper and lower dental models, hindering the handling of complex tooth structures. In this paper, a collaborative learning framework with coupling graph Transformers (CGT-CLF) is proposed for automatic tooth segmentation on 3D dental models. The framework collaboratively learns geometric features of both upper and lower dental models, capturing their interactivity and complementarity by facilitating interaction between graph-Transformer encoders to improve segmentation of complex and diverse teeth. Specifically, CGT-CLF consists of three key components as follows: First, a graph embedding-based boundary perception module (GEBPM) is developed to aggregate fine-grained geometric features within the neighborhood graph domain, enhancing the network's ability to perceive and distinguish intricate tooth boundaries. Then, coupling geometric Transformers are designed to capture the intrinsic relationships of pair-wise dental models by promoting the exchange of relevant information to gain a comprehensive understanding of the overall tooth structure, allowing for better identification of adjacent teeth with similar appearances. Finally, a collaborative cross-scale feature fusion (CCFF) strategy is utilized to obtain interactive and complementary information by modeling the inter-relationships between dual-stream features. Experimental results on a clinical dental model dataset demonstrate that the proposed CGT-CLF framework outperforms state-of-the-art methods, delivering superior segmentation performance.

3-D lane detection is a challenging task due to the diversity of lanes, occlusion, dazzle light, and so on. Traditional methods usually use highly specialized handcrafted features and carefully designed postprocessing to detect them. However, these methods are based on strong assumptions and single modal so that they are easily scalable and have poor performance. In this article, a multimodal fusion network (MFNet) is proposed through using multihead nonlocal attention and feature pyramid for 3-D lane detection. It includes three parts: multihead deformable transformation (MDT) module, multidirectional attention feature pyramid fusion (MA-FPF) module, and top-view lane prediction (TLP) ones. First, MDT is presented to learn and mine multimodal features from RGB images, depth maps, and point cloud data (PCD) for achieving optimal lane feature extraction. Then, MA-FPF is designed to fuse multiscale features for presenting the vanish of lane features as the network deepens. Finally, TLP is developed to estimate 3-D lanes and predict their position. Experimental results on the 3-D lane synthetic and ONCE-3DLanes datasets demonstrate that the performance of the proposed MFNet outperforms the state-of-the-art methods in both qualitative and quantitative analyses and visual comparisons.

Accurate object detection in remote sensing images (RSIs) is of great significance for various applications such as environmental monitoring and agricultural production. However, it is a challenging task mainly due to the complex backgrounds and scale diversity of geospatial objects. In this letter, a Cross-Scale Hybrid Gaussian Attention Network (CSHGANet) is proposed for accurate object detection in RSIs, and it consists of two main components as follows. First, hybrid Gaussian attention is designed to learn the interrelationships between channels and spatial locations of features, which can focus on geospatial objects and reduce the interference of complex backgrounds in RSIs. Then, a cross-scale feature aggregation module is developed to adaptively fuse multi-scale attention feature maps to capture more rich and discriminative feature representations, so as to better handle scale variations of remote sensing objects. Extensive experiments on two public datasets (i.e., NWPU VHR-10 and RSOD) show that the proposed CSHGANet outperforms state-of-the-art object detection methods, achieving mean average precision (mAP) scores of 95.53% and 98.61%, respectively.

The sparse collaborative tracking (SCT) method has been developed for object tracking recently, and it is very efficient and robust to various occlusions. In SCT, sparse representation (SR) plays an essential role because it needs to perform several manipulations of sparse matrix representation (SMR) or nonnegative SMR in each iteration. So one of the most challenging problems in SCT is how to efficiently solve the SMR. However, existing SR algorithms are solely developed for the vectors-based SR. They partition SMR into a set of vector-based SR problems and solve them in the level-2 BLAS (Basic Linear Algebra Subprograms) manner, i.e., matrix-vector operations, which is computationally much less efficient than the direct level-3 BLAS (direct matrix-matrix operations). To solve this problem, by extending the standard SR algorithm from the vector version to the matrix for SMR and nonnegative SMR, BLAS3-based Sparse Learning (BLAS3-SpaL) is first developed, and then the corresponding BLAS3-SpaL-based SCT method (FastSCT-BLAS3SpaL) is further developed for fast robust-object-tracking in this paper. The experiments verified that it achieves robust object tracking by reducing accumulation errors and speeds up tracking with more than double speed.

