In modern Computer-Aided Design (CAD), parametric sketches play a crucial role by capturing both the geometric structure and design intent through constraints. However, existing deep learning–based sketch methods remain restricted to simple geometric primitives and limited constraint types, hindering their application to complex real-world engineering tasks. To address this gap, we introduce the UniSketch dataset, comprising 3,836,290 sketches. It offers a comprehensive and diverse collection of 7 types of geometric primitives and 23 types of 2D constraints, all represented as unified vector sequences suitable for deep learning applications. Leveraging the UniSketch dataset, we propose a unified multi-task Transformer framework as a true foundation model for parametric sketch modeling, supporting diverse core tasks like image-to-sketch generation, constraint prediction, and unconditional sketch synthesis. Furthermore, the generated sketches can be efficiently converted to CAD-compatible formats, enabling seamless integration with industrial CAD system for re-editing and reusing. The experimental results show that UniSketch outperforms existing methods in multiple tasks, demonstrating its versatility and practical value in industrial CAD applications.

On the one hand, parametric and feature-based design (PFDesign) is one of key techniques in today's CAD/CAM enterprises. On the other hand, the challenges in reconstruction of parametric and feature-based CAD models (PFCAD models) are quite different from that in reconstruction of geometry models (such as 3D mesh or B-rep models) in the previous studies. In this paper, we propose a novel architecture with dual-transformer and continuation attention to reconstruct PFCAD models. Specifically, our architecture contains a representation extractor module for discrete 3D data (such as mesh, point cloud, voxel), a dual-transformer reconstructor module for CAD operations and an adaptor module with CAD continuation attention for CAD pa-rameters. The proposed dual-transformer reconstructor includes two decoders, one is global decoder and the other is local decoder. Thus, we can leverage the whole design history as well as detail information to build PFCAD models. In addition, we devise a parameter adaptor with CAD continuation attention mechanism to further refine the CAD operation parameters. We conduct extensive experiments, in which the proposed approach achieves excellent or competitive results when compared to typical works in leading publications.

Dynamic reasoning frameworks such as Chain of Thought (CoT), Tree of Thought (ToT), and Graph of Thought (GoT) have greatly enhanced the logical reasoning capabilities of large language models (LLMs). However, their effectiveness depends on appropriately setting the granularity of each thought. Long thoughts may lead to higher error rates due to insufficient utilization of control signals, while short thoughts can reduce reasoning efficiency. This study introduces two dynamic step size control methods—Dynamic-step ToT and Chain-ToT—to address this issue. Dynamic-step ToT adjusts the number of reasoning steps in each thought dynamically to balance accuracy and efficiency, while Chain-ToT employs a linear reasoning approach, progressively expanding the step size until errors are detected. Experimental results on cutting-edge models such as Llama 3.1, Qwen 2.5, and GPT-4o-mini, as well as datasets including MATH, AIME, and MMLU-pro, demonstrate that our proposed dynamic step size methods significantly improve reasoning efficiency. This is achieved while maintaining or even surpassing the accuracy levels of standard ToT frameworks in complex reasoning tasks. We will release the code and results.

Deep learning techniques have become transformative forces in the field of Computer Graphics, including voxels, point clouds, and meshes. However, the integration of deep learning with Computer-Aided Design (CAD) has not yet reached a mature stage due to the lack of support for a rich variety of high-level CAD features. In parametric and feature-based modeling, various advanced CAD feature operations require unique identifiers to specify topological elements like surface and edge, known as naming mechanism. Unfortunately, this mechanism is currently unavailable in CAD deep learning due to its difficulty in formulation and representation. Therefore, this paper proposes a novel method for combining naming and CAD learning, which is the first work that applies name to specify model topological elements in CAD deep learning. Specifically, we create a dataset which records the name identifier information of elements contained in CAD models, together with model construction history for reconstruction. Subsequently, we propose a deep learning approach for predicting topological element names from model construction history, which shows a high prediction rate in the experiments. Additionally, with the help of name identifiers, we introduce high-level feature operations into CAD deep learning modeling and conduct an extended model generation experiment to show the practicality of our method. The impressive generation results prove that our method opens a new direction to bridge the gap between CAD deep learning and practical CAD modeling. The code and dataset are available at https://github.com/fazhihe/NamingCAD.

In this article, different from previous traditional multi-exposure image fusion (MEF) algorithms that use hand-designed feature extraction approaches or deep learning-based algorithms that utilize convolutional neural networks for information preservation, we propose a novel multi-Exposure image fusion method via Adversarial learning and focal Transformer, named EAT. In our framework, a Focal Transformer is proposed to focus on more remarkable regions and construct long-range multi-exposure relationships, with which the fusion model can simultaneously extract local and global multi-exposure properties and therefore generate promising fusion results. To further improve the fusion performance, we introduce adversarial learning to train the proposed method in an adversarial manner with the guidance of ground truth. By doing so, the fused images exhibit better visual perception and color fidelity. Extensive experiments conducted on publicly available databases provide compelling evidence that EAT surpasses other state-of-the-art approaches on both quantitative and qualitative evaluations. Furthermore, we directly employ our trained model to address another benchmark MEF dataset. The impressive fusion performance serves as evidence of the credible generalization ability of EAT.

3D point cloud has been wildly used in security crucial domains, such as self-driving and 3D face recognition. Backdoor attack is a serious threat that usually destroy Deep Neural Networks (DNN) in the training stage. Though a few 3D backdoor attacks are designed to achieve guaranteed attack efficiency, their deformation will alarm human inspection. To obtain invisible backdoored point cloud, this paper proposes a novel 3D backdoor attack, named IBAPC, which generates backdoor trigger in the graph spectral domain. The effectiveness is grounded by the advantage of graph spectral signal that it can induce both global structure and local points to be responsible for the caused deformation in spatial domain. In detail, a new backdoor implanting function is proposed whose aim is to transform point cloud to graph spectral signal for conducting backdoor trigger. Then, we design a backdoor training procedure which updates the parameter of backdoor implanting function and victim 3D DNN alternately. Finally, the backdoored 3D DNN and its associated backdoor implanting function is obtained by finishing the backdoor training procedure. Experiment results suggest that IBAPC achieves SOTA attack stealthiness from three aspects including objective distance measurement, subjective human evaluation, graph spectral signal residual. At the same time, it obtains competitive attack efficiency. The code is available at https://github.com/f-lk/IBAPC.

