Search Results (1,700)

Human interaction recognition (HIR) between two people in videos is a critical field in computer vision and pattern recognition, aimed at identifying and understanding human interaction and actions for applications such as healthcare, surveillance, and human–computer interaction. Despite its significance, video-based HIR faces challenges in achieving satisfactory performance due to the complexity of human actions, variations in motion, different viewpoints, and environmental factors. In the study, we proposed a two-stream deep learning-based HIR system to address these challenges and improve the accuracy and reliability of HIR systems. In the process, two streams extract hierarchical features based on the skeleton and RGB information, respectively. In the first stream, we utilised YOLOv8-Pose for human pose extraction, then extracted features with three stacked LSM modules and enhanced them with a dense layer that is considered the final feature of the first stream. In the second stream, we utilised SAM on the input videos, and after filtering the Segment Anything Model (SAM) feature, we employed integrated LSTM and GRU to extract the long-range dependency feature and then enhanced them with a dense layer that was considered the final feature for the second stream module. Here, SAM was utilised for segmented mesh generation, and ImageNet was used for feature extraction from images or meshes, focusing on extracting relevant features from sequential image data. Moreover, we newly created a custom filter function to enhance computational efficiency and eliminate irrelevant keypoints and mesh components from the dataset. We concatenated the two stream features and produced the final feature that fed into the classification module. The extensive experiment with the two benchmark datasets of the proposed model achieved 96.56% and 96.16% accuracy, respectively. The high-performance accuracy of the proposed model proved its superiority. Full article

Cracks represent one of the most common types of damage in building structures and it is crucial to detect cracks in a timely manner to maintain the safety of the buildings. In general, tiny cracks require focusing on local detail information while complex long cracks and cracks similar to the background require more global features for detection. Therefore, it is necessary for crack detection to effectively integrate local and global information. Focusing on this, a local–global feature adaptive fusion network (LGFAF-Net) is proposed. Specifically, we introduce the VMamba encoder as the global feature extraction branch to capture global long-range dependencies. To enhance the ability of the network to acquire detailed information, the residual network is added as another local feature extraction branch, forming a dual-encoding network to enhance the performance of crack detection. In addition, a multi-feature adaptive fusion (MFAF) module is proposed to integrate local and global features from different branches and facilitate representative feature learning. Furthermore, we propose a building exterior wall crack dataset (BEWC) captured by unmanned aerial vehicles (UAVs) to evaluate the performance of the proposed method used to identify wall cracks. Other widely used public crack datasets are also utilized to verify the generalization of the method. Extensive experiments performed on three crack datasets demonstrate the effectiveness and superiority of the proposed method. Full article

Recently, significant advancements have been made in 3D point cloud analysis by leveraging transformer architecture in 3D space. However, it remains challenging to effectively implement local and global learning within irregular and sparse structures of 3D point clouds. This paper presents the Adaptive Interaction Transformer (AIFormer), a novel hierarchical transformer architecture designed to enhance 3D point cloud analysis by fusing local and global features through the adaptive interaction of features. Specifically, AIFormer mainly consists of several stacked AIFormer Blocks. Each AIFormer module employs the Local Relation Aggregation Module and the Global Context Aggregation Module, respectively, to extract local details of relationships within the reference point and long-range dependencies between reference points. Then, the local and global features are fused using the Adaptive Interaction Module for adaptive interaction to optimize the point representation. Additionally, the AIFormer Block further designs geometric relation functions and contextual relative semantic encoding to enhance local and global feature extraction capabilities, respectively. Extensive experiments on three popular 3D point cloud datasets verify that AIFormer achieves state-of-the-art or comparable performances. Our comprehensive ablation study further validates the effectiveness and soundness of the AIFormer design. Full article

The unique properties of graphene have attracted the interest of researchers from various fields, and the discovery of graphene has sparked a revolution in materials science, specifically in the field of two-dimensional materials. However, graphene synthesis’s costly and complex process significantly impairs researchers’ endeavors to explore its properties and structure experimentally. Molecular dynamics simulation is a well-established and useful tool for investigating graphene’s atomic structure and dynamic behavior at the nanoscale without requiring expensive and complex experiments. The accuracy of the molecular dynamics simulation depends on the potential functions. This work assesses the performance of various potential functions available for graphene in mechanical properties prediction. The following two cases are considered: pristine graphene and pre-cracked graphene. The most popular fifteen potentials have been assessed. Our results suggest that diverse potentials are suitable for various applications. REBO and Tersoff potentials are the best for simulating monolayer pristine graphene, and the MEAM and the AIREBO-m potentials are recommended for those with crack defects because of their respective utilization of the electron density and inclusion of the long-range interaction. We recommend the AIREBO-m potential for a general case of classical molecular dynamics study. This work might help to guide the selection of potentials for graphene simulations and the development of further advanced interatomic potentials. Full article