Accurate segmentation of 3D dental models derived from intra-oral scanners (IOS) is one of the key steps in many digital dental applications such as orthodontics and implants. However, it is difficult to accurately segment individual teeth and gums in 3D dental models due to the following problems: 1) the shape and appearance of adjacent teeth are very similar, which is easy to be misidentified; 2) the boundary between teeth and gums is often indistinct, especially in orthodontic patients with abnormalities such as missing and crowded teeth. To solve such problems, a Dual-Branch Geometric Attention Network (DBGANet) for 3D tooth segmentation is proposed, which can capture tooth geometric structure and detailed boundary information from multi-view geometric features encoded by 3D coordinates and normal vectors. The framework contains two branches, i.e., C-branch and N-branch. First, centroid-guided separable attention is designed in the C-branch to learn global context information by modeling the spatial dependencies of tooth point clouds, which can capture the overall geometric structure of teeth to better distinguish adjacent teeth with similar appearance. Then, Gaussian neighbor attention is designed in the N-branch to encode normal vectors to highlight detailed differences between geometric features at different points, which helps to refine the boundaries of teeth and gingiva for more accurate and smooth tooth segmentation. Extensive experiments on the real-patient datasets of 3D dental models demonstrate that the proposed DBGANet significantly outperforms state-of-the-art methods.

Surface defect detection plays an essential role in industry, and it is challenging due to the following problems: 1) the similarity between defect and nondefect texture is very high, which eventually leads to recognition or classification errors and 2) the size of defects is tiny, which are much more difficult to be detected than larger ones. To address such problems, this article proposes an adaptive image segmentation network (AIS-Net) for pixelwise segmentation of surface defects. It consists of three main parts: multishuffle-block dilated convolution (MSDC), dual attention context guidance (DACG), and adaptive category prediction (ACP) modules, where MSDC is designed to merge the multiscale defect features for avoiding the loss of tiny defect feature caused by model depth, DACG is designed to capture more contextual information from the defect feature map for locating defect regions and obtaining clear segmentation boundaries, and ACP is used to make classification and regression for predicting defect categories. Experimental results show that the proposed AIS-Net is superior to the state-of-the-art approaches on four actual surface defect datasets (NEU-DET: 98.38% ± 0.03%, DAGM: 99.25% ± 0.02%, Magnetic-tile: 98.73% ± 0.13%, and MVTec: 99.72% ± 0.02%).

In order to obtain a high-precision contact model that can properly describe the target soft tissue, this paper proposes a hybrid soft contact model based on a clustering algorithm ART-II, which selects the most suitable soft contact model according to the surgical environment. The least-square method is used to identify the parameters of the model online. In the experiments, different parts of animal tissues were used as the experimental objects. The hybrid model was used to identify and switch for the most appropriate soft contact model when dealing with a certain type of animal tissue. The performance of the hybrid model on force estimation was compared with several individual soft contact models. The results showed that the estimated/reconstructed force of the hybrid model was closer to the ground truth measured by the force sensor. In addition, a new reference soft contact model has been purposely added online to verify the expandability of the hybrid model.

To prevent the population from getting stuck in local areas and then missing the constrained Pareto front fragments in dealing with constrained multiobjective optimization problems (CMOPs), it is important to guide the population to evenly explore the promising areas that are not dominated by all examined feasible solutions. To this end, we first introduce a cost value-based distance into the objective space, and then use this distance and the constraints to define an indicator to evaluate the contribution of each individual to exploring the promising areas. Theoretical studies show that the proposed indicator can effectively guide population to focus on exploring the promising areas without crowding in local areas. Accordingly, we propose a new constraint handling technique (CHT) based on this indicator. To further improve the diversity of population in the promising areas, the proposed indicator-based CHT divides the promising areas into multiple subregions, and then gives priority to removing the individuals with the worst fitness values in the densest subregions. We embed the indicator-based CHT in evolutionary algorithm and propose an indicator-based constrained multiobjective algorithm for solving CMOPs. Numerical experiments on several benchmark suites show the effectiveness of the proposed algorithm. Compared with six state-of-the-art constrained evolutionary multiobjective optimization algorithms, the proposed algorithm performs better in dealing with different types of CMOPs, especially in those problems that the individuals are easy to appear in the local infeasible areas that dominate the constrained Pareto front fragments.

This article investigates the properties of ratio and difference-based indicators under the Minkovsky distance and demonstrates that a ratio-based indicator with infinite norm is the best for solution evaluation among these indicators. Accordingly, a promising-region-based evolutionary many-objective algorithm with the ratio-based indicator is proposed. In our proposed algorithm, a promising region is identified in the objective space using the ratio-based indicator with infinite norm. Since the individuals outside the promising region are of poor quality, we can discard these solutions from the current population. To ensure the diversity of population, a strategy based on the parallel distance is introduced to select individuals in the promising region. In this strategy, all individuals in the promising region are projected vertically onto the normal plane so that crowded distances between them can be calculated. Afterward, two solutions with a smaller distance are selected from the candidate solutions each time, and the solution with the smaller indicator fitness value is removed from the current population. Empirical studies on various benchmark problems with 3-20 objectives show that the proposed algorithm performs competitively on all test problems. Compared with a number of other state-of-the-art evolutionary algorithms, the proposed algorithm is more robust on these problems with various Pareto fronts.