The contours of objects effectively represent essential 3D information such as shapes and boundaries. Existing contour detection methods mostly rely on thresholding or neural networks to classify points as edge or non-edge points. However, these methods often lack generalization ability on datasets with different shapes, leading to issues such as missing contours and discontinuous distribution. To address this, we propose a 3D point cloud contour generation method based on the denoising diffusion probabilistic model (DDPM). Our method treats the complete point cloud as an explicit condition to guide the generation of contour from noise. Specifically, our method trains the DDPM to be a conditional generative network customized for contour generation tasks. In the network, we design the Conditional Feature Extraction (CFE) module that obtains multi-scale feature information, and the Conditional Feature Fusion (CFF) module embeds this information in the generation process to guide contour generation. The experimental results demonstrate the effectiveness of our method. The source code of our method is available at: https://github.com/djzgroup/ContourGeneration.

Computer-aided design (CAD) is the primary and indispensable tool for engineers and designers, streamlining design processes and contributing to innovation in various industries. However, mastering these complex CAD programs demands extensive training and experience for CAD practitioners. To this end, this paper proposes View2CAD to reconstruct CAD models from multi-view. Specifically, we first introduce a novel end-to-end network that directly reconstructs parametric CAD command sequences from multi-view images. Then, the proposed View2CAD solves the problem of the low-rank bottle in the traditional attention mechanism of neural networks. Finally, a new parametric CAD dataset is presented, in which we add multi-view images for the corresponding CAD sequence and remove redundant CAD data. The comparison experiments demonstrate that our View2CAD framework is capable of reconstructing high-quality parametric CAD models, which can be further edited by other users in collaborative CAD/CAM environment.

Cross-modality visible-infrared person reidentification (VI-ReID) has attracted widespread concern due to its scalability in 24-h video surveillance of the Visual Internet of Things (VIoT). Driven by enough annotated training data, supervised VI-ReID has achieved superior performance. However, annotating a large amount of cross-modality data is extremely time-consuming, which limits its employment in real-world scenarios. Existing several works neglect the image-level discrepancy and could not obtain reliable feature-level heterogeneous correlation. In this article, we propose a novel homogeneous and heterogeneous optimization with modality style adaptation (HHO) mechanism to eliminate intramodality and intermodality discrepancies without any label information for unsupervised VI-ReID. Specifically, we present the modality style adaptation strategy to transfer unlabeled cross-modality pedestrian styles, which not only increases the image diversity but also bridges the intermodality gap. Meanwhile, we employ the clustering algorithm to generate pseudo labels for each modality. The homogeneous feature optimization is developed to extract intramodality pedestrian features. Furthermore, we propose heterogeneous feature optimization to eliminate the intermodality discrepancy. To this end, a heterogeneous feature search (HFS) module is designed to mine reliable cross-modality signals for each identity. These reliable heterogeneous features are constrained to generate the compact feature distribution, while different identities are forced to be separated. The HHO are seamlessly integrated to learn cross-modality robust features. Abundant experiments prove the superiority of HHO, which gains superior performance.

3D mesh classification deep neural network (3D DNN) has been widely applied in many safety-critical domains. Backdoor attack is a serious threat that occurs during the training stage. Previous backdoor attacks from 2D image and 3D point cloud domains are not suitable for 3D mesh due to data structure restrictions. Therefore, in a pioneering effort, this paper presents two types of backdoor attacks on 3D mesh. Specifically, the first attack is a Mesh Geometrical Feature guided 3D Mesh Backdoor Attack named MGF-MBA. Most 3D DNNs have to convert 3D mesh to a regular matrix (mesh geometrical feature), which is a refinement of the input 3D mesh. The 3D DNN directly learns the 3D shape from the mesh geometrical feature, which enables attackers to implant backdoor through it. Hence, the proposed MGF-MBA generates a backdoored 3D mesh under the guidance of mesh geometrical feature. The second attack is a Remeshing based 3D Mesh Backdoor Attack named ReMBA. The quality of samples backdoored by exiting backdoor attacks always decrease. Although many efforts have been made to reduce the descent in quality in return for stealthiness, the descent persists. For better stealthiness, we regard the backdoor implantation process as a way to increase the quality of backdoored sample rather than a way to reduce it. Specifically, ReMBA designs a new isotropic remeshing method that attempts to represent a 3D mesh by equilateral triangles while keeping the number of vertices, edges and faces unchanged. Numerous experimental results show that both MGF-MBA and ReMBA achieve guaranteed attack performance on 3D DNNs. Furthermore, transferability experiments demonstrate that ReMBA can even attack 3D point cloud networks with an increased ability to resist defenses.

Billions of people share images from their daily lives on social media every day. However, their biometric information (e.g., fingerprints) could be easily stolen from these images. The threat of fingerprint leakage from social media has created a strong desire to anonymize shared images while maintaining image quality, since fingerprints act as a lifelong individual biometric password. To guard the fingerprint leakage, adversarial attack that involves adding imperceptible perturbations to fingerprint images have emerged as a feasible solution. However, existing works of this kind are either weak in black-box transferability or cause the images to have an unnatural appearance. Motivated by the visual perception hierarchy (i.e., high-level perception exploits model-shared semantics that transfer well across models while low-level perception extracts primitive stimuli that result in high visual sensitivity when a suspicious stimulus is provided), we propose FingerSafe, a hierarchical perceptual protective noise injection framework to address the above mentioned problems. For black-box transferability, we inject protective noises into the fingerprint orientation field to perturb the model-shared high-level semantics (i.e., fingerprint ridges). Considering visual naturalness, we suppress the low-level local contrast stimulus by regularizing the response of the Lateral Geniculate Nucleus. Our proposed FingerSafe is the first to provide feasible fingerprint protection in both digital (up to 94.12%) and realistic scenarios (Twitter and Facebook, up to 68.75%). Our code can be found at https://github.com/nlsde-safety-team/FingerSafe.

Delaunay meshes play a critical role in geometry processing for their favorable geometric and numerical properties. However, Delaunay mesh simplification is rather challenging because of the no-differentiable constraint and the two conflicting goals: high geometric fidelity and low mesh complexity. To simultaneously meet these criteria, this paper addresses the Delaunay mesh simplification from an evolutionary multi-objective viewpoint. First, the adaptive segment-specific thresholds replace the previous unique error-bound threshold. Second, we perform constrained simplification by a sequence of edge collapses with Delaunay and error constraints. Finally, the non-dominated sorting genetic algorithm II (NSGA-II) is introduced to search optimal trade-off threshold sequences. Compared with state-of-the-art methods, our method can consistently achieve a satisfactory balance regarding approximation error and the number of vertices.