In computer vision, eliminating the effects of adverse weather conditions such as rain, snow, and fog on images is a key research challenge. Existing studies primarily focus on image restoration for single weather types, while methods addressing image restoration under multiple combined weather conditions remain relatively scarce. Furthermore, current mainstream restoration networks, mostly based on Transformer and CNN architectures, struggle to achieve an effective balance between global receptive field and computational efficiency, limiting their performance in practical applications. This study proposes ACMamba, an end-to-end lightweight network based on selective state space models, aimed at achieving image restoration under multiple weather conditions using a unified set of parameters. Specifically, we design a novel Visual State Space Module (VSSM) and a Spatially Aware Feed-Forward Network (SAFN), which organically combine the local feature extraction capabilities of convolutions with the long-range dependency modeling capabilities of selective state space models (SSMs). This combination significantly improves computational efficiency while maintaining a global receptive field, enabling effective application of the Mamba architecture to multi-weather image restoration tasks. Comprehensive experiments demonstrate that our proposed approach significantly outperforms existing methods for both specific and multi-weather tasks across multiple benchmark datasets, showcasing its efficient long-range modeling potential in multi-weather image restoration tasks. Full article

Change detection (CD) identifies surface changes by analyzing bi-temporal remote sensing (RS) images of the same region and is essential for effective urban planning, ensuring the optimal allocation of resources, and supporting disaster management efforts. However, deep-learning-based CD methods struggle with background noise and pseudo-changes due to local receptive field limitations or computing resource constraints, which limits long-range dependency capture and feature integration, normally resulting in fragmented detections and high false positive rates. To address these challenges, we propose a tree topology Mamba-guided network (TTMGNet) based on Mamba architecture, which combines the Mamba architecture for effectively capturing global features, a unique tree topology structure for retaining fine local details, and a hierarchical feature fusion mechanism that enhances multi-scale feature integration and robustness against noise. Specifically, the a Tree Topology Mamba Feature Extractor (TTMFE) leverages the similarity of pixels to generate minimum spanning tree (MST) topology sequences, guiding information aggregation and transmission. This approach utilizes a Tree Topology State Space Model (TTSSM) to embed spatial and positional information while preserving the global feature extraction capability, thereby retaining local features. Subsequently, the Hierarchical Incremental Aggregation Module is utilized to gradually align and merge features from deep to shallow layers to facilitate hierarchical feature integration. Through residual connections and cross-channel attention (CCA), HIAM enhances the interaction between neighboring feature maps, ensuring that critical features are retained and effectively utilized during the fusion process, thereby enabling more accurate detection results in CD. The proposed TTMGNet achieved F1 scores of 92.31% on LEVIR-CD, 90.94% on WHU-CD, and 77.25% on CL-CD, outperforming current mainstream methods in suppressing the impact of background noise and pseudo-change and more accurately identifying change regions. Full article

Motion blur is a common problem in the field of surveillance scenarios, and it obstructs the acquisition of valuable information. Thanks to the success of deep learning, a sequence of CNN-based architecture has been designed for image deblurring and has made great progress. As another type of neural network, transformers have exhibited powerful deep representation learning and impressive performance based on high-level vision tasks. Transformer-based networks leverage self-attention to capture the long-range dependencies in the data, yet the computational complexity is quadratic to the spatial resolution, which makes transformers infeasible for the restoration of high-resolution images. In this article, we propose an efficient transformer-based deblurring network, named MIMO-Uformer, for vehicle-surveillance scenarios. The distinct feature of the MIMO-Uformer is that the basic-window-based multi-head self-attention (W-MSA) of the Swin transformer is employed to reduce the computational complexity and then incorporated into a multi-input and multi-output U-shaped network (MIMO-UNet). The performance can benefit from the operation of multi-scale images by MIMO-UNet. However, most deblurring networks are designed for global blur, while local blur is more common under vehicle-surveillance scenarios since the motion blur is primarily caused by local moving vehicles. Based on this observation, we further propose an Intersection over Patch (IoP) factor and a supervised morphological loss to improve the performance based on local blur. Extensive experiments on a public and a self-established dataset are carried out to verify the effectiveness. As a result, the deblurring behavior based on PSNR is improved at least 0.21 dB based on GOPRO and 0.74 dB based on the self-established datasets compared to the existing benchmarks. Full article

