Classical computation of electronic properties in large-scale materials remains challenging.Quantum computation has the potential to offer advantages in memory footprint and computational scaling.However,general and v...Classical computation of electronic properties in large-scale materials remains challenging.Quantum computation has the potential to offer advantages in memory footprint and computational scaling.However,general and viable quantum algorithms for simulating large-scale materials are still limited.We propose and implement random-state quantum algorithms to calculate electronic-structure properties of real materials.Using a random state circuit on a small number of qubits,we employ real-time evolution with first-order Trotter decomposition and Hadamard test to obtain electronic density of states,and we develop a modified quantum phase estimation algorithm to calculate real-space local density of states via direct quantum measurements.Furthermore,we validate these algorithms by numerically computing the density of states and spatial distributions of electronic states in graphene,twisted bilayer graphene quasicrystals,and fractal lattices,covering system sizes from hundreds to thousands of atoms.Our results manifest that the random-state quantum algorithms provide a general and qubit-efficient route to scalable simulations of electronic properties in large-scale periodic and aperiodic materials.展开更多
The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditio...The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditional approaches like network compression,quantization,and lightweight design often sacrifice accuracy or feature representation robustness.This article introduces the Fast Multi-scale Channel Shuffling Network(FMCSNet),a novel lightweight detection model optimized for mobile devices.FMCSNet integrates a fully convolutional Multilayer Perceptron(MLP)module,offering global perception without significantly increasing parameters,effectively bridging the gap between CNNs and Vision Transformers.FMCSNet achieves a delicate balance between computation and accuracy mainly by two key modules:the ShiftMLP module,including a shift operation and an MLP module,and a Partial group Convolutional(PGConv)module,reducing computation while enhancing information exchange between channels.With a computational complexity of 1.4G FLOPs and 1.3M parameters,FMCSNet outperforms CNN-based and DWConv-based ShuffleNetv2 by 1%and 4.5%mAP on the Pascal VOC 2007 dataset,respectively.Additionally,FMCSNet achieves a mAP of 30.0(0.5:0.95 IoU threshold)with only 2.5G FLOPs and 2.0M parameters.It achieves 32 FPS on low-performance i5-series CPUs,meeting real-time detection requirements.The versatility of the PGConv module’s adaptability across scenarios further highlights FMCSNet as a promising solution for real-time mobile object detection.展开更多
In conventional higher-order topological insulators(HOTIs),the emergence of topological states can be explained by using the nonzero bulk polarization index.However,corner states emerge in HOTIs with incomplete bounda...In conventional higher-order topological insulators(HOTIs),the emergence of topological states can be explained by using the nonzero bulk polarization index.However,corner states emerge in HOTIs with incomplete boundary unit cells(i.e.,boundary defects)even though the bulk polarization is zero,which challenges the conventional understanding of HOTIs.Here,based on a Kekul´e-distorted honeycomb lattice with incomplete unit cells,we reveal that incomplete unit cells exhibit fractional charges through the analysis of Wannier centers by developing a compensation method and creating the concept of Wannier center domain(WCD)which is the smallest region that one Wannier center occupies.This method compensates for the missing parts of these boundary incomplete unit cells with additional WCDs to make them complete.The compensated WCDs automatically carry the corresponding charge,and this charge together with that of the incomplete unit cell constitutes the total charge of the complete unit cell after compensation.We conclude that the emergence of corner states is attributed to the filling anomaly,which is a fundamental mechanism.Our results refresh the understanding of HOTIs,especially those with structural discontinuities,and provide a novel design for topological states which have application value in producing optical functional devices.展开更多
To address the issues of frequent identity switches(IDs)and degraded identification accuracy in multi object tracking(MOT)under complex occlusion scenarios,this study proposes an occlusion-robust tracking framework ba...To address the issues of frequent identity switches(IDs)and degraded identification accuracy in multi object tracking(MOT)under complex occlusion scenarios,this study proposes an occlusion-robust tracking framework based on face-pedestrian joint feature modeling.By constructing a joint tracking model centered on“intra-class independent tracking+cross-category dynamic binding”,designing a multi-modal matching metric with spatio-temporal and appearance constraints,and innovatively introducing a cross-category feature mutual verification mechanism and a dual matching strategy,this work effectively resolves performance degradation in traditional single-category tracking methods caused by short-term occlusion,cross-camera tracking,and crowded environments.Experiments on the Chokepoint_Face_Pedestrian_Track test set demonstrate that in complex scenes,the proposed method improves Face-Pedestrian Matching F1 area under the curve(F1 AUC)by approximately 4 to 43 percentage points compared to several traditional methods.The joint tracking model achieves overall performance metrics of IDF1:85.1825%and MOTA:86.5956%,representing improvements of 0.91 and 0.06 percentage points,respectively,over the baseline model.Ablation studies confirm the effectiveness of key modules such as the Intersection over Area(IoA)/Intersection over Union(IoU)joint metric and dynamic threshold adjustment,validating the significant role of the cross-category identity matching mechanism in enhancing tracking stability.Our_model shows a 16.7%frame per second(FPS)drop vs.fairness of detection and re-identification in multiple object tracking(FairMOT),with its cross-category binding module adding aboute 10%overhead,yet maintains near-real-time performance for essential face-pedestrian tracking at small resolutions.展开更多