Accurate and rapid diagnosis of COVID-19 using chest X-ray (CXR) plays an important role in large-scale screening and epidemic prevention. Unfortunately, identifying COVID-19 from the CXR images is challenging as its radiographic features have a variety of complex appearances, such as widespread ground-glass opacities and diffuse reticular-nodular opacities. To solve this problem, we propose an adaptive attention network (AANet), which can adaptively extract the characteristic radiographic findings of COVID-19 from the infected regions with various scales and appearances. It contains two main components: an adaptive deformable ResNet and an attention-based encoder. First, the adaptive deformable ResNet, which adaptively adjusts the receptive fields to learn feature representations according to the shape and scale of infected regions, is designed to handle the diversity of COVID-19 radiographic features. Then, the attention-based encoder is developed to model nonlocal interactions by self-attention mechanism, which learns rich context information to detect the lesion regions with complex shapes. Extensive experiments on several public datasets show that the proposed AANet outperforms state-of-the-art methods.

Blind source separation (BSS) is a typical unsupervised learning method that extracts latent components from their observations. In the meanwhile, convolutive BSS (CBSS) is particularly challenging as the observations are the mixtures of latent components as well as their delayed versions. CBSS is usually solved in frequency domain since convolutive mixtures in time domain is just instantaneous mixtures in frequency domain, which allows to recover source frequency components independently of each frequency bin by running ordinary BSS, and then concatenate them to form the Fourier transformation of source signals. Because BSS has inherent permutation ambiguity, this category of CBSS methods suffers from a common drawback: it is very difficult to choose the frequency components belonging to a specific source as they are estimated from different frequency bins using BSS. This paper presents a tensor framework that can completely eliminate the permutation ambiguity. By combining each frequency bin with an anchor frequency bin that is chosen arbitrarily in advance, we establish a new virtual BSS model where the corresponding correlation matrices comply with a block tensor decomposition (BTD) model. The essential uniqueness of BTD and the sparse structure of coupled mixing parameters allow the estimation of the mixing matrices free of permutation ambiguity. Extensive simulation results confirmed that the proposed algorithm could achieve higher separation accuracy compared with the state-of-the-art methods.

This paper proposes a novel method, called robust latent subspace learning (RLSL), for image classification. We formulate an RLSL problem as a joint optimization problem over both the latent SL and classification model parameter predication, which simultaneously minimizes: 1) the regression loss between the learned data representation and objective outputs and 2) the reconstruction error between the learned data representation and original inputs. The latent subspace can be used as a bridge that is expected to seamlessly connect the origin visual features and their class labels and hence improve the overall prediction performance. RLSL combines feature learning with classification so that the learned data representation in the latent subspace is more discriminative for classification. To learn a robust latent subspace, we use a sparse item to compensate error, which helps suppress the interference of noise via weakening its response during regression. An efficient optimization algorithm is designed to solve the proposed optimization problem. To validate the effectiveness of the proposed RLSL method, we conduct experiments on diverse databases and encouraging recognition results are achieved compared with many state-of-the-arts methods.

Focal underdetermined system solver (FOCUSS) is a powerful method for basis selection and sparse representation, where it employs the [Formula: see text]-norm with p ∈ (0,2) to measure the sparsity of solutions. In this paper, we give a systematical analysis on the rate of convergence of the FOCUSS algorithm with respect to p ∈ (0,2) . We prove that the FOCUSS algorithm converges superlinearly for and linearly for usually, but may superlinearly in some very special scenarios. In addition, we verify its rates of convergence with respect to p by numerical experiments.

Sparse subspace clustering (SSC), as one of the most successful subspace clustering methods, has achieved notable clustering accuracy in computer vision tasks. However, SSC applies only 10 vector data in Euclidean space. Unfortunately there is still no satisfactory approach to solve subspace clustering by self-expressive principle f or symmetric positive definite (SPD) matrices which is very useful, in computer vision. In this paper, by embedding the SPD matrices into a Reproducing Kernel Hilbert Space (RKHS), a kernel subspace clustering method is constructed un the SPD manifold through an appropriate Log-Euclidean kernel, termed as kernel sparse subspace clustering on the SPD Riemannian manifold(KSSCR). By exploiting the intrinsic Riemannian geometry within data, KSSCR can effectively characterize the geodesic distance between SPD matrices to uncover the underlying subspace structure. Experimental results Oft several famous datasets demonstrate that the proposed method achieves better clustering results than the state-of-the-art approaches.