The measurement and description of the charge-carrier lifetime (${\tau }_{\mathrm{c}}$) is crucial for the wide-ranging applications of lead-halide perovskites. We present time-resolved microwave-detected photoconductivity decay (TRMCD) measurements and a detailed analysis of the possible recombination mechanisms including trap-assisted, radiative, and Auger recombination. We prove that performing injection-dependent measurement is crucial in identifying the recombination mechanism. We present temperature and injection level dependent measurements in CsPbBr₃, which is the most common inorganic lead-halide perovskite. In this material, we observe the dominance of charge-carrier trapping, which results in ultra-long charge-carrier lifetimes. Although charge trapping can limit the effectiveness of materials in photovoltaic applications, it also offers significant advantages for various alternative uses, including delayed and persistent photodetection, charge-trap memory, afterglow light-emitting diodes, quantum information storage, and photocatalytic activity. Full article

Image super-resolution (SR) algorithms based on deep learning yield good visual performances on visible images. Due to the blurred edges and low contrast of infrared (IR) images, methods transferred directly from visible images to IR images have a poor performance and ignore the demands of downstream detection tasks. Therefore, an Inception Dilated Super-Resolution (IDSR) network with multiple branches is proposed. A dilated convolutional branch captures high-frequency information to reconstruct edge details, while a non-local operation branch captures long-range dependencies between any two positions to maintain the global structure. Furthermore, deformable convolution is utilized to fuse features extracted from different branches, enabling adaptation to targets of various shapes. To enhance the detection performance of low-resolution (LR) images, we crop the images into patches based on target labels before feeding them to the network. This allows the network to focus on learning the reconstruction of the target areas only, reducing the interference of background areas in the target areas’ reconstruction. Additionally, a feature-driven module is cascaded at the end of the IDSR network to guide the high-resolution (HR) image reconstruction with feature prior information from a detection backbone. This method has been tested on the FLIR Thermal Dataset and the M3FD Dataset and compared with five mainstream SR algorithms. The final results demonstrate that our method effectively maintains image texture details. More importantly, our method achieves 80.55% mAP, outperforming other methods on FLIR Dataset detection accuracy, and with 74.7% mAP outperforms other methods on M3FD Dataset detection accuracy. Full article

In the context of rapid industrialization, efficiently detecting metal corrosion areas has become a critical task in preventing material damage. Unlike conventional semantic segmentation targets, metal corrosion characteristics vary significantly in color, texture, and size. Traditional image segmentation methods need improvement in scenarios involving occlusions, shadows, and defects. This paper proposes a convolution and sequence encoding combined network, MCD-Net, for metal corrosion area segmentation. First, a visual Transformer sequence encoder is introduced into the convolutional encoder–decoder network to enhance global information processing capabilities and establish long-range feature dependencies. A feature fusion method based on an attention module is proposed to enhance the model’s ability to recognize corrosion boundaries, thereby enhancing segmentation accuracy and model robustness. Finally, in the model’s decoding stage, a score-based multi-scale feature enhancement method is employed to emphasize significant features in the corrosion areas. Experimental results indicate that this method attained an F1 score of 84.53% on a public corrosion dataset, demonstrating the model’s deeper understanding and reasoning capabilities for shadow and defect features, as well as excellent noise resistance performance. Full article

Accurate prediction of PM_2.5 concentrations is essential for public health management, especially in areas affected by long-range pollutant transport. This study presents a hybrid model combining convolutional long short-term memory (ConvLSTM) and deep neural networks (DNNs) to enhance PM_2.5 forecasting in Seoul, South Korea. The hybrid model leverages ConvLSTM’s ability to capture spatiotemporal dependencies and DNN’s strength in feature extraction, enabling it to outperform standalone CMAQ and DNN models. For the T1 forecast (6 h averages), the ConvLSTM-DNN model exhibited superior performance, with an RMSE of 7.2 µg/m³ compared to DNN’s 8.5 µg/m³ and CMAQ’s 10.1 µg/m³. The model also maintained high categorical accuracy (ACC) and probability of detection (POD) for critical PM_2.5 levels while reducing false alarms (FARs), particularly in bad and very bad events. Although its performance decreases over extended forecast periods, the ConvLSTM-DNN model demonstrates its utility as a robust forecasting tool. Future work will focus on optimizing the network structure to improve long-term forecast accuracy. Full article