Automated classification of gas flow states in blast furnaces using top-camera imagery typically demands a large volume of labeled data,whose manual annotation is both labor-intensive and cost-prohibitive.To mitigate ...Automated classification of gas flow states in blast furnaces using top-camera imagery typically demands a large volume of labeled data,whose manual annotation is both labor-intensive and cost-prohibitive.To mitigate this challenge,we present an enhanced semi-supervised learning approach based on the Mean Teacher framework,incorporating a novel feature loss module to maximize classification performance with limited labeled samples.The model studies show that the proposed model surpasses both the baseline Mean Teacher model and fully supervised method in accuracy.Specifically,for datasets with 20%,30%,and 40%label ratios,using a single training iteration,the model yields accuracies of 78.61%,82.21%,and 85.2%,respectively,while multiple-cycle training iterations achieves 82.09%,81.97%,and 81.59%,respectively.Furthermore,scenario-specific training schemes are introduced to support diverse deployment need.These findings highlight the potential of the proposed technique in minimizing labeling requirements and advancing intelligent blast furnace diagnostics.展开更多
BACKGROUND The prevalence of negative emotional states,such as anxiety and depression,has increased annually.Although personal habits are known to influence emotional regulation,the precise mechanisms underlying this ...BACKGROUND The prevalence of negative emotional states,such as anxiety and depression,has increased annually.Although personal habits are known to influence emotional regulation,the precise mechanisms underlying this relationship remain unclear.AIM To investigate emotion regulation habits impact on students negative emotions during lockdown,using the coronavirus disease 2019 pandemic as a case example.METHODS During the coronavirus disease 2019 lockdown,an online cross-sectional survey was conducted at a Chinese university.Emotional states were assessed using the Depression,Anxiety,and Stress Scale-21(DASS-21),while demographic data and emotion regulation habits were collected concurrently.Data analysis was performed using SPSS version 27.0 and includedχ^(2)-tests for intergroup comparisons,Spearman’s rank-order correlation coefficient analysis to examine associations,and stepwise linear regression modeling to explore the relationships between emotion regulation habits and emotional states.Statistical significance was set atα=0.05.RESULTS Among the 494 valid questionnaires analyzed,the prevalence rates of negative emotional states were as follows:Depression(65.0%),anxiety(69.4%),and stress(50.8%).DASS-21 scores(mean±SD)demonstrated significant symptomatology:Total(48.77±34.88),depression(16.21±12.18),anxiety(14.90±11.91),and stress(17.64±12.07).Significant positive intercorrelations were observed among all DASS-21 subscales(P<0.01).Regression analysis identified key predictors of negative emotions(P<0.05):Risk factors included late-night frequency and academic pressure,while protective factors were the frequency of parental contact and the number of same-gender friends.Additionally,compensatory spending and binge eating positively predicted all negative emotion scores(β>0,P<0.01),whereas appropriate recreational activities negatively predicted these scores(β<0,P<0.01).CONCLUSION High negative emotion prevalence occurred among confined students.Recreational activities were protective,while compensatory spending and binge eating were risk factors,necessitating guided emotion regulation.展开更多
With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods ...With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.展开更多
With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State I...With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State Information(CSI)offers fine-grained temporal,frequency,and spatial insights into multipath propagation,making it a crucial data source for human-centric sensing.Recently,the integration of deep learning has significantly improved the robustness and automation of feature extraction from CSI in complex environments.This paper provides a comprehensive review of deep learning-enhanced human sensing based on CSI.We first outline mainstream CSI acquisition tools and their hardware specifications,then provide a detailed discussion of preprocessing methods such as denoising,time–frequency transformation,data segmentation,and augmentation.Subsequently,we categorize deep learning approaches according to sensing tasks—namely detection,localization,and recognition—and highlight representative models across application scenarios.Finally,we examine key challenges including domain generalization,multi-user interference,and limited data availability,and we propose future research directions involving lightweight model deployment,multimodal data fusion,and semantic-level sensing.展开更多
Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone t...Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.展开更多
Superconducting elect rides have attracted growing attention for their potential to achieve high superconducting transition temperatures(T_(C))under pressure.However,many known elect rides are chemically reactive and ...Superconducting elect rides have attracted growing attention for their potential to achieve high superconducting transition temperatures(T_(C))under pressure.However,many known elect rides are chemically reactive and unstable,making high-quality single-crystal growth,characterization,and measurements difficult,and most do not exhibit superconductivity at ambient pressure.In contrast,La_(3) In stands out for its ambient-pressure superconductivity(T_(C)∼9.4 K)and the availability of high-quality single crystals.Here,we investigate its low-energy electronic structure using angle-resolved photoemission spectroscopy and first-principles calculations.The bands near the Fermi energy(E_(F))are mainly derived from La 5d and In 5p orbitals.A saddle point is directly observed at the Brillouin zone(BZ)boundary,while a three-dimensional Van Hove singularity crosses E_(F) at the BZ corner.First-principles calculations further reveal topological Dirac surface states within the bulk energy gap above E_(F).The coexistence of a high density of states and in-gap topological surface states near𝐸F suggests that La3In offers a promising platform for tuning superconductivity and exploring possible topological superconducting phases through doping or external pressure.展开更多