In linear registration, a floating image is spatially aligned with a reference image after performing a series of linear metric transformations. Additionally, linear registration is mainly considered a preprocessing version of nonrigid registration. To better accomplish the task of finding the optimal transformation in pairwise intensity-based medical image registration, in this work, we present an optimization algorithm called the normal vibration distribution search-based differential evolution algorithm (NVSA), which is modified from the Bernstein search-based differential evolution (BSD) algorithm. We redesign the search pattern of the BSD algorithm and import several control parameters as part of the fine-tuning process to reduce the difficulty of the algorithm. In this study, 23 classic optimization functions and 16 real-world patients (resulting in 41 multimodal registration scenarios) are used in experiments performed to statistically investigate the problem solving ability of the NVSA. Nine metaheuristic algorithms are used in the conducted experiments. When compared to the commonly utilized registration methods, such as ANTS, Elastix, and FSL, our method achieves better registration performance on the RIRE dataset. Moreover, we prove that our method can perform well with or without its initial spatial transformation in terms of different evaluation indicators, demonstrating its versatility and robustness for various clinical needs and applications. This study establishes the idea that metaheuristic-based methods can better accomplish linear registration tasks than the frequently used approaches; the proposed method demonstrates promise that it can solve real-world clinical and service problems encountered during nonrigid registration as a preprocessing approach.The source code of the NVSA is publicly available at https://github.com/PengGui-N/NVSA.

The fusion of infrared and visible images aims to generate a composite image that can simultaneously contain the thermal radiation information of an infrared image and the plentiful texture details of a visible image to detect targets under various weather conditions with a high spatial resolution of scenes. Previous deep fusion models were generally based on convolutional operations, resulting in a limited ability to represent long-range context information. In this paper, we propose a novel end-to-end model for infrared and visible image fusion via a dual attention Transformer termed DATFuse. To accurately examine the significant areas of the source images, a dual attention residual module (DARM) is designed for important feature extraction. To further model long-range dependencies, a Transformer module (TRM) is devised for global complementary information preservation. Moreover, a loss function that consists of three terms, namely, pixel loss, gradient loss, and structural loss, is designed to train the proposed model in an unsupervised manner. This can avoid manually designing complicated activity-level measurement and fusion strategies in traditional image fusion methods. Extensive experiments on public datasets reveal that our DATFuse outperforms other representative state-of-the-art approaches in both qualitative and quantitative assessments. The proposed model is also extended to address other infrared and visible image fusion tasks without fine-tuning, and the promising results demonstrate that it has good generalization ability. The source code is available athttps://github.com/tthinking/DATFuse.

Hyperspectral endmember extraction (HEE) is an essential part of remote-sensing image processing. There have been recent attempts to model the HEE as a multiobjective optimization problem and apply multiobjective evolutionary algorithms to solve the problem. However, because of the large HEE search space, it is difficult for the current algorithms to achieve exploration–exploitation balance, and they easily stall prematurely. To address these issues, this article proposes a multistrategy evolutionary multiobjective method based on roulette wheel selection and the genetic algorithm (RWS-GA) for endmember extraction. This method designs two parallel algorithms corresponding to global exploration and local exploitation. In the RWS-GA, an improved NSGA-II method, adopting a novel method to sort individuals on the same front instead of the crowding distance, is proposed to divide individuals into superior and inferior subpopulations. Thereafter, different modified population update strategies are utilized for subpopulations based on characteristics. Pixels that appear more frequently in the population are considered to perform better to have a higher probability of forming an endmember set with other pixels. In addition, excellent individuals often exhibit a higher probability of including endmembers compared with inferior individuals. Considering the abovementioned opinions, roulette wheel selection is performed on the inferior subpopulation for global search. Meanwhile, the superior subpopulation is responsible for local search based on the genetic algorithm (GA). Furthermore, an offspring complement mechanism (OCM) is presented to prevent duplicate individuals from appearing in historical archives. Numerous comparative experiments show that the proposed method is superior to other endmember extraction methods in three real-world datasets.

Unsupervised person re-identification (Re-ID) aims to learn discriminative features without human-annotated labels. Recently, contrastive learning has provided a new prospect for unsupervised person Re-ID, and existing methods primarily constrain the feature similarity among easy sample pairs. However, the feature similarity among hard sample pairs is neglected, which yields suboptimal performance in unsupervised person Re-ID. In this paper, we propose a novel Hybrid Contrastive Model (HCM) to perform the identity-level contrastive learning and the image-level contrastive learning for unsupervised person Re-ID, which adequately explores feature similarities among hard sample pairs. Specifically, for the identity-level contrastive learning, an identity-based memory is constructed to store pedestrian features. Accordingly, we define the dynamic contrast loss to identify identity information with dynamic factor for distinguishing hard/easy samples. As for the image-level contrastive learning, an image-based memory is established to store each image feature. We design the sample constraint loss to explore the similarity relationship between hard positive and negative sample pairs. Furthermore, we optimize the two contrastive learning processes in one unified framework to make use of their own advantages as so to constrain the feature distribution for extracting potential information. Extensive experiments demonstrate that the proposed HCM distinctly outperforms existing methods.

Infrared and visible image fusion is aims to generate a composite image that can simultaneously describe the salient target in the infrared image and texture details in the visible image of the same scene. Since deep learning (DL) exhibits great feature extraction ability in computer vision tasks, it has also been widely employed in handling infrared and visible image fusion issue. However, the existing DL-based methods generally extract complementary information from source images through convolutional operations, which results in limited preservation of global features. To this end, we propose a novel infrared and visible image fusion method, i.e., the Y-shape dynamic Transformer (YDTR). Specifically, a dynamic Transformer module (DTRM) is designed to acquire not only the local features but also the significant context information. Furthermore, the proposed network is devised in a Y-shape to comprehensively maintain the thermal radiation information from the infrared image and scene details from the visible image. Considering the specific information provided by the source images, we design a loss function that consists of two terms to improve fusion quality: a structural similarity (SSIM) term and a spatial frequency (SF) term. Extensive experiments on mainstream datasets illustrate that the proposed method outperforms both classical and state-of-the-art approaches in both qualitative and quantitative assessments. We further extend the YDTR to address other infrared and RGB-visible images and multi-focus images without fine-tuning, and the satisfactory fusion results demonstrate that the proposed method has good generalization capability.