A model based on the fitting of stress–strain data by tensile tests of bio-composites made of a bioplastic (polybutylene succinate (PBS)) and brewer spent grain filler (BSGF) is developed. Experimental tests were performed for various concentrations of BSGF in the range from 2% to 30%. The model is suitable for describing the elastic–plastic behavior of these materials in terms of two mechanical parameters, tensile stress and tensile stiffness (or Young’s modulus), depending on the filler concentration. The mechanical characteristics, derived from the fit parameters, show good agreement with the experimental data. The mathematical model used here could be an important aid for the experimentation and manufacturing process as it allows the prediction of the mechanical tensile parameters of a mixture with different filler concentrations, avoiding the long and complex preparation cycle of bio-composites, as well as the specific mechanical tests. The physical properties required by the objects created with the PBS–BSGF bio-composite by the partners/stakeholders of the research project co-financing this research can be quite different; therefore, a mathematical model that predicts some of the mechanical properties in terms of the mixture composition may be useful to speed up the selection of the required amount of BSGF in the mixture. Full article

To address the low recognition accuracy of models for coal gangue images in intelligent coal preparation systems—especially in identifying small target coal gangue due to factors such as camera angle changes, low illumination, and motion blur—we propose an improved coal gangue separation model, Yolov8n-improvedGD(GD—Gangue Detection), based on Yolov8n. The optimization strategy includes integrating the GCBlock(Global Context Block) from GCNet(Global Context Network) into the backbone network to enhance the model’s ability to capture long-range dependencies in images and improve recognition performance. The CGFPN (Contextual Guidance Feature Pyramid Network) module is designed to optimize the feature fusion strategy and enhance the model’s feature expression capabilities. The GSConv-SlimNeck architecture is employed to optimize computational efficiency and enhance feature map fusion capabilities, thereby improving the model’s robustness. A 160 × 160 scale detection head is incorporated to enhance the sensitivity and accuracy of small coal and gangue detection, mitigate the effects of low-quality data, and improve target localization accuracy. Full article

Physics-informed neural networks (PINNs) have recently emerged as a promising alternative to traditional numerical methods for solving partial differential equations (PDEs) in fluid dynamics. By using PDE-derived loss functions and auto-differentiation, PINNs can recover solutions without requiring costly simulation data, spatial gridding, or time discretization. However, PINNs often exhibit slow or incomplete convergence, depending on the architecture, optimization algorithms, and complexity of the PDEs. To address these difficulties, a variety of novel and repurposed techniques have been introduced to improve convergence. Despite these efforts, their effectiveness is difficult to assess due to the wide range of problems and network architectures. As a novel test case for PINNs, we propose one-dimensional shallow water equations with closed boundaries, where the solutions exhibit repeated boundary wave reflections. After carefully constructing a reference solution, we evaluate the performance of PINNs across different architectures, optimizers, and special training techniques. Despite the simplicity of the problem for classical methods, PINNs only achieve accurate results after prohibitively long training times. While some techniques provide modest improvements in stability and accuracy, this problem remains an open challenge for PINNs, suggesting that it could serve as a valuable testbed for future research on PINN training techniques and optimization strategies. Full article

The major factors affecting the in vitro immature embryo rescue efficiencies from Prunus persica or P. armeniaca accessions have been identified, along with improving the feasibility. Variations in the woody plant medium (WPM) were used depending on the embryo size. Embryos less than 5 mm long were cultured in WPM supplemented with 1 μM BAP and 1 μM GA₃, while embryos bigger than 5 mm long were cultured in hormone-free medium, with or without vermiculite. The environmental in vitro culture conditions consisted of three phases: a (I) stratification at 4 °C during a 3- to 5-month-long period in the dark, followed by (II) growth of germinated embryos at 14 °C for a 4-week-long period, with 12 h light a day, which favors plantlet development, and finally, (III) growth at 24 °C, with 16 h light a day, until the plantlets were acclimatized in the greenhouse. The germination of smaller embryos, at the end of phase I, ranged from 82.2% to 22.1% for apricots and flat peaches, respectively, whereas for bigger embryos, the germination varied from 97.3% to 53.2% for the same species. The embryo germination for peaches and nectarines ranged from 40.1% to 30.3% for smaller embryos, and from 91.9% to 63.0% for bigger embryos. Endo- and epiphytic contamination, affecting from 7.4% to 52.9% of cultured embryos, depending on the fruit type and conservation conditions, and the capacity to acclimate to soil conditions, ranging from 50.4% to 93.2%, were the two most important factors influencing the protocol’s efficiency and feasibility. Considering the overall efficiencies, expressed as hardened plants transferred to field plots over clean uncontaminated embryo, the values ranged from 55.8% for nectarines, 54.0% for peaches, 45.6% for apricots, and 23.3% for flat fruits. The addition of vermiculite to the culture medium significantly improved the plantlet development, avoiding subculture to fresh medium when an extension of phase III was required before acclimatization. Compared to laboratory glassware, the use of food glass containers with air-permeable sealing film, along with vermiculite-containing medium, significantly reduced the costs when handling the large number of embryos required for breeding programs. Full article