Multi-View Stereo (MVS) is a long-standing and fundamental task in computer vision, which aims to reconstruct the 3D geometry of a scene from a set of overlapping images. With known camera parameters, MVS matches pixe...
详细信息
In the field of hardware Trojan (HT) detection, recent research that utilize graph learning models for HT detection have demonstrated advantages in detection capabilities, scalability and adaptability. However, the de...
详细信息
Optical braille recognition methods typically employ existing target detection models or segmentation modelsfor the direct detection and recognition of braille characters in original braille images. However, these met...
详细信息
Optical braille recognition methods typically employ existing target detection models or segmentation modelsfor the direct detection and recognition of braille characters in original braille images. However, these methodsneed improvement in accuracy and generalizability, especially in densely dotted braille image environments. Thispaper presents a two-stage braille recognition framework. The first stage is a braille dot detection algorithmbased on Gaussian diffusion, targeting Gaussian heatmaps generated by the convex dots in braille images. Thisis applied to the detection of convex dots in double-sided braille, achieving high accuracy in determining thecentral coordinates of the braille convex dots. The second stage involves constructing a braille grid using traditionalpost-processing algorithms to recognize braille character information. Experimental results demonstrate that thisframework exhibits strong robustness and effectiveness in detecting braille dots and recognizing braille charactersin complex double-sided braille image datasets. The framework achieved an F1 score of 99.89% for Braille dotdetection and 99.78% for Braille character recognition. Compared to the highest accuracy in existing methods,these represent improvements of 0.08% and 0.02%, respectively.
With the rise of blockchain technology,the security issues of smart contracts have become increasingly *** the availability of numerous smart contract vulnerability detection tools,many face challenges such as slow up...
详细信息
With the rise of blockchain technology,the security issues of smart contracts have become increasingly *** the availability of numerous smart contract vulnerability detection tools,many face challenges such as slow updates,usability issues,and limited installation *** challenges hinder the adoption and practicality of these *** paper examines smart contract vulnerability detection tools from 2016 to 2023,sourced from the Web of science(WOS)and Google *** systematically collecting,screening,and synthesizing relevant research,38 open-source tools that provide installation methods were selected for further *** a developer’s perspective,this paper offers a comprehensive survey of these 38 open-source tools,discussing their operating principles,installation methods,environmental dependencies,update frequencies,and installation *** on this,we propose an Ethereum smart contract vulnerability detection *** framework enables developers to easily utilize various detection tools and accurately analyze contract security *** validate the framework’s stability,over 1700 h of testing were ***,a comprehensive performance test was performed on the mainstream detection tools integrated within the framework,assessing their hardware requirements and vulnerability detection *** results indicate that the Slither tool demonstrates satisfactory performance in terms of system resource consumption and vulnerability detection *** study represents the first performance evaluation of testing tools in this domain,providing significant reference value.
Knowledge distillation (KD) techniques have been employed to tackle the issue of incomplete multi-modality data, aiming to enhance the performance of the student model (i.e., using unimodal data) as close as possible ...
详细信息
Palmprint recognition is an emerging biometrics technology that has attracted increasing attention in recent years. Many palmprint recognition methods have been proposed, including traditional methods and deep learnin...
详细信息
Palmprint recognition is an emerging biometrics technology that has attracted increasing attention in recent years. Many palmprint recognition methods have been proposed, including traditional methods and deep learning-based methods. Among the traditional methods, the methods based on directional features are mainstream because they have high recognition rates and are robust to illumination changes and small noises. However, to date, in these methods, the stability of the palmprint directional response has not been deeply studied. In this paper, we analyse the problem of directional response instability in palmprint recognition methods based on directional feature. We then propose a novel palmprint directional response stability measurement (DRSM) to judge the stability of the directional feature of each pixel. After filtering the palmprint image with the filter bank, we design DRSM according to the relationship between the maximum response value and other response values for each pixel. Using DRSM, we can judge those pixels with unstable directional response and use a specially designed encoding mode related to a specific method. We insert the DRSM mechanism into seven classical methods based on directional feature, and conduct many experiments on six public palmprint databases. The experimental results show that the DRSM mechanism can effectively improve the performance of these methods. In the field of palmprint recognition, this work is the first in-depth study on the stability of the palmprint directional response, so this paper has strong reference value for research on palmprint recognition methods based on directional features.
Railway turnouts often develop defects such as chipping,cracks,and wear during *** not detected and addressed promptly,these defects can pose significant risks to train operation safety and passenger *** advances in d...
详细信息
Railway turnouts often develop defects such as chipping,cracks,and wear during *** not detected and addressed promptly,these defects can pose significant risks to train operation safety and passenger *** advances in defect detection technologies,research specifically targeting railway turnout defects remains *** address this gap,we collected images from railway inspectors and constructed a dataset of railway turnout defects in complex *** enhance detection accuracy,we propose an improved YOLOv8 model named YOLO-VSS-SOUP-Inner-CIoU(YOLO-VSI).The model employs a state-space model(SSM)to enhance the C2f module in the YOLOv8 backbone,proposed the C2f-VSS module to better capture long-range dependencies and contextual features,thus improving feature extraction in complex *** the network’s neck layer,we integrate SPDConv and Omni-Kernel Network(OKM)modules to improve the original PAFPN(Path Aggregation Feature Pyramid Network)structure,and proposed the Small Object Upgrade Pyramid(SOUP)structure to enhance small object detection ***,the Inner-CIoU loss function with a scale factor is applied to further enhance the model’s detection *** to the baseline model,YOLO-VSI demonstrates a 3.5%improvement in average precision on our railway turnout dataset,showcasing increased accuracy and *** on the public NEU-DET dataset reveal a 2.3%increase in average precision over the baseline,indicating that YOLO-VSI has good generalization capabilities.
MnCeO_(x)/P84 catalytic filters with spherical,flower-like,cubic and rod-like catalytic interfaces were synthesized respectively,and their catalytic activities in the NH_(3)-SCR reaction were *** MnCeO_(x)/P84 catalyt...
详细信息
MnCeO_(x)/P84 catalytic filters with spherical,flower-like,cubic and rod-like catalytic interfaces were synthesized respectively,and their catalytic activities in the NH_(3)-SCR reaction were *** MnCeO_(x)/P84 catalytic filter with spherical catalytic interfaces(recorded as S-MnCeO_(x)/P84)exhibits the best catalytic denitration *** NO_(x)removal efficiency of S-MnCeO_(x)/P84 reaches the highest value of 98.6%at 160℃when the catalyst loading is 100 g/m^(2).At the same time,S-MnCeO_(x)/P84 exhibits good SO_(2)resistance and stability,achieving a NO_(x)removal rate of 83%at 190℃with 30 ppm SO_(2).The characterization results illustrate that the MnCeO_x active component in S-MnCeO_(x)/P84 is present in weak crystalline states,tightly wrapped around the surface of the filter fiber,and uniformly dispersed,and the mesopore is the main pore structure of the S-MnCeO_(x)/P84,which can provide a channel for the catalytic reaction to *** the same time,transmission electron microscopy(TEM)characterization shows that y-MnO_(2)is the main form of MnO_(2)in the S-MnCeO_(x)/*** analysis of H_(2)temperature programmed reduction(H_(2)-TPR).NH_(3)temperature programmed desorption(NH_(3)-TPD)and in-situ diffuse reflectance infrared spectra(DRIFTS)show that S-MnCeO_(x)/P84 has good redox ability at 100-200℃and has abundant Lewis acid sites and Bronsteds acid sites,which provides an important guarantee for its superior low-temperature NH_(3)-SCR denitration performance.
In recent years,the number of smart contracts deployed on blockchain has ***,the issue of vulnerability has caused incalculable *** to the irreversible and immutability of smart contracts,vulnerability detection has b...
详细信息
In recent years,the number of smart contracts deployed on blockchain has ***,the issue of vulnerability has caused incalculable *** to the irreversible and immutability of smart contracts,vulnerability detection has become particularly *** the popular use of neural network model,there has been a growing utilization of deep learning-based methods and tools for the identification of vulnerabilities within smart *** paper commences by providing a succinct overview of prevalent categories of vulnerabilities found in smart ***,it categorizes and presents an overview of contemporary deep learning-based tools developed for smart contract *** tools are categorized based on their open-source status,the data format and the type of feature extraction they *** we conduct a comprehensive comparative analysis of these tools,selecting representative tools for experimental validation and comparing them with traditional tools in terms of detection coverage and ***,Based on the insights gained from the experimental results and the current state of research in the field of smart contract vulnerability detection tools,we suppose to provide a reference standard for developers of contract vulnerability detection ***,forward-looking research directions are also proposed for deep learning-based smart contract vulnerability detection.
Entity and relation extraction is a critical task in information *** approaches have emphasized obtaining improved span ***,existing work suffers from two major ***,there is an overabundance of low-quality candidate s...
详细信息
Entity and relation extraction is a critical task in information *** approaches have emphasized obtaining improved span ***,existing work suffers from two major ***,there is an overabundance of low-quality candidate spans,which hinders the effective extraction of information from high-quality candidate ***,the information encoded by existing marker strategies is often too simple to fully capture the nuances of the span,resulting in the loss of potentially valuable *** address these issues,we propose an enhancing entity and relation extraction with high-quality spans and enhanced marker(HSEM)strategies,it assigns adaptive weights to different spans in order to make the model more focused on high quality ***,the HSEM model enriches marker representation to incorporate more span information and enhance entity ***,we design a span scoring framework that assesses span quality based on the fusion of internal information and focuses the model on training high-quality samples to improve *** results on six benchmark datasets demonstrate that our model achieves state-of-the-art results after discriminating span quality.
暂无评论