Image classification is a basic task in machine intelligence, but challenging due to high variations across images. Traditional methods use hand-crafted features to solve it, which require much domain knowledge. Genetic Programming (GP) can automatically solve problems without much knowledge about the structure and form of the solution. And GP is interpretable and needs less time to adjust the parameters compared with deep image classification methods. However, the existing GP-based image classification methods have some disadvantages, such as poor classification performance and long training time. This paper proposed a new image classification algorithm based on multilayer genetic programming with cache (MCGP). MCGP designs a new hierarchical individual program structure with a classification layer and uses a subtree cache strategy to reduce training time. The experiments show that MCGP can get better or competitive results compared with traditional methods, other GP methods, and convolutional neural network methods. In addition, the training speed of MCGP is much faster than other GP methods.

The distribution of feature vectors plays a critical role in image registration. In this letter, we propose a novel approach for remote sensing image registration based on marginal distribution adaptation. First, we map the feature vectors of reference and sensed images into a latent space. Transfer component analysis (TCA) is employed to compute the transformation matrix by minimizing the maximum mean discrepancy (MMD). Then, we match feature vectors in the latent space where their marginal distributions are similar, which can increase correct correspondences and enhance registration accuracy. Finally, we test the proposed algorithm on ten real image pairs. The effectiveness and efficiency of our approach are verified by experimental results.

Abstract Co‐editors are a class of human‐centered collaborative systems that allow multiple geographically dispersed people to freely and concurrently edit shared documents at the same time over networks. The most important building co‐editors technique is consistency maintenance. Even though OT (operational transformation) is a widely adopted consistency maintenance technique, researchers and practitioners have persistently explored alternative techniques to OT. One of the representative techniques is AST (Address Space Transformation), which replaces OT's transformation components with basic manipulation on an additional object sequence. However, the additional object sequence causes an unbounded metadata overhead problem. To solve the problem, this work proposes an optimized AST algorithm called ASTO, which is equipped with a specially designed self‐compressing object sequence. ASTO can automatically compress the object sequence and keep the metadata overhead under control. The effectiveness and feasibility of ASTO are verified by simulation experiments and a publicly accessible prototype system.

The 3D point cloud is a common 3D data representation that has received increasing attention for remote sensing applications. However, processing 3D point cloud semantics, especially local semantic information, has always been a challenge and has attracted much attention. In this paper, we propose a novel enhanced local semantic learning transformer for 3D point cloud analysis, which aims to enhance the transformer awareness of local semantic features to handle complex point cloud tasks. First, we propose a novel transformer framework, the local semantic learning point cloud transformer (LSLPCT), which not only learns 3D point clouds the global information, but also enhances the perception of local semantic information end-to-end. Second, we design an efficient local semantic learning self-attention mechanism, namely LSL-SA, which can parallelize the perception of global contextual information and the capture of finer-grained local semantic features. Third, our proposed LSL-SA is easy to implement and can integrate existing transformers and CNN-based networks for processing various point cloud tasks. Numerous experiments in different types of point cloud tasks have been conducted, and our method performs better or is competitive with other state-of-the-art methods.

Owing to the limitations of imaging sensors, it is challenging to obtain a medical image that simultaneously contains functional metabolic information and structural tissue details. Multimodal medical image fusion, an effective way to merge the complementary information in different modalities, has become a significant technique to facilitate clinical diagnosis and surgical navigation. With powerful feature representation ability, deep learning (DL)-based methods have improved such fusion results but still have not achieved satisfactory performance. Specifically, existing DL-based methods generally depend on convolutional operations, which can well extract local patterns but have limited capability in preserving global context information. To compensate for this defect and achieve accurate fusion, we propose a novel unsupervised method to fuse multimodal medical images via a multiscale adaptive Transformer termed MATR. In the proposed method, instead of directly employing vanilla convolution, we introduce an adaptive convolution for adaptively modulating the convolutional kernel based on the global complementary context. To further model long-range dependencies, an adaptive Transformer is employed to enhance the global semantic extraction capability. Our network architecture is designed in a multiscale fashion so that useful multimodal information can be adequately acquired from the perspective of different scales. Moreover, an objective function composed of a structural loss and a region mutual information loss is devised to construct constraints for information preservation at both the structural-level and the feature-level. Extensive experiments on a mainstream database demonstrate that the proposed method outperforms other representative and state-of-the-art methods in terms of both visual quality and quantitative evaluation. We also extend the proposed method to address other biomedical image fusion issues, and the pleasing fusion results illustrate that MATR has good generalization capability. The code of the proposed method is available at https://github.com/tthinking/MATR.

While collaborative designing keeps on showing its capability in improving the efficiency of product designing and optimizing the quality of product, conflict management still remains a great challenge for this promising designing mode. By summarizing the basic principles for conflict management in feature based 3D collaborative designing, this paper presents a conflict prediction and prevention solution. Using an inspecting server to receive the stepwise designing process message from each site written in declarative language, the server would be able to predict the potential conflict by extracting critical parameters from these messages. Afterwards, a negotiation-based conflict prevention approach is proposed by transmitting messages between clients and server/client. Case studies show that the approach is an effective way to guarantee the designing model to be a consensus of designers.

With the burgeoning of mobile devices, collaborative editing through mobile devices has become an alternative choice to traditional desktop PCs. However, mobile collaborative editing has to face some technical challenges. How to achieve an efficient mobile collaboration while maintaining the shared document copies consistency is one of the core issues in collaborative computing area. This paper proposes a cloud-based lightweight collaborative algorithm for mobile devices. Firstly, a cloud-based mobile collaborative editing framework is proposed for collaborating between cloud platform and mobile devices. Secondly, a collaborative editing task allocation model is constructed to assign editing operations for cloud platform and mobile devices. Thirdly, a cloud-based lightweight collaborative editing approach is presented to achieve the data synchronization and the consistency maintenance for the shared document copies. Finally, experiments evaluations prove the effectiveness of the proposed approach.