Focal Underdetermined System Solver (FOCUSS) is a powerful and easy to implement tool for basis selection and inverse problems. One of the fundamental problems regarding this method is its convergence, which remains unsolved until now. We investigate the convergence of the FOCUSS algorithm in this paper. We first give a rigorous derivation for the FOCUSS algorithm by exploiting the auxiliary function. Following this, we further prove its convergence by stability analysis.

The nonnegative convex polyhedral cone (NCPC) learning is discussed in this paper. By exploiting the multiplicative update nonnegative quadratic programming, a multiplicative update algorithm is developed for NCPC learning. The proposed algorithm is promising for nonnegative matrix factorization (NMF) and we verify this by numerical experiments.

Nonnegative matrix factorization (NMF) is an unsupervised learning method useful in various applications including image processing and semantic analysis of documents. This paper focuses on symmetric NMF (SNMF), which is a special case of NMF decomposition. Three parallel multiplicative update algorithms using level 3 basic linear algebra subprograms directly are developed for this problem. First, by minimizing the Euclidean distance, a multiplicative update algorithm is proposed, and its convergence under mild conditions is proved. Based on it, we further propose another two fast parallel methods: α-SNMF and β -SNMF algorithms. All of them are easy to implement. These algorithms are applied to probabilistic clustering. We demonstrate their effectiveness for facial image clustering, document categorization, and pattern clustering in gene expression.

Nonnegative matrix factorization (NMF) with minimum-volume-constraint (MVC) is exploited in this paper. Our results show that MVC can actually improve the sparseness of the results of NMF. This sparseness is L(0)-norm oriented and can give desirable results even in very weak sparseness situations, thereby leading to the significantly enhanced ability of learning parts of NMF. The close relation between NMF, sparse NMF, and the MVC_NMF is discussed first. Then two algorithms are proposed to solve the MVC_NMF model. One is called quadratic programming_MVC_NMF (QP_MVC_NMF) which is based on quadratic programming and the other is called negative glow_MVC_NMF (NG_MVC_NMF) because it uses multiplicative updates incorporating natural gradient ingeniously. The QP_MVC_NMF algorithm is quite efficient for small-scale problems and the NG_MVC_NMF algorithm is more suitable for large-scale problems. Simulations show the efficiency and validity of the proposed methods in applications of blind source separation and human face images analysis.

Recently, there has been a growing interest in multiway probabilistic clustering. Some efficient algorithms have been developed for this problem. However, not much attention has been paid on how to detect the number of clusters for the general n-way clustering (n ≥ 2). To fill this gap, this problem is investigated based on n-way algebraic theory in this paper. A simple, yet efficient, detection method is proposed by eigenvalue decomposition (EVD), which is easy to implement. We justify this method. In addition, its effectiveness is demonstrated by the experiments on both simulated and real-world data sets.

Overcomplete representations have greater robustness in noise environment and also have greater flexibility in matching structure in the data. Lewicki and Sejnowski (2000) proposed an efficient extended natural gradient for learning the overcomplete basis and developed an overcomplete representation approach. However, they derived their gradient by many approximations, and their proof is very complicated. To give a stronger theoretical basis, we provide a brief and more rigorous mathematical proof for this gradient in this note. In addition, we propose a more robust constrained Lewicki-Sejnowski gradient.

Convolutive blind source separation (CBSS) that exploits the sparsity of source signals in the frequency domain is addressed in this paper. We assume the sources follow complex Laplacian-like distribution for complex random variable, in which the real part and imaginary part of complex-valued source signals are not necessarily independent. Based on the maximum a posteriori (MAP) criterion, we propose a novel natural gradient method for complex sparse representation. Moreover, a new CBSS method is further developed based on complex sparse representation. The developed CBSS algorithm works in the frequency domain. Here, we assume that the source signals are sufficiently sparse in the frequency domain. If the sources are sufficiently sparse in the frequency domain and the filter length of mixing channels is relatively small and can be estimated, we can even achieve underdetermined CBSS. We illustrate the validity and performance of the proposed learning algorithm by several simulation examples.

Stone's method is one of the novel approaches to the blind source separation (BSS) problem and is based on Stone's conjecture. However, this conjecture has not been proved. We present a simple simulation to demonstrate that Stone's conjecture is incorrect. We then modify Stone's conjecture and prove this modified conjecture as a theorem, which can be used a basis for BSS algorithms.

Through an analysis and comparison of the algorithm proposed by Hyvarinen-Oja (1996), we present an approach of blind separation based on the penalty functions with multipliers. The approach gives the method to select the penalty function and speeds up the convergence of the algorithm. It avoids the ill-posed problem that may be caused by the pure penalty functions. Also, we propose a new simple method of deflation. The simulations show the good effectiveness of our algorithm. The separation time of our algorithm is shorter than the one proposed by Hyvarinen-Oja (1996) by 30%.