The hybridization gap in strained-layer InAs/In_(x)Ga_(1−x) Sb quantum spin Hall insulators(QSHIs)is significantly enhanced compared to binary InAs/GaSb QSHI structures,where the typical indium composition,x,ranges be...The hybridization gap in strained-layer InAs/In_(x)Ga_(1−x) Sb quantum spin Hall insulators(QSHIs)is significantly enhanced compared to binary InAs/GaSb QSHI structures,where the typical indium composition,x,ranges between 0.2 and 0.4.This enhancement prompts a critical question:to what extent can quantum wells(QWs)be strained while still preserving the fundamental QSHI phase?In this study,we demonstrate the controlled molecular beam epitaxial growth of highly strained-layer QWs with an indium composition of x=0.5.These structures possess a substantial compressive strain within the In_(0.5)Ga_(0.5)Sb QW.Detailed crystal structure analyses confirm the exceptional quality of the resulting epitaxial films,indicating coherent lattice structures and the absence of visible dislocations.Transport measurements further reveal that the QSHI phase in InAs/In_(0.5)Ga_(0.5)Sb QWs is robust and protected by time-reversal symmetry.Notably,the edge states in these systems exhibit giant magnetoresistance when subjected to a modest perpendicular magnetic field.This behavior is in agreement with the𝑍2 topological property predicted by the Bernevig–Hughes–Zhang model,confirming the preservation of topologically protected edge transport in the presence of enhanced bulk strain.展开更多
Although intermediate temperature solid oxide fuel cells(IT-SOFCs)show great potential to address energy conversion challenges,the sluggish oxygen reduction reaction(ORR)kinetics of cathode materials has severely hind...Although intermediate temperature solid oxide fuel cells(IT-SOFCs)show great potential to address energy conversion challenges,the sluggish oxygen reduction reaction(ORR)kinetics of cathode materials has severely hindered extended applications.Herein,we have demonstrated that Bi^(3+)doping on the A-site synergistically regulates the phase transition and electron spin state in La_(0.3)Bi_(0.3)Ca_(0.4)FeO_(3-δ)(LBCF3)for improved performance.An orthorhombic to cubic phase transition occurred with Bi^(3+)doping increases oxygen vacancy concentration and thus increases oxygen ion migration capacity.Simultaneously,the change of Fe from low to medium electron spin state strengths O_(2)adsorption and improves catalytic performances.Consequently,a peak power density improvement up to 48%(from 1.21 to 1.79 W·cm^(-2))at 800℃ is realized in the anodesupported single cell using LBCF3 as cathode,which remains stable for over 270 h at 750℃.展开更多
An adaptive unscented Kalman filter(AUKF)and an augmented state method are employed to estimate the timevarying parameters and states of a kind of nonlinear high-speed objects.A strong tracking filter is employed to i...An adaptive unscented Kalman filter(AUKF)and an augmented state method are employed to estimate the timevarying parameters and states of a kind of nonlinear high-speed objects.A strong tracking filter is employed to improve the tracking ability and robustness of unscented Kalman filter(UKF)when the process noise is inaccuracy,and wavelet transform is used to improve the estimate accuracy by the variance of measurement noise.An augmented square-root framework is utilized to improve the numerical stability and accuracy of UKF.Monte Carlo simulations and applications in the rapid trajectory estimation of hypersonic artillery shells confirm the effectiveness of the proposed method.展开更多
Wide swath Synthetic Aperture Radar (SAR) images acquired over sea areas contain a variety of information regarding small scale and mesoscale phenomena in the ocean and marine boundary layer e.g. spills, slicks, surfa...Wide swath Synthetic Aperture Radar (SAR) images acquired over sea areas contain a variety of information regarding small scale and mesoscale phenomena in the ocean and marine boundary layer e.g. spills, slicks, surface or internal waves, eddies, oceanic fronts. One of most challenging processing step is to create image objects describing these phenomena on SAR images. The most significant problem in the wide swath images is the backscattering trend at the range direction, which results a progressive brightness reduction over images from near to far range. This reduction affects the detection and classification of sea surface features on wide swath SAR images and a normalization step is needed in a certain incidence angle for compensating the brightness reduction. The aim of the present paper is to investigate the result of image normalization to a set of Wide Swath Mode SAR images. Dark areas were initially detected in SAR images using thresholds, adapted or not. Afterwards, SAR images were normalized and a global threshold was calculated for each image. Images were segmented and objects were created for each dark area. The results were compared to a reference dataset created from theoretical modeled values and extracted in a GIS environment. Results clearly indicate that overall accuracy of the detected dark areas has been increased after normalization. On the contrary, local thresholds were insufficient in producing acceptable results. The proposed normalization can be used as a pre-processing step in image classification.展开更多
Dynamic nonlinearities of C70/toluene solution are measured and analysed by an improved picosecond timeresolved pump-probe system based on a nonlinear imaging technique with phase object. The photophysical parameters ...Dynamic nonlinearities of C70/toluene solution are measured and analysed by an improved picosecond timeresolved pump-probe system based on a nonlinear imaging technique with phase object. The photophysical parameters are determined by the five-level model, which is adopted to interpret the experimental data. The change of refraction index per unit density of the excited state obtained by a numerically simulation is a critical factor to determine the nonlinear behaviour of C70 in picosecond time regime.展开更多
This paper devises a scheme which can discover the state association rules of process object. The scheme aims to dig the hidden close relationships of different links in process object. We adopt a method based on diff...This paper devises a scheme which can discover the state association rules of process object. The scheme aims to dig the hidden close relationships of different links in process object. We adopt a method based on difference and extremum to compute the timing. Clustering is used to classifying the adjusted data, and the next is associating the clusters. Based on the rules of clusters, we produce the rules of links. Association degrees between each two links can be determined. It is easy to get association chains according to the degree. The state association rules that can be obtained in accordance with association rules are the final results. Some industry guidance can be directly summarized from the state association rules, and we can apply the guidance to improve the efficiency of production and operational in allied industries.展开更多
We propose a method for imaging a periodic moving/state-changed object based on computational ghost imaging with Hadamard speckle patterns and a slow bucket detector, named as PO-HCGI. In the scheme, speckle patterns ...We propose a method for imaging a periodic moving/state-changed object based on computational ghost imaging with Hadamard speckle patterns and a slow bucket detector, named as PO-HCGI. In the scheme, speckle patterns are produced from a part of each row of a Hadamard matrix. Then, in each cycle, multiple speckle patterns are projected onto the periodic moving/state-changed object, and a bucket detector with a slow sampling rate records the total intensities reflected from the object as one measurement. With a series of measurements, the frames of the moving/state-changed object can be obtained directly by the second-order correlation function based on the Hadamard matrix and the corresponding bucket detector measurement results. The experimental and simulation results demonstrate the validity of the PO-HCGI. To the best of our knowledge, PO-HCGI is the first scheme that can image a fast periodic moving/state-changed object by computational ghost imaging with a slow bucket detector.展开更多
Precisely estimating the state of health(SOH)of lithium-ion batteries is essential for battery management systems(BMS),as it plays a key role in ensuring the safe and reliable operation of battery systems.However,curr...Precisely estimating the state of health(SOH)of lithium-ion batteries is essential for battery management systems(BMS),as it plays a key role in ensuring the safe and reliable operation of battery systems.However,current SOH estimation methods often overlook the valuable temperature information that can effectively characterize battery aging during capacity degradation.Additionally,the Elman neural network,which is commonly employed for SOH estimation,exhibits several drawbacks,including slow training speed,a tendency to become trapped in local minima,and the initialization of weights and thresholds using pseudo-random numbers,leading to unstable model performance.To address these issues,this study addresses the challenge of precise and effective SOH detection by proposing a method for estimating the SOH of lithium-ion batteries based on differential thermal voltammetry(DTV)and an SSA-Elman neural network.Firstly,two health features(HFs)considering temperature factors and battery voltage are extracted fromthe differential thermal voltammetry curves and incremental capacity curves.Next,the Sparrow Search Algorithm(SSA)is employed to optimize the initial weights and thresholds of the Elman neural network,forming the SSA-Elman neural network model.To validate the performance,various neural networks,including the proposed SSA-Elman network,are tested using the Oxford battery aging dataset.The experimental results demonstrate that the method developed in this study achieves superior accuracy and robustness,with a mean absolute error(MAE)of less than 0.9%and a rootmean square error(RMSE)below 1.4%.展开更多
Dear Editor,This letter focuses on the fact that small objects with few pixels disappear in feature maps with large receptive fields, as the network deepens, in object detection tasks. Therefore, the detection of dens...Dear Editor,This letter focuses on the fact that small objects with few pixels disappear in feature maps with large receptive fields, as the network deepens, in object detection tasks. Therefore, the detection of dense small objects is challenging.展开更多
Drone-based small object detection is of great significance in practical applications such as military actions, disaster rescue, transportation, etc. However, the severe scale differences in objects captured by drones...Drone-based small object detection is of great significance in practical applications such as military actions, disaster rescue, transportation, etc. However, the severe scale differences in objects captured by drones and lack of detail information for small-scale objects make drone-based small object detection a formidable challenge. To address these issues, we first develop a mathematical model to explore how changing receptive fields impacts the polynomial fitting results. Subsequently, based on the obtained conclusions, we propose a simple but effective Hybrid Receptive Field Network (HRFNet), whose modules include Hybrid Feature Augmentation (HFA), Hybrid Feature Pyramid (HFP) and Dual Scale Head (DSH). Specifically, HFA employs parallel dilated convolution kernels of different sizes to extend shallow features with different receptive fields, committed to improving the multi-scale adaptability of the network;HFP enhances the perception of small objects by capturing contextual information across layers, while DSH reconstructs the original prediction head utilizing a set of high-resolution features and ultrahigh-resolution features. In addition, in order to train HRFNet, the corresponding dual-scale loss function is designed. Finally, comprehensive evaluation results on public benchmarks such as VisDrone-DET and TinyPerson demonstrate the robustness of the proposed method. Most impressively, the proposed HRFNet achieves a mAP of 51.0 on VisDrone-DET with 29.3 M parameters, which outperforms the extant state-of-the-art detectors. HRFNet also performs excellently in complex scenarios captured by drones, achieving the best performance on the CS-Drone dataset we built.展开更多
基金supported by the Major Project for the Integration of ScienceEducation and Industry (Grant No.2025ZDZX02)。
文摘Classical computation of electronic properties in large-scale materials remains challenging.Quantum computation has the potential to offer advantages in memory footprint and computational scaling.However,general and viable quantum algorithms for simulating large-scale materials are still limited.We propose and implement random-state quantum algorithms to calculate electronic-structure properties of real materials.Using a random state circuit on a small number of qubits,we employ real-time evolution with first-order Trotter decomposition and Hadamard test to obtain electronic density of states,and we develop a modified quantum phase estimation algorithm to calculate real-space local density of states via direct quantum measurements.Furthermore,we validate these algorithms by numerically computing the density of states and spatial distributions of electronic states in graphene,twisted bilayer graphene quasicrystals,and fractal lattices,covering system sizes from hundreds to thousands of atoms.Our results manifest that the random-state quantum algorithms provide a general and qubit-efficient route to scalable simulations of electronic properties in large-scale periodic and aperiodic materials.
基金funded by the National Natural Science Foundation of China under Grant No.62371187the Open Program of Hunan Intelligent Rehabilitation Robot and Auxiliary Equipment Engineering Technology Research Center under Grant No.2024JS101.
文摘The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditional approaches like network compression,quantization,and lightweight design often sacrifice accuracy or feature representation robustness.This article introduces the Fast Multi-scale Channel Shuffling Network(FMCSNet),a novel lightweight detection model optimized for mobile devices.FMCSNet integrates a fully convolutional Multilayer Perceptron(MLP)module,offering global perception without significantly increasing parameters,effectively bridging the gap between CNNs and Vision Transformers.FMCSNet achieves a delicate balance between computation and accuracy mainly by two key modules:the ShiftMLP module,including a shift operation and an MLP module,and a Partial group Convolutional(PGConv)module,reducing computation while enhancing information exchange between channels.With a computational complexity of 1.4G FLOPs and 1.3M parameters,FMCSNet outperforms CNN-based and DWConv-based ShuffleNetv2 by 1%and 4.5%mAP on the Pascal VOC 2007 dataset,respectively.Additionally,FMCSNet achieves a mAP of 30.0(0.5:0.95 IoU threshold)with only 2.5G FLOPs and 2.0M parameters.It achieves 32 FPS on low-performance i5-series CPUs,meeting real-time detection requirements.The versatility of the PGConv module’s adaptability across scenarios further highlights FMCSNet as a promising solution for real-time mobile object detection.
基金supported by the Natural Science Basic Research Program of Shaanxi Province (Grant Nos.2024JC-JCQN-06 and2025JC-QYCX-006)the National Natural Science Foundation of China (Grant No.12474337)Chinese Academy of Sciences Project (Grant Nos.E4BA270100,E4Z127010F,E4Z6270100,and E53327020D)。
文摘In conventional higher-order topological insulators(HOTIs),the emergence of topological states can be explained by using the nonzero bulk polarization index.However,corner states emerge in HOTIs with incomplete boundary unit cells(i.e.,boundary defects)even though the bulk polarization is zero,which challenges the conventional understanding of HOTIs.Here,based on a Kekul´e-distorted honeycomb lattice with incomplete unit cells,we reveal that incomplete unit cells exhibit fractional charges through the analysis of Wannier centers by developing a compensation method and creating the concept of Wannier center domain(WCD)which is the smallest region that one Wannier center occupies.This method compensates for the missing parts of these boundary incomplete unit cells with additional WCDs to make them complete.The compensated WCDs automatically carry the corresponding charge,and this charge together with that of the incomplete unit cell constitutes the total charge of the complete unit cell after compensation.We conclude that the emergence of corner states is attributed to the filling anomaly,which is a fundamental mechanism.Our results refresh the understanding of HOTIs,especially those with structural discontinuities,and provide a novel design for topological states which have application value in producing optical functional devices.
基金supported by the confidential research grant No.a8317。
文摘To address the issues of frequent identity switches(IDs)and degraded identification accuracy in multi object tracking(MOT)under complex occlusion scenarios,this study proposes an occlusion-robust tracking framework based on face-pedestrian joint feature modeling.By constructing a joint tracking model centered on“intra-class independent tracking+cross-category dynamic binding”,designing a multi-modal matching metric with spatio-temporal and appearance constraints,and innovatively introducing a cross-category feature mutual verification mechanism and a dual matching strategy,this work effectively resolves performance degradation in traditional single-category tracking methods caused by short-term occlusion,cross-camera tracking,and crowded environments.Experiments on the Chokepoint_Face_Pedestrian_Track test set demonstrate that in complex scenes,the proposed method improves Face-Pedestrian Matching F1 area under the curve(F1 AUC)by approximately 4 to 43 percentage points compared to several traditional methods.The joint tracking model achieves overall performance metrics of IDF1:85.1825%and MOTA:86.5956%,representing improvements of 0.91 and 0.06 percentage points,respectively,over the baseline model.Ablation studies confirm the effectiveness of key modules such as the Intersection over Area(IoA)/Intersection over Union(IoU)joint metric and dynamic threshold adjustment,validating the significant role of the cross-category identity matching mechanism in enhancing tracking stability.Our_model shows a 16.7%frame per second(FPS)drop vs.fairness of detection and re-identification in multiple object tracking(FairMOT),with its cross-category binding module adding aboute 10%overhead,yet maintains near-real-time performance for essential face-pedestrian tracking at small resolutions.
基金financial support provided by the Natural Science Foundation of Hebei Province,China(No.E2024105036)the Tangshan Talent Funding Project,China(Nos.B202302007 and A2021110015)+1 种基金the National Natural Science Foundation of China(No.52264042)the Australian Research Council(No.IH230100010)。
文摘Automated classification of gas flow states in blast furnaces using top-camera imagery typically demands a large volume of labeled data,whose manual annotation is both labor-intensive and cost-prohibitive.To mitigate this challenge,we present an enhanced semi-supervised learning approach based on the Mean Teacher framework,incorporating a novel feature loss module to maximize classification performance with limited labeled samples.The model studies show that the proposed model surpasses both the baseline Mean Teacher model and fully supervised method in accuracy.Specifically,for datasets with 20%,30%,and 40%label ratios,using a single training iteration,the model yields accuracies of 78.61%,82.21%,and 85.2%,respectively,while multiple-cycle training iterations achieves 82.09%,81.97%,and 81.59%,respectively.Furthermore,scenario-specific training schemes are introduced to support diverse deployment need.These findings highlight the potential of the proposed technique in minimizing labeling requirements and advancing intelligent blast furnace diagnostics.
文摘BACKGROUND The prevalence of negative emotional states,such as anxiety and depression,has increased annually.Although personal habits are known to influence emotional regulation,the precise mechanisms underlying this relationship remain unclear.AIM To investigate emotion regulation habits impact on students negative emotions during lockdown,using the coronavirus disease 2019 pandemic as a case example.METHODS During the coronavirus disease 2019 lockdown,an online cross-sectional survey was conducted at a Chinese university.Emotional states were assessed using the Depression,Anxiety,and Stress Scale-21(DASS-21),while demographic data and emotion regulation habits were collected concurrently.Data analysis was performed using SPSS version 27.0 and includedχ^(2)-tests for intergroup comparisons,Spearman’s rank-order correlation coefficient analysis to examine associations,and stepwise linear regression modeling to explore the relationships between emotion regulation habits and emotional states.Statistical significance was set atα=0.05.RESULTS Among the 494 valid questionnaires analyzed,the prevalence rates of negative emotional states were as follows:Depression(65.0%),anxiety(69.4%),and stress(50.8%).DASS-21 scores(mean±SD)demonstrated significant symptomatology:Total(48.77±34.88),depression(16.21±12.18),anxiety(14.90±11.91),and stress(17.64±12.07).Significant positive intercorrelations were observed among all DASS-21 subscales(P<0.01).Regression analysis identified key predictors of negative emotions(P<0.05):Risk factors included late-night frequency and academic pressure,while protective factors were the frequency of parental contact and the number of same-gender friends.Additionally,compensatory spending and binge eating positively predicted all negative emotion scores(β>0,P<0.01),whereas appropriate recreational activities negatively predicted these scores(β<0,P<0.01).CONCLUSION High negative emotion prevalence occurred among confined students.Recreational activities were protective,while compensatory spending and binge eating were risk factors,necessitating guided emotion regulation.
文摘With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.
基金supported by National Natural Science Foundation of China(NSFC)under grant U23A20310.
文摘With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State Information(CSI)offers fine-grained temporal,frequency,and spatial insights into multipath propagation,making it a crucial data source for human-centric sensing.Recently,the integration of deep learning has significantly improved the robustness and automation of feature extraction from CSI in complex environments.This paper provides a comprehensive review of deep learning-enhanced human sensing based on CSI.We first outline mainstream CSI acquisition tools and their hardware specifications,then provide a detailed discussion of preprocessing methods such as denoising,time–frequency transformation,data segmentation,and augmentation.Subsequently,we categorize deep learning approaches according to sensing tasks—namely detection,localization,and recognition—and highlight representative models across application scenarios.Finally,we examine key challenges including domain generalization,multi-user interference,and limited data availability,and we propose future research directions involving lightweight model deployment,multimodal data fusion,and semantic-level sensing.
基金National Science and Technology Council,the Republic of China,under grants NSTC 113-2221-E-194-011-MY3 and Research Center on Artificial Intelligence and Sustainability,National Chung Cheng University under the research project grant titled“Generative Digital Twin System Design for Sustainable Smart City Development in Taiwan.
文摘Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.
基金supported by the National Natural Science Foundation of China(Grant Nos.12222413,12174443,12274459,and 12404266)the National Key R&D Program of China(Grant Nos.2023YFA1406500,2022YFA1403800,and 2022YFA1403103)+3 种基金the Natural Science Foundation of Shanghai (Grant No.23ZR1482200)the Natural Science Foundation of Ningbo (Grant No.2024J019)the Science Research Project of Hebei Education Department (Grant No.BJ2025060)the funding of Ningbo Yongjiang Talent Program。
文摘Superconducting elect rides have attracted growing attention for their potential to achieve high superconducting transition temperatures(T_(C))under pressure.However,many known elect rides are chemically reactive and unstable,making high-quality single-crystal growth,characterization,and measurements difficult,and most do not exhibit superconductivity at ambient pressure.In contrast,La_(3) In stands out for its ambient-pressure superconductivity(T_(C)∼9.4 K)and the availability of high-quality single crystals.Here,we investigate its low-energy electronic structure using angle-resolved photoemission spectroscopy and first-principles calculations.The bands near the Fermi energy(E_(F))are mainly derived from La 5d and In 5p orbitals.A saddle point is directly observed at the Brillouin zone(BZ)boundary,while a three-dimensional Van Hove singularity crosses E_(F) at the BZ corner.First-principles calculations further reveal topological Dirac surface states within the bulk energy gap above E_(F).The coexistence of a high density of states and in-gap topological surface states near𝐸F suggests that La3In offers a promising platform for tuning superconductivity and exploring possible topological superconducting phases through doping or external pressure.
基金supported by the Strategic Priority Research Program of Chinese Academy of Sciences (Grant Nos.XDB28000000 and XDB0460000)the Quantum Science and Technology-National Science and Technology Major Project (Grant No.2021ZD0302600)the National Key Research and Development Program of China(Grant No.2024YFA1409002)。
文摘The hybridization gap in strained-layer InAs/In_(x)Ga_(1−x) Sb quantum spin Hall insulators(QSHIs)is significantly enhanced compared to binary InAs/GaSb QSHI structures,where the typical indium composition,x,ranges between 0.2 and 0.4.This enhancement prompts a critical question:to what extent can quantum wells(QWs)be strained while still preserving the fundamental QSHI phase?In this study,we demonstrate the controlled molecular beam epitaxial growth of highly strained-layer QWs with an indium composition of x=0.5.These structures possess a substantial compressive strain within the In_(0.5)Ga_(0.5)Sb QW.Detailed crystal structure analyses confirm the exceptional quality of the resulting epitaxial films,indicating coherent lattice structures and the absence of visible dislocations.Transport measurements further reveal that the QSHI phase in InAs/In_(0.5)Ga_(0.5)Sb QWs is robust and protected by time-reversal symmetry.Notably,the edge states in these systems exhibit giant magnetoresistance when subjected to a modest perpendicular magnetic field.This behavior is in agreement with the𝑍2 topological property predicted by the Bernevig–Hughes–Zhang model,confirming the preservation of topologically protected edge transport in the presence of enhanced bulk strain.
基金supported by the Xinjiang Autonomous Region Key Research Project(No.2022D01D31)the Start-up Grant of Xinjiang University,the Basic Research Fund for Autonomous Region Universities(No.XJEDU2024P015)the Natural Science Foundation of Xinjiang Uygur Autonomous Region(No.2022D01C668).
文摘Although intermediate temperature solid oxide fuel cells(IT-SOFCs)show great potential to address energy conversion challenges,the sluggish oxygen reduction reaction(ORR)kinetics of cathode materials has severely hindered extended applications.Herein,we have demonstrated that Bi^(3+)doping on the A-site synergistically regulates the phase transition and electron spin state in La_(0.3)Bi_(0.3)Ca_(0.4)FeO_(3-δ)(LBCF3)for improved performance.An orthorhombic to cubic phase transition occurred with Bi^(3+)doping increases oxygen vacancy concentration and thus increases oxygen ion migration capacity.Simultaneously,the change of Fe from low to medium electron spin state strengths O_(2)adsorption and improves catalytic performances.Consequently,a peak power density improvement up to 48%(from 1.21 to 1.79 W·cm^(-2))at 800℃ is realized in the anodesupported single cell using LBCF3 as cathode,which remains stable for over 270 h at 750℃.
基金supported by the National Natural Science Foundation of China(61304254)the National Science Foundation for Distinguished Young Scholars of China(60925011)the Provincial and Ministerial Key Fund of China(9140A07010511BQ0105)
文摘An adaptive unscented Kalman filter(AUKF)and an augmented state method are employed to estimate the timevarying parameters and states of a kind of nonlinear high-speed objects.A strong tracking filter is employed to improve the tracking ability and robustness of unscented Kalman filter(UKF)when the process noise is inaccuracy,and wavelet transform is used to improve the estimate accuracy by the variance of measurement noise.An augmented square-root framework is utilized to improve the numerical stability and accuracy of UKF.Monte Carlo simulations and applications in the rapid trajectory estimation of hypersonic artillery shells confirm the effectiveness of the proposed method.
文摘Wide swath Synthetic Aperture Radar (SAR) images acquired over sea areas contain a variety of information regarding small scale and mesoscale phenomena in the ocean and marine boundary layer e.g. spills, slicks, surface or internal waves, eddies, oceanic fronts. One of most challenging processing step is to create image objects describing these phenomena on SAR images. The most significant problem in the wide swath images is the backscattering trend at the range direction, which results a progressive brightness reduction over images from near to far range. This reduction affects the detection and classification of sea surface features on wide swath SAR images and a normalization step is needed in a certain incidence angle for compensating the brightness reduction. The aim of the present paper is to investigate the result of image normalization to a set of Wide Swath Mode SAR images. Dark areas were initially detected in SAR images using thresholds, adapted or not. Afterwards, SAR images were normalized and a global threshold was calculated for each image. Images were segmented and objects were created for each dark area. The results were compared to a reference dataset created from theoretical modeled values and extracted in a GIS environment. Results clearly indicate that overall accuracy of the detected dark areas has been increased after normalization. On the contrary, local thresholds were insufficient in producing acceptable results. The proposed normalization can be used as a pre-processing step in image classification.
基金Project supported by the National Natural Science Fundation of China(Grant No.90922007)
文摘Dynamic nonlinearities of C70/toluene solution are measured and analysed by an improved picosecond timeresolved pump-probe system based on a nonlinear imaging technique with phase object. The photophysical parameters are determined by the five-level model, which is adopted to interpret the experimental data. The change of refraction index per unit density of the excited state obtained by a numerically simulation is a critical factor to determine the nonlinear behaviour of C70 in picosecond time regime.
文摘This paper devises a scheme which can discover the state association rules of process object. The scheme aims to dig the hidden close relationships of different links in process object. We adopt a method based on difference and extremum to compute the timing. Clustering is used to classifying the adjusted data, and the next is associating the clusters. Based on the rules of clusters, we produce the rules of links. Association degrees between each two links can be determined. It is easy to get association chains according to the degree. The state association rules that can be obtained in accordance with association rules are the final results. Some industry guidance can be directly summarized from the state association rules, and we can apply the guidance to improve the efficiency of production and operational in allied industries.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61871234 and 62001249)the University Talent Project of Anhui Province,China(Grant No.gxyq2020102)the Scientific Research Project of College of Information Engineering,Fuyang Normal University(Grant No.FXG2021ZZ02)。
文摘We propose a method for imaging a periodic moving/state-changed object based on computational ghost imaging with Hadamard speckle patterns and a slow bucket detector, named as PO-HCGI. In the scheme, speckle patterns are produced from a part of each row of a Hadamard matrix. Then, in each cycle, multiple speckle patterns are projected onto the periodic moving/state-changed object, and a bucket detector with a slow sampling rate records the total intensities reflected from the object as one measurement. With a series of measurements, the frames of the moving/state-changed object can be obtained directly by the second-order correlation function based on the Hadamard matrix and the corresponding bucket detector measurement results. The experimental and simulation results demonstrate the validity of the PO-HCGI. To the best of our knowledge, PO-HCGI is the first scheme that can image a fast periodic moving/state-changed object by computational ghost imaging with a slow bucket detector.
基金supported by the National Natural Science Foundation of China(NSFC)under Grant(No.51677058).
文摘Precisely estimating the state of health(SOH)of lithium-ion batteries is essential for battery management systems(BMS),as it plays a key role in ensuring the safe and reliable operation of battery systems.However,current SOH estimation methods often overlook the valuable temperature information that can effectively characterize battery aging during capacity degradation.Additionally,the Elman neural network,which is commonly employed for SOH estimation,exhibits several drawbacks,including slow training speed,a tendency to become trapped in local minima,and the initialization of weights and thresholds using pseudo-random numbers,leading to unstable model performance.To address these issues,this study addresses the challenge of precise and effective SOH detection by proposing a method for estimating the SOH of lithium-ion batteries based on differential thermal voltammetry(DTV)and an SSA-Elman neural network.Firstly,two health features(HFs)considering temperature factors and battery voltage are extracted fromthe differential thermal voltammetry curves and incremental capacity curves.Next,the Sparrow Search Algorithm(SSA)is employed to optimize the initial weights and thresholds of the Elman neural network,forming the SSA-Elman neural network model.To validate the performance,various neural networks,including the proposed SSA-Elman network,are tested using the Oxford battery aging dataset.The experimental results demonstrate that the method developed in this study achieves superior accuracy and robustness,with a mean absolute error(MAE)of less than 0.9%and a rootmean square error(RMSE)below 1.4%.
基金supported in part by the National Science Foundation of China(52371372)the Project of Science and Technology Commission of Shanghai Municipality,China(22JC1401400,21190780300)the 111 Project,China(D18003)
文摘Dear Editor,This letter focuses on the fact that small objects with few pixels disappear in feature maps with large receptive fields, as the network deepens, in object detection tasks. Therefore, the detection of dense small objects is challenging.
基金supported by the National Natural Science Foundation of China(Nos.62276204 and 62203343)the Fundamental Research Funds for the Central Universities(No.YJSJ24011)+1 种基金the Natural Science Basic Research Program of Shanxi,China(Nos.2022JM-340 and 2023-JC-QN-0710)the China Postdoctoral Science Foundation(Nos.2020T130494 and 2018M633470).
文摘Drone-based small object detection is of great significance in practical applications such as military actions, disaster rescue, transportation, etc. However, the severe scale differences in objects captured by drones and lack of detail information for small-scale objects make drone-based small object detection a formidable challenge. To address these issues, we first develop a mathematical model to explore how changing receptive fields impacts the polynomial fitting results. Subsequently, based on the obtained conclusions, we propose a simple but effective Hybrid Receptive Field Network (HRFNet), whose modules include Hybrid Feature Augmentation (HFA), Hybrid Feature Pyramid (HFP) and Dual Scale Head (DSH). Specifically, HFA employs parallel dilated convolution kernels of different sizes to extend shallow features with different receptive fields, committed to improving the multi-scale adaptability of the network;HFP enhances the perception of small objects by capturing contextual information across layers, while DSH reconstructs the original prediction head utilizing a set of high-resolution features and ultrahigh-resolution features. In addition, in order to train HRFNet, the corresponding dual-scale loss function is designed. Finally, comprehensive evaluation results on public benchmarks such as VisDrone-DET and TinyPerson demonstrate the robustness of the proposed method. Most impressively, the proposed HRFNet achieves a mAP of 51.0 on VisDrone-DET with 29.3 M parameters, which outperforms the extant state-of-the-art detectors. HRFNet also performs excellently in complex scenarios captured by drones, achieving the best performance on the CS-Drone dataset we built.