Feature selection is extremely important in machine learning and data mining. Typical two-objective feature selection methods aim to minimize the number of features and maximize classification performance. However, they overlook the fact that there may be multiple subsets with similar information content for a given cardinality. The paper presents a many-objective feature selection approach to address this problem. Firstly, we establish a five-objective optimization model, which consists of classification accuracy, the number of features, feature relevance, feature redundancy, and feature complementarity. Therefore, the proposed model can enlarge the search space with more Pareto solutions. Secondly, we propose a wrapper structure for many-objective feature selection, which integrates a learning algorithm. Thirdly, in order to reduce the computional overhead, we propose a filter structure, which separates the learning algorithm. For implementation, we adopt NSGA-III multi-objective evolutionary algorithm and extreme learning machine. The experiments on mainstream datasets confirm the superiority of the proposed method.

Abstract In the field of target detecting, lots of progress have been made in recent years. Owing to the progress of multiple frames time series data, or video satellites, target detecting from space‐borne satellite videos has been available. However, detecting a slightly moving target from space‐borne videos is still a difficult task, because of the low resolution and illumination variation influence. This paper considers target detecting from time series data as multi‐label problem as there are several different kinds of background objects and targets of interest. To some extent the background of time series data is comparative invariant, using background analysis method to extract the target from the background is promising. This paper proposes a novel target detecting algorithm based on multi‐label learning and Gaussian background description model aiming at extracting slowly moving target. To further enhance performances, multi‐frame fusion and post processing method was utilized to catch the slight difference due to movement. Experimental results on real world datasets indicate that the proposed method outperforms some state‐of‐the‐art algorithms.

Deep convolutional networks have obtained remarkable achievements on various visual tasks due to their strong ability to learn a variety of features. A well-trained deep convolutional network can be compressed to 20%–40% of its original size by removing filters that make little contribution, as many overlapping features are generated by redundant filters. Model compression can reduce the number of unnecessary filters but does not take advantage of redundant filters since the training phase is not affected. Modern networks with residual, dense connections and inception blocks are considered to be able to mitigate the overlap in convolutional filters, but do not necessarily overcome the issue. To do so, we propose a new training strategy, weight asynchronous update, which helps to significantly increase the diversity of filters and enhance the representation ability of the network. The proposed method can be widely applied to different convolutional networks without changing the network topology. Our experiments show that the stochastic subset of filters updated in different iterations can significantly reduce filter overlap in convolutional networks. Extensive experiments show that our method yields noteworthy improvements in neural network performance.

Bat algorithm (BA) has the advantage of fast convergence, but there is still room for improvement in accuracy and stability of solution. An efficient and robust fusion bat algorithm (ERFBA) is proposed to overcome these defects. In the population reconstruction, an effective diversity population (E DP) is reconstructed by designing a multi-strategy opposition-based learning with disturbance. In the exploration, an adaptive constraint step whale optimization algorithm is presented to obtain the promising regions with fewer blind spots by exploring EDP. In the exploitation, we design a new BA local search strategy by novel combination between dynamic regulation and Cauchy mutation to get accurate and stable solution. Numerous experiments show that ERFBA has remarkable advantages in accuracy and stability for many high dimension, unimodal and multimodal problems. Moreover, the proposed algorithm is further tested and applied in areas of intelligent data analysis and intelligent design. The results show that the overall performance of the proposed ERFBA is better than other existing algorithms.

As a new design and manufacture paradigm, Cloud-Based Collaborative Design (CBCD) has motivated designers to outsource their product data and design computation onto the cloud service. Despite non-negligible benefits of CBCD, there are potential security threats for the outsourced product data, such as intellectual property, design intentions and private identity, which has become an interest point. This paper presents a novel secure product data exchange (PDE) in the processes of CBCD. Different from general cloud security mechanism, our method is content-based. We first show an outline of the collaborative scenario to describe the architecture of the proposed secure CBCD, in which a security mechanism is combined with the data exchange service to achieve secure PDE. Second, we present a novel grid-based geometric deformation method for the security mechanism with three processes: the original shapes of a source Computer Aided Design (CAD) model can be hidden by deforming the control grid; then the deformed grid can be exchanged to target system where a deformed target CAD model can be reconstructed; at last, the deformed target CAD model can be recovered to the original shape after recovering the deformed grid. Finally, typical CAD model tests demonstrate that our method can keep the sensitive information of source model and also maintain the same level of data exchange error.

Model update scheme is a challenging issue to develop a robust object tracking system. This paper puts forward to a collaborative feature learning for accurate tracking with extended particle filter framework. Meanwhile, different model update schemes are employed to select the precise target model. With the collaborative feature learning, the template library with salient features can maintain the rich target appearances. Even when appearance of the target significantly changes, it can still find appropriate appearance model from the template library. Experimental results on several image sequences demonstrate the robustness and accuracy of our approach in a complex scenario.

Feature-based collaborative designing environment has provided designers with a platform where products are developed in a parallel way. Conflicts among concurrent operations can never be ignored. Other than detecting and resolving conflicts after they occurred and caused inconsistencies, in this paper, a unified conflict prevention framework considering do, undo, redo operations is presented. By defining the reading and writing actions imposed on a part model, 6 operation transactions are identified. Potential conflicts are detected by monitoring the states of concurrent operation transactions and estimating possible topological entity change. A partial and total operation transaction rollback based confliction prevention method is proposed to preserve the design intentions of multiple users and maintain the data consistency of system. The proposed methods are tested in a prototype system with several case studies.

Trust Relationships have shown great potential to improve recommendation quality, especially for cold start and sparse users. Since each user trust their friends in different degrees, there are numbers of works been proposed to take Trust Strength into account for recommender systems. However, these methods ignore the information of trust directions between users. In this paper, we propose a novel method to adaptively learn directive trust strength to improve trust-aware recommender systems. Advancing previous works, we propose to establish direction of trust strength by modeling the implicit relationships between users with roles of trusters and trustees. Specially, under new trust strength with directions, how to compute the directive trust strength is becoming a new challenge. Therefore, we present a novel method to adaptively learn directive trust strengths in a unified framework by enforcing the trust strength into range of [0, 1] through a mapping function. Our experiments on Epinions and Ciao datasets demonstrate that the proposed algorithm can effectively outperform several state-of-art algorithms on both MAE and RMSE metrics.

