检索结果-内蒙古大学图书馆

Versatile manipulation of orbital angular momentum combs enabled by diffractive neural networks

Optics express 2025年第4期33卷 6771-6787页

作者： Ruan, Zhengsen Yan, Ruize Zhang, Jinlong Yin, Xukun Liu, Lixian Liang, Yize Xu, Huailiang Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology Zhejiang Gongshang University Zhejiang Hangzhou310018 China School of Optoelectronic Engineering Xidian University Xi’an710071 China

The orbital angular momentum (OAM) of light, which can be created through the helical phase front, has attracted significant attention and found numerous applications in both classical and quantum optics. The manipulation of light’s OAM has evolved from the generation of a single OAM mode to the simultaneous generation of multiple OAM modes. As a typical kind of multiple OAM superposition mode, an OAM comb features a discrete, equispaced OAM spectrum. Similar to how optical frequency combs promoted many technical revolutions in optics, such an OAM comb may likewise pave the way for OAM-related applications. Here, we propose an approach to versatilely manipulating OAM combs based on a two-layer fully connected diffractive neural network (DNN). We achieve four kinds of manipulation and transformations on OAM combs, including four arithmetic operations, square and square root operations, high-pass/low-pass/band-pass filtering, and arbitrary transformation between two OAM combs, etc. All four kinds of manipulation reach an average accuracy of 99.65% and the lowest accuracy of over 99%. Our work may advance the research on OAM combs and open new prospects for applications based on OAM comb sources. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

CBPF: A Novel Method For Filtering Poisoned data Based on Composite Backdoor Attacks

引用

Ieee Internet of Things Journal 2025年

作者： Xia, Hanfeng Hong, Haibo Wang, Ruili Sun, Yiru Ding, Hao Zhejiang Gongshang University Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology School of Computer Science and Technology Hangzhou China Massey University School of Mathematical and Computational Sciences Auckland New Zealand

Backdoor attacks involve the injection of a limited quantity of poisoned samples containing triggers into the training dataset. During the inference stage, backdoor attacks can uphold a high level of accuracy for normal examples, yet when presented with trigger-containing instances, the model may erroneously predict them as the targeted class designated by the attacker. This paper addresses the challenge of backdoor attacks by developing a novel method for filtering poisoned samples. We primarily leverage two key characteristics of backdoor attacks: 1) Multiple backdoors can exist simultaneously within a single model;2) The discovery through Composite Backdoor Attack (CBA) that altering two triggers in a sample to new target labels does not compromise the original functionality of the triggers, yet enables the prediction of the data as a new target class when both triggers are present simultaneously. Therefore, a novel three-stage poisoning data filtering approach, known as Composite Backdoor Poisoning Filtering (CBPF), is proposed as an effective solution. Firstly, utilizing the identified distinctions in output between poisoned and clean samples, a subset of data is partitioned to include both poisoned and clean data. Subsequently, benign triggers are incorporated and labels are adjusted to create new target and benign target classes, thereby prompting the poisoned and clean data to be classified as distinct entities during the inference stage. The experimental results indicate that CBPF is successful in filtering out poisoned data produced by seven advanced attacks on CIFAR-10, GTSRB and ImageNet-12. On average, CBPF attains a notable filtering success rate of 99.88% for these attacks on CIFAR-10. Additionally, the model trained on the uncontaminated samples exhibits sustained high accuracy levels. © 2014 Ieee.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

SMS Spam Detection Using BeRT and Multi-Graph Convolutional Networks

SSRN

引用

SSRN 2025年

作者： Shen, Linjie Wang, Yanbin Li, Zhao Ma, Wenrui School of Computer Science and Technology Zhejiang Gongshang University Zhejiang Hangzhou China Department of Engineering Shenzhen MSU-BIT University Guangdong Shenzhen518172 China Zhejiang Lab Zhejiang Hangzhou China Department of Big Data and Future E-Commerce Technology Zhejiang Key Laboratory Zhejiang Hangzhou China

The surge in smartphone usage has significantly increased SMS traffic and, consequently, SMS spam, posing risks such as phishing, financial losses, and privacy breaches. Traditional rule-based and blacklist methods fail against evolving spamming techniques, prompting the adoption of machine learning and deep learning approaches. However, models like CNNs and RNNs struggle to capture global co-occurrence patterns and complex semantics, while transformer-based models like BeRT lack explicit syntactic and co-occurrence modeling. To address these limitations, we propose the BeRT with Triple-Graph Convolutional Networks (BeRT-G3CN) model, the first framework to integrate BeRT word embeddings with graph embeddings from Cooccurrence, Heterogeneous, and Integrated Syntactic Graphs. This multi-graph approach captures diverse features and models both global and local structures using tailored Graph Convolutional Networks (GCNs). experiments on two benchmark datasets demonstrate that BeRT-G3CN achieves superior accuracy of 99.28% and 93.78%. © 2025, The Authors. All rights reserved.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Quantifying Bubble-Induced Diffusion Resistance Through Real-Time Sam-Assisted Yolo High Density Bubble Detection Algorithm

SSRN

引用

SSRN 2025年

作者： Wang, Bowen Lv, Haoyang Wang, Xun Hao, Minghui Guay, Daniel Kirk, Donald W. Thorpe, Steven Ruan, Zhengsen Zhejiang Key Laboratory of Big data and Future E-Commerce Technology Zhejiang Gongshang University. Zhejiang Hangzhou China Surface Engineering and Electrochemistry Group Department of Material Science and Engineering University of Toronto TorontoON Canada Énergie Matériaux Télécommunications Research Centre INRS VarennesQC Canada Department of Chemical Engineering and Applied Chemistry University of Toronto TorontoON Canada

The chemistry and localized structure of materials greatly affect their efficiency in gas evolution reactions leading to cell resistance loses. This work focuses on the role of morphological changes in the nature of the bubble distribution by a comparison of two different surface structures: polished Ni and various porous Ni surfaces fabricated by dynamic hydrogen bubble templating. This study introduces a refined method for counting bubbles in gas evolution reactions, focusing on high-density, overlapping bubble flows. By incorporating the Segment Anything Model (SAM), we significantly reduced the training cost of the You Only Look Once algorithm, maintaining accuracy while improving efficiency. Surface characteristics strongly influenced the bubble distribution, with superaerophobic surfaces exhibiting smaller Sauter Mean Diameter (D32) values than polished ones. A polynomial extrapolation indicated that D32s were roughly one third of the thickness of the bubble layer at higher current densities. Building on the established connection between bubble layer thickness and diffusion resistance through electrochemical impedance spectroscopy (eIS), this study establishes a direct relationship between D32 and diffusion resistance. We have also demonstrated that the characteristics of the bubble layer are independent of the electrochemical surface area (eCSA) beneath the surface. This combined approach uses eIS for broader current coverage and imaging for real-time data, providing a powerful framework for bubble management and performance monitoring in gas evolution applications. © 2025, The Authors. All rights reserved.

关键词： Hydrogen evolution reaction

来源：评论

学校读者我要写书评

暂无评论

Temporal Sentence Grounding with Relevance Feedