Low-light environments commonly cause significant degradation in image quality, thereby negatively impacting vision-related multimedia retrieval processes. Despite the advent of numerous promising low-light image enhancement techniques, restoring color fidelity and reducing noise while enhancing image brightness remains a non-trivial task. Moreover, the issue of inadequate or overly enhancement in some enhanced images further complicates the matter. To address these challenges, we introduce TLENet, a low light enhancement network based on two-stage training and single-stage testing. Specifically, TLENet first features a Color Illumination Adjustment (CIA) module, which leverages spatial information from the HSV color space to achieve precise color adjustment of images. Then, to mitigate noise amplification, TLENet incorporates a Bilateral Feature Mutual Guidance Denoising (BMGD) module. This module effectively extracts both global and local features, ensuring comprehensive image content restoration, while utilizing advanced attention mechanisms for enhanced denoising capabilities. At last, TLENet incorporates the Illumination Parameter Adaptation (IPA) module to accomplish adaptive lighting enhancement during testing. We conducted extensive quantitative and qualitative experiments on the LOLv2 and LSRW datasets, and the results showed that TLENet significantly outperformed state-of-the-art methods while requiring fewer parameters and lower computational complexity. Specifically, TLENet achieves 24.31 dB (PSNR) and 0.863 (SSIM) on the LOLv2 dataset, surpassing the second-best method(RetinexFormer & SNRNet ) by 1.51 dB (PSNR) and 0.014 (SSIM). Similarly, it achieves 20.34 dB (PSNR) and 0.573 (SSIM) on the LSRW dataset, surpassing the second-best method(LCDBNet) by 1.03 dB (PSNR) and 0.013 (SSIM). And TLENet only has 0.16M parameters and 17.01G FLOPS.

Scene flow estimation, which aims to predict point-wise displacement in 3-D space from sequential data, is a challenging task with wide application in fields such as robotics and autonomous driving. Currently, the accuracy of scene flow estimation from sparse point clouds using prior-based models is suboptimal. Therefore, we revisit the point-by-point scene flow prior and propose a multiscale neighborhood cluster scene flow prior (MNCSFP) to enhance the accuracy of scene flow estimation in sparse point clouds. We optimize the prior model utilizing the multiscale neighborhood cluster feature of the point cloud, in which the point neighborhood is constructed only once. According to the neighborhood index (NI), we design a multiscale neighborhood cluster feature construction (MNCFC) module. The MNCFC module rapidly constructs multiscale neighborhood cluster features using a Gaussian-based neighborhood feature normalization (GNFN) strategy to improve the representation of neighborhood cluster characteristics. Moreover, we propose a neighborhood cluster weighted aggregation (NCWA) module to encode neighborhood cluster features. In NCWA, we design the logsoft function to calculate the neighborhood cluster weights and complete the extraction and aggregation of neighborhood cluster features. Furthermore, we design the multiscale feature fusion (MFF) module that combines the symmetry operation and the logsoft function to complete the fusion of multiscale features to enhance the sparse point feature stability. We evaluate our method on samples from the KITTI, Argoverse, nuScenes, and Waymo Open datasets and demonstrate that it outperforms existing methods and achieves advanced performance.

In recent years, there has been a notable increase in interest in image-based surface normal estimation. These approaches are capable of predicting the surface normal of real scenes using only an image, thereby facilitating a more profound comprehension of the actual scene and providing assistance with other perceptual tasks. However, dense regression predictions are susceptible to misdirection when encountering intricate details, which presents a paradoxical challenge for image-based surface normal estimation in reconciling detail and density. By introducing quaternion rotations as fusion module with geometric property, we propose a quaternion-based refined network structure that fuses detailed and structural information. Specifically, we design a high-resolution surface normal baseline with a streamlined structure, to extract fine-grained features while reducing the angular error in surface normal regression values caused by downsampling. Additionally, we propose a subtle angle loss function that prevents subtle changes from being overlooked without extra information, further enhancing the model's ability to learn detailed information. The proposed method demonstrates state-of-the-art performance compared to existing techniques on three real-world datasets comprising indoor and outdoor scenes. The results demonstrate the robust effectiveness of our deep learning approach that incorporates geometric prior guidance, highlighting improved robustness in applying deep learning methods. The source code will be released upon acceptance.

Coarse-to-fine schemes are widely used in traditional single-image motion deblur; however, in the context of deep learning, existing multi-scale algorithms not only require the use of complex modules for feature fusion of low-scale RGB images and deep semantics, but also manually generate low-resolution pairs of images that do not have sufficient confidence. In this work, we propose a multi-scale network based on single-input and multiple-outputs(SIMO) for motion deblurring. This simplifies the complexity of algorithms based on a coarse-to-fine scheme. To alleviate restoration defects impacting detail information brought about by using a multi-scale architecture, we combine the characteristics of real-world blurring trajectories with a learnable wavelet transform module to focus on the directional continuity and frequency features of the step-by-step transitions between blurred images to sharp images. In conclusion, we propose a multi-scale network with a learnable discrete wavelet transform (MLWNet), which exhibits state-of-the-art performance on multiple real-world deblurred datasets, in terms of both subjective and objective quality as well as computational efficiency. Our code is available on https://github.com/thqiu0419/MLWNet.

Cooperative LiDAR systems integrating vehicles and road infrastructure, termed V2I calibration, exhibit substantial potential, yet their deployment encounters numerous challenges. A pivotal aspect of ensuring data accuracy and consistency across such systems involves the calibration of LiDAR units across heterogeneous vehicular and infrastructural endpoints. This necessitates the development of calibration methods that are both real-time and robust, particularly those that can ensure robust performance in urban canyon scenarios without relying on initial positioning values. Accordingly, this paper introduces a novel approach to V2I calibration, leveraging spatial association information among perceived objects. Central to this method is the innovative Overall Intersection over Union (oIoU) metric, which quantifies the correlation between targets identified by vehicle and infrastructure systems, thereby facilitating the real-time monitoring of calibration results. Our approach involves identifying common targets within the perception results of vehicle and infrastructure LiDAR systems through the construction of an affinity matrix. These common targets then form the basis for the calculation and optimization of extrinsic parameters. Comparative and ablation studies conducted using the DAIR-V2X dataset substantiate the superiority of our approach. For further insights and resources, our project repository is accessible at https://github.com/MassimoQu/v2i-calib.

Driving behavior classification is a critical component of social transportation systems and advanced driver assistance systems, and it has gained increasing attention in recent years. Accurate classification algorithms for driving behavior play a significant role in enhancing traffic safety, energy conservation, and related fields. In this article, we propose a novel driving behavior classification network named feature-attention-embedding-based multimodal-fusion driving-behavior-classification network (FMDNet). FMDNet incorporates eight types of data, including acceleration along the x-axis, y-axis, z-axis, roll angle, pitch angle, yaw angle, roadside image, and vehicle speed, to classify driving behavior. To effectively fuse features extracted from different modalities, taking into account their varying importance, we introduce the feature attention embedding-based fusion module (FAEF) as our fusion strategy. This fusion strategy enhances the network's capability to capture meaningful features by incorporating two feature attention embedding units that delve deeper into the interplay between different modes. Furthermore, we provide further validation of the effectiveness of our approach through extensive ablation experiments to investigate and analyze the impact of various modal data on the classification of driving behavior. Our proposed FMDNet achieves state-of-the-art performance on the public UAH-DriveSet dataset, demonstrating its effectiveness with an impressive F1-score of 99.0%. Additionally, the robustness of our model is confirmed on distracted dataset, achieving a remarkable F1-score of 99.7%. The model's outstanding performance on both the UAH-DriveSet dataset and the distracted-dataset highlights its capabilities and potential for real-world applications.https://github.com/Wenzhuo-Liu/FMDNet

Coal and gas outbursts classification has become more important than before due to the serious threat to the safety of coal production, in this paper, we proposed a novel combination model consists of feature decomposition and reconstruction, feature selection and feature extraction for classification of coal and gas outbursts. First, EMD is used to decompose the coal and gas outbursts index features into a number of different IMFS; Second, in order to find out the relevance of IMFS with regard to the features, a wrapper algorithm Boruta with the RF classifier is employed, and the IMFS which has high relevance with the feature are selected to form a new index feature, then the new obtained features construct new influencing factors that affect coal and gas outbursts; Furtherly, in order to eliminate the redundancy between the new generated features and the uncorrelation between the index features and outbursts, the LDA is used to extract the features with class differentiation. Finally, the SVM classifiers based on the optimal parameters by Bayesian optimisation algorithm is employed to evaluate the proposed feature extraction scheme. Experimental results show that the proposed comprehensive model can achieve significant performance in terms of classification accuracy and feature size compared to existing methods for coal and gas outbursts classification.

Abstract Coal‐rock fracture evolution has a key role in coal seam permeability. Due to the randomness and uncertainty of coal‐rock fractures, the prediction of fracture evolution is difficult and challenging. In this paper, the authors propose a dynamic‐difference based generative adversarial network (DDGAN) for coal‐rock fracture evolution prediction. Firstly, the spatial‐feature encoder and the dynamic‐difference encoder are proposed to capture the spatial features and the dynamic fracture evolution information independently. And a channel‐attention (CA) module is presented to enhance the contribution of fracture evolution details information in the dynamic‐difference encoder. Then, a multi‐scale fusion (MSF) module is proposed to fuse the spatial features and the dynamic‐difference features, which benefits to refine the detailed structure during decoding. Final, the compound objective function is employed to supervise and guide the network to achieve coal‐rock fracture evolution predictions. Compared with the state‐of‐the‐art methods, extensive experiment results demonstrate that the authors’ model can achieve better performance for the task of coal‐rock fracture evolution prediction.

Mobile crowdsensing (MCS) booms the implementation of the Internet of Things (IoT) in different areas due to flexibility and low deployment cost. However, collecting sufficient high quality sensing data is crucial for the success of various applications. Incentive mechanism design plays a critical role in the successful implementation of mobile MCS systems. Most of existing work consider that the platform exactly knows the trajectory of mobile users. However, in most cases, it is difficult to obtain the accurate information of the location of mobile users due to either privacy issue or the lack of information. In this article, we consider nondeterministic mobility of mobile users, where only the probability distribution of users’ mobility is available. We design an effective mechanism to achieve the quality data collection with the objective of maximizing the expected social welfare. Simulation results show that the proposed mechanism achieves her expected social welfare compared with four existing schemes, while satisfying truthfulness, individual rationality, and computational efficiency.

In Mobile Crowd Sensing (MCS), mobile users usually can be both the contributor of sensing data and the customer of the service provided by the data collector or service provider. Most of existing work does not consider the dual-role of mobile users in MCS. In this work, by jointly considering users' dual-role as both the contributor of sensing data and the customer of service, we design a Lyapunov based online algorithm to achieve the stability of dynamic MCS system while maximizing the platform utility. Meanwhile, we demonstrate the impacts of parameter on the balance of these two roles of mobile users. Simulation results show that the proposed method outperforms some existing methods in terms of achieved platform utility and system stability. In addition, it is proved that, the time-averaged platform utility could converge to the maximum benchmark asymptotically.

This article aims to extend the theory of Lie subgroups and symmetric subspaces for studying an important class of submanifolds of the special Euclidean group SE(3) whose tangent space at each point on the submanifold relates to that at the identity by an adjoint map. These submanifolds, which we call adjoint-invariant submanifolds in this article, are known in the literature as persistent submanifolds, since they are strictly related to the concept of persistent screw systems. The difference is that in this article, just as Lie subgroups and symmetric subspaces, we put forward adjoint-invariant submanifolds as independent geometric objects from mechanisms and their associated local screw systems. Adjoint invariance relaxes the strict left and right invariance of Lie subgroups and the reflective invariance of symmetric subspaces by allowing generic moving reference frame in the aforementioned adjoint map. It turns out such adjoint invariance can be studied under the framework of distributions on manifolds, which allows us to explore global geometric properties of adjoint-invariant submanifolds. We classify adjoint-invariant submanifolds into reflective-type and product-type submanifolds and derive the conditions for their adjoint invariance. We then propose geometric methods and algorithms for synthesizing the kinematic generators for reflective-type submanifolds, as demonstrated with a number of examples.

In this paper, we consider the nondeterministic mobility of mobile users, where the platform only has the probability distribution about users' mobility. We design an effective mechanism to achieve high quality data collection with the objective of maximizing the expected social welfare. Simulation results show the better performance of the proposed mechanism compared with four counterparts. In addition, the proposed mechanism also satisfies truthfulness and individual rationality.

Fast and accurate identification of the peptides with anticancer activity potential from large-scale proteins is currently a challenging task. In this study, we propose a new machine learning predictor, namely, ACPred-Fuse, that can automatically and accurately predict protein sequences with or without anticancer activity in peptide form. Specifically, we establish a feature representation learning model that can explore class and probabilistic information embedded in anticancer peptides (ACPs) by integrating a total of 29 different sequence-based feature descriptors. In order to make full use of various multiview information, we further fused the class and probabilistic features with handcrafted sequential features and then optimized the representation ability of the multiview features, which are ultimately used as input for training our prediction model. By comparing the multiview features and existing feature descriptors, we demonstrate that the fused multiview features have more discriminative ability to capture the characteristics of ACPs. In addition, the information from different views is complementary for the performance improvement. Finally, our benchmarking comparison results showed that the proposed ACPred-Fuse is more precise and promising in the identification of ACPs than existing predictors. To facilitate the use of the proposed predictor, we built a web server, which is now freely available via http://server.malab.cn/ACPred-Fuse.

In order to investigate the relationship between IT application maturity and management capabilities, the authors conducted a survey study to collect related company information for analysis. Data processing was conducted to obtain valid and reliable variables representing IT application maturity, management institutional capability, and process management capability. Then, they adopted a partial differential equation approach to capture the time dynamics of these variables. The equations were solved analytically, and further empirically estimated through our processed survey data. The validated model demonstrates that both management capabilities have direct enhancement effects on IT application maturity. In addition, process management capability has a greater influence on IT application maturity in comparison with management institutional capability. Furthermore, it is found that there exist local maximums for both enhancement effects, provided that the two management capabilities are well balanced. The findings not only offer practical implications, but also supplement the literature of factors for IS success in light of the dynamic relationship between IT application maturity and management capabilities.

A key problem in online social networks is the identification of users' link information and the analysis of how these are reflected in the recommender systems. The basis to tackle this issue is user similarity measures. In this paper, we propose non-negative multiple matrix factorization with social similarity for recommender systems, considering the similarities between users, the relationships of users-resources and tags-resources. On this basis, we comparatively analyzed different performances of the recommendation with every similarity measure between users. In addition, our method can also recommend friends, resources, and tags to users. Experimental results on Lastfm and Delicious datasets show that the proposed method can significantly improve the recommendation accuracy compared with the art collaborative filtering methods.

Effective patch management is critical to ensure the security of information systems that modern organizations count on today. Facing numerous patch releases from vendors, an information technology (IT) manager must weigh the costs of frequent patching against the security risks that can arise from delays in patch application. To this end, we develop a rigorous quantitative framework to analyze and compare several patching policies that are of practical interest. Our analyses of pure policies—policies that rely on a single metric such as elapsed time or patch severity level—show that certain policies are never optimal and no single policy may fit all information systems uniformly well. Depending on the context parameters, particularly the setup and business disruption costs for patching, either a time-based approach or an approach based on the cumulative severity level may be effective. To develop a more complete guideline for policy selection, we decipher hybrid policies that combine multiple metrics. Finally, we conduct extensive numerical experiments to verify the robustness of our analytical results. Overall, our paper establishes a comprehensive framework for analyzing various patching policies and furnishes useful insights for IT managers.