As a new kind of swarm intelligence algorithms, bat algorithm is inspired by the bat's echolocation model to search an optimization solution. In this paper, we propose a novel bat algorithm based on collaborative and dynamic learning of opposite population. The proposed algorithm adapts a collaborative strategy to generate the opposite population. Therefore more possible opposite individuals can be dynamically learned and added to the population. We also present elite choices for the current and the opposite population. In this way, the search diversity and search intensity can be achieved. The experimental results of 8 typical test functions show that the proposed algorithm has the characteristics of fast convergence and avoiding falling into local optimal solution.

Ant colony optimization (ACO) is a population-based metaheuristic for solving hard combinatorial optimization problems. Many studies are dedicated to accelerating ACO by parallel hardware, especially by graphics processing units (GPUs). However, due to the irregular (random) pattern of ACO algorithms in data access and control flow, the performance of GPU-based approaches is constrained by hardware limitations. CPU-based SIMD computing for ACOs is rarely investigated in previous literatures, and how well multicore-SIMD CPU-based parallel ACOs could perform remains unknown. In this paper, we present and evaluate a model of vector parallel ACO for multi-core SIMD CPU architecture. In the proposed model, each ant is mapped with a CPU core and the tour construction of each ant is accelerated by vector instructions. Furthermore, based on the model, we propose a new fitness proportionate selection approach named Vector-based Roulette Wheel (VRW) in the tour construction stage. In this approach, the fitness values are grouped into SIMD lanes and the prefix sum is computed in vector-parallel mode. The proposed algorithm is tested on standard TSP instances ranging from 198 to 4461 cities and shows a speedup factor of 57.8x compared to the single-threaded CPU counterpart. More significantly, we compare our approach with high performance GPU-based ACOs, and the results demonstrate the strong potential of CPU-based parallel ACOs.

In the co-design process of hardware/software (HW/SW) system, especially for large and complicated embedded systems, HW/SW partitioning is a challenging step. Among different heuristic approaches, particle swarm optimization (PSO) has the advantages of simple implementation and computational efficiency, which is suitable for solving large-scale problems. This paper presents a conformity particle swarm optimization with fireworks explosion operation (CPSO-FEO) to solve large-scale HW/SW partitioning. First, the proposed CPSO algorithm simulates the conformist mentality from biology research. The CPSO particles with psychological conformist always try to move toward a secure point and avoid being attacked by natural enemy. In this way, there is a greater possibility to increase population diversity and avoid local optimum in CPSO. Next, to enhance the search accuracy and solution quality, an improved FEO with new initialization strategy is presented and is combined with CPSO algorithm to search a better position for the global best position. This combination can keep both the diversified and intensified searching. At last, the experiments on benchmarks and large-scale HW/SW partitioning demonstrate the efficiency of the proposed algorithm.

With the rapid development of service-oriented computing (SOC)/service-oriented architecture (SOA), cloud computing and web services, cloud-based design and manufacture (CBDM) is emerging as state-of-the-art technologies and methodologies to enable collaborative product development (CPD). CBDM-enabled CPD can provide cost-effective, flexible and scalable solutions to collaborative partners by sharing the resources in the applications of design and manufacturing. Feature-based data exchange (FBDE) has been one of the key issues in history of CPD and should be adapted in lasted CBDM-enabled CPD. Firstly this paper presents a service-oriented architecture for data exchange in CBDM. Within this architecture, FBDE was registered as service and FBDE users in the CBDM environment can acquire a set of FBDE services to replace the traditional FBDE functions among heterogeneous CAD systems. Secondly, in orderto put the philosophy of FBDE-as-a-Service into practice for CBDM, this paper proposes a peerto peer (P2P) approach for service-oriented FBDE, which revolutionizes the traditional centralized and neutral-file based approach. Thirdly, technique issues of FBDE-as-a-Service in P2P architecture are discussed in details, including constituting of the P2P FBDE service, procedure of service-oriented P2P FBDE, pre-P2P FBDE service, topological entity matching between pre/post-P2P service and post-P2P FBDE service. Finally, a case study of data exchange is tested to demonstrate the proposed idea of service-oriented FBDE for CBDM.

In collaborative editing environments, operations issued by a group of users may be duplicate and undesired. A selective undo mechanism allows collaborative users to undo any of mis-issued operations at any time and has become an indispensable facility for collaborative editing. However, supporting selective undo is a technical challenge. The traditional selective undo approach explicitly modifies the original consistency maintenance mechanism of do operations or presents a new algorithm with integrated do and undo operations. In additional, these do operations and undo operations interfere with each other, which complicates correctness proofs and causes a high time complexity. In this paper, we propose a novel selective undo algorithm T-UNDO (transparent selective undo). T-UNDO can be transparently integrated into the consistency maintenance algorithms of do operations that maintains insertions before deletions in the edit history. Moreover, T-UNDO can achieve correct undo effect. T-UNDO has a linear time complexity of O(|Hi|+log(|Hd|)), where |Hi| is the number of insertions and |Hd| is the number of deletions in the history.

This paper presents a GPU-accelerated parallel MAX-MIN Ant System (MMAS) algorithm based on an approach named grouped roulette wheel selection (G-Roulette). A data parallel model is adapted in the proposed approach with special consideration for GPU architecture. We propose a G-Roulette strategy to enhance the parallel computation of fitness-proportionate selection. The G-Roulette strategy includes two hierarchical stages to choose the optimal city. Consequently the running time is decreased by the G-Roulette strategy. We modify the MMAS with dynamical evaporation factor in the stage of pheromone updating. Experimental results show that G-Roulette enhanced MMAS algorithm is competitive with other state-of-art parallel ACO algorithms.

Hardware/software partitioning is an essential step in Hardware/Software Co-design. This paper presents a GPU-accelerated adaptive neighborhood taboo search algorithm(GPU-accelerated ANTS) to solve the problem. Firstly, a pre-GPU version of ANTS is presented to test our idea, in which both the number of feasible candidates in neighborhood and the length of taboo list can be adaptively adjusted. Secondly, a GPU-accelerated version combined with the two merits from pre-GPU version is presented. Furthermore, in order to fully leverage the power of GPU, the special consideration for the optimization strategies and implementation details on GPU are explored for our GPU- accelerated ANTS algorithm. Finally, enough number of experiments show that our GPU-accelerated ANTS method outperforms state-of-the-art work of taboo search for the HW/SW partitioning in both quality and speed under mid/low range GPU platform.

Recently, Commutative Replicated Data Type(CRDT) algorithms have been proposed and proved by many references to outperform traditional algorithms in real-time collaborative editing. Replicated Growable Array(RGA) has the best average performance among CRDT algorithms. However, RGA only supports character-based primitive operations. This paper proposes an efficient collaborative editing approach supporting string-based operations(RGA Supporting String). Firstly, RGASS is presented under string-wise architecture to preserve operation intentions of collaborative users. Secondly, the time complexity of RGASS has been analyzed in theory to be lower than that of RGA and the state of the art OT algorithm(ABTSO). Thirdly, the experiment evaluations show that the computative performance of RGASS is better than that of RGA and ABTSO. Therefore, RGASS is more adaptable to large-scale collaborative editing with higher performance than a representative class of CRDT and OT algorithms in publications.

As the popularization of 3D print technology, in the future cloud manufacturing environment, it makes the customization of personalized product with low cost to be possible. The design in the customization of personalized product is particularly important. And the key issues are the expression and understanding of design intentions from designers with different backgrounds in collaborative CAD which is main design tool for industrial products. An operation-effects merging for collaborative design method of personalized product is presented, which treats the operation effects reflecting the design intention as the research object, and merges the operation effects based on the geometric semantics to support the real-time collaborative product design freely. The advantage of the proposed method is that, the design intentions are expressed without any delay in the design which can improve the design efficiency and product quality.

Feature-based data exchange (FBDE) for heterogeneous CAD systems is one of the key issues in Collaborative Product Development (CPD) which is now enabled by Cloud-Based Design and Manufacturing (CBDM). Firstly this paper presents a FBDE-as-a-Service architecture for data exchange in CBDM. Within this architecture, FBDE users in the CBDM environment can acquire a set of Peer to Peer (P2P) services to realize the FBDE functions among heterogeneous CAD systems. Secondly, in order to integrate FBDE services into CBDM, we present a P2P approach for FBDE, which is totally different from traditional centralized and neutral file-based approach. Thirdly, some key issues of FBDE-as-a-Service, such as Pre-P2P FBDE service, Post-P2P FBDE service and topological entity matching are researched. Finally, a prototype system of FBDE-as-a-Service for data exchange is implemented to demonstrate the proposed ideas.

Product data exchange is one of most important key issues in Collaborative Product Development. Since feature-based parametric CAD systems have been dominated by industrial applications, Feature-Based Data Exchange (FBDE) is getting real growth. However the main feature-based method still lacks the ability to exchange complex shape among the heterogeneous CAD Systems. This paper attacks the problem by exchanging the parametric curve (such as Spline) which is sketched in 2D and will be used to prepare complex 3D shapes by various extrusion features. Therefore the data exchange of complex shape is divided into two layers: 3D extrusion layer and 2D sketch layer. The exchange of spline proceed in the 2D sketch layer between different CAD systems. We innovatively convert the problem of spline exchange into the problem of spline fitting, and employ the Genetic Algorithm (GA) to solve the problem. A new coding strategy in stage of initialization population is presented to improve the GA so it works well with the spline fitting among the heterogeneous CAD systems. Finally, a Hausdorff Distance (HD) is adopted to calculate the fitness. Experimental results demonstrate the effectiveness of our method.

Model security for collaborative product design in a networked environment (or called networked manufacture, grid manufacture, and cloud manufacture) is an important and also challenging research issue. In order to support collaborative product design in a secure and flexible means, a multi-granularity partial encryption method has been proposed in this paper. Base on the above method, parts of a Computer Aided Design (CAD) model can be selected flexibly by users for encrypting with multi-granularity, according to different users' requirements. The secret keys for the different parts of the CAD model can be customized to meet the requirements of users. Case studies have been developed to demonstrate the effectiveness of the proposed method.

The environmental impact of manufacturing processes is closely associated with energy consumption. Decreasing energy consumption of manufacturing processes can significantly improve the environmental performance of manufacturing to obtain sustainability. However, in most manufacturing process planning and scheduling methods, little attention has been paid to the energy consumption. In this paper, an energy consumption model and a honey-bee mating optimization (HBMO) approach have been developed to take the energy consumption into account as an objective to facilitate sustainable manufacturing process planning and scheduling. In the approach, a honey-bee mating process is simulated to achieve the optimization process where makespan and energy consumption are used as the performance criteria. A case study of process planning and scheduling is given. The experimental results are promising and compare well with the final results of the genetic algorithm based optimization approach.

In 3D collaborative modeling systems, users need a convenient mechanism to repeatedly modify the models they are operating on. In this paper, we contribute a selective undo/redo solution for users to select arbitrary operation to undo. With the consistency maintainence mechanism we proposed, operations need to be re-arranged on each site for after their arriving. Both history buffer and model state stream are adopted to present the arriving sequence of operations and their actual execution sequence. In case of concurrent undo/redo, undo state vector is proposed to make sure that an operation can only be undone once and redone by the designer who undoes it. Based on all the precautions we have made, an undo/redo algorithm is proposed. The algorithm has been verified in the prototype we implemented.

Consistency maintenance is one of the most important problems in collaborative CAD systems. However, existing consistency maintenance mechanisms limit multi-user interaction. This paper presents a consistency maintenance method to gain a less-constrained multi-user interaction. First, the causal relation between modeling operations is preserved using the state vector. Then, the concurrent deletion operations are checked to decide if the current operation is masked. If not, the solution for topological entities' matching is adopted to deal with the operations that use topological entities. Then, for those operations which do not use topological entities, the corresponding mechanism is adopted according to their types. By these mechanisms, the commutative, masked and conflicted relations between the concurrent operations, are explored and the conflicts are solved. The experiments prove that our method can support less-constrained multi-user interaction.

In this paper, we introduce a novel 2D-3D hybrid video stabilization method which combines virtues of 2D and 3D video stabilization methods in one routine. It attempts to achieve high-quality camera motions and to retain full frame coherence in each frame, at while, ensure that local regions undergo a similarity transformation. We solve the stabilization problem by integrating 3D and 2D video stabilization methods into one routine. It smooths camera motions and explicitly employs local motion information which constraints video frames to be temporal coherent, and achieves high-quality video stabilization. Experiments show that our method not only can achieve high-quality camera motion on good 3D reconstructed scene, but also can deal with complicated videos containing near, large moving objects.

This paper introduces an approach to performance animation that uses window-based principal component analysis (WLPCA). Our key idea is to construct a series of local models from a prerecorded motion database and utilize them to construct full-body human motion in a maximum a posteriori frame work. We have demonstrated the effectiveness of our approach by synthesizing a variety of human actions. Given an appropriate motion capture database, the results are comparable in quality to the ground truth data. We have also evaluated the performance of our approach by leave-one-out experiments and by comparing to two baseline algorithms.

In the feature modeling procedure, one-dimensional topological entities (edges) are always used as references or operational objects. Hence, to realize the integration of heterogeneous CAD systems, the corresponding one-dimensional topological entities must be found in the target CAD system to match the source ones. This paper presents a method to gain one-dimensional topological entity matching. The method is based on two algorithms, i.e. combining algorithm and matching algorithm. The combining algorithm is adopted to combine the edges retrieved in a source CAD system. Then, for each combined edge, the matching edges are found by using the matching algorithm in a target CAD system. The experiments prove that our method is valid for both offline and online integrations.

Heterogeneous CAD data exchange is very important in collaborative product development and also extremely difficult. Feature-based data exchange has many advantages than traditional geometry-based data exchange. According to the framework of procedure recovery in feature-based data exchange, this paper discusses the key issues of feature extraction and reconstruction, including the extraction of first-order feature information, extraction of second-order feature information and the reconstruction of feature model. The proposed methods have been tested in experiments. The result shows that propsed approach has efficiently improved the former researches, such as ISO/STEP method, Macro command method and UPR method.

One difference between real-time CSCW systems and traditional distributed systems is that the former one needs to provide a natural, free and fast interface for multi-user interaction. However, typical multi-user interaction methods in 3D CAD systems apply strict consistency maintenance, such as lock mechanism and floor control which result in a stagnant and unnatural interface. This article proposes a semantic-based operational transformation (OT), which is similar to the traditional OT form, to support less constraint multi-user interaction and to achieve consistency in collaborative CAD editing (co-CAD) systems. Major technical contributions of this article include: a 3D semantic priority to select operations from waiting list, an OT strategy to decide OT direction, OT rules and a kernel OT function for co-CAD systems.

How to name the topological entities is the footstone of collaborative modeling systems. This paper presents a method to correspond topological entities in non-quiescent context of replicated collaborative CAD system. The proposed method adopts an automatic undo/do/redo mechanism to restore the definition context of CAD command to achieve a consistent naming mechanism in non-quiescent context.

Undo/Redo can help rolling the whole system back to some previous state. However, many group Undo/Redo researches are based on co-edit system of text object. This paper firstly addresses the Undo/Redo in 3D collaborative solid modeling system. After analysis of the existing Undo/Redo method, this article proposed a multiuser Undo/Redo method in replicated collaborative modeling system. The implementation of the Undo/Redo operation in both local site and remote site is described in detail respectively. In our method, the user's intention can be preserved. The preservation is based on dependency relationship among users at different sites. The proposed approach has been tested in a prototype system with case study.

Data exchange is one of key issues in collaborative design. The purpose of feature-based data exchange is that the target model is editable after being exchanged. This is the reason why nowadays feature-based data exchanges become the research focus beyond the traditional geometry-based data exchange. This paper presents a two-stage mechanism to recover a complete modeling process of a parametric CAD mode in source systems. Therefore, what we exchange is the procedure of modeling steps. In target systems, we use the exchanged procedure to simulate a real human to reconstruct the parametric CAD mode in any heterogeneous CAD systems. The proposed method has been tested with case studies among typical CAD systems, such as SolidWorks, UG, Pro/E and Catia.

From CSCW view, the name issues in replicated collaborative solid modeling involve several fundamental challenges, such as consistency maintenance, multi-user interaction and undo/redo mechanism. Therefore, a consistency and awareness naming approach will contribute to all of above three challenges, either directly or potentially. The paper begins with the multi-user interaction framework in replicated collaborative solid modeling. And then a collaborative name structure is constructed to consistently name merged faces. Finally an awareness method is presented to distinguish which type of operation to create the merged faces. The proposed methods are illustrated with case studies in replicated collaborative solid modeling.

Abstract This paper presents a new exemplar‐based framework for video completion, allowing aesthetically pleasing completion of large space‐time holes. We regard video completion as a discrete global optimization on a 3D graph embedded in the space‐time video volume. We introduce a new objective function which enforces global spatio‐temporal consistency among patches that fill the hole and surrounding it, in terms of both color similarity and motion similarity. The optimization is solved by a novel algorithm, calledweighted priority belief propagation(BP), which alleviates the problems of slow convergence and intolerable storage size when using the standard BP. This objective function can also handle video texture synthesis by extending an input video texture to a larger texture region. Experiments on a wide variety of video examples with complex dynamic scenes demonstrate the advantages of our method over existing techniques: salient structures and motion information are much better restored. Copyright © 2008 John Wiley & Sons, Ltd.

At first, graphics media are abstracted into high level and low level representation. The high level representation includes the design history and feature description. The low level includes topology, geometry and attribution. Secondly, the consistency conditions for different abstracted levels are established. The consistency conditions can be described as strong consistency or weak consistency. They also can be described as strong no-consistency or weak no-consistency. Thirdly, according to layered consistency conditions, different abstracted levels of graphics media are associated with suitable concurrent control methods respectively, which can be strict or relaxed. Fourthly, the strategy how to apply hierarchical consistency model into flexible collaboration transparent infrastructure are analyzed. Finally, we applied the model and methods in our test-bed for collaborative design of engineering graphics.

Name converge is the footstone of converge problem in replicated collaborative solid modeling (CSM). In order to explore name converge in quiescent context, both collaboration status and solid status in replicated CSM are analyzed. Based on the analysis, a details roadmap for name consistency is presented. As part of details roadmap, a name converge method is proposed. The method transforms definition (local) name of a topological entity into execution (remote) name of the entity. The transformation rules utilize both context conditions for transformation and topological position in split faces

A method of multi-user interaction in replicated collaborative solid modeling (CSM) is proposed. New challenges and problems of name consistency are analyzed. A roadmap for name consistency is explored. The roadmap uses a distributed method to correspond topological entities across sites. A faceIndex structure is organized to enable overall corresponding among intervals of interaction steps. A priority point based method is presented to sort exact faceIndex of faces inside each step. The above methods are illustrated with a case study.

A method combining the agent and middleware technology is presented to integrate transparent CAD applications. The method uses both inside and outside encapsulation to wrapper the legacy CAD application. The proposed method has been tested to demonstrate potential advantage than former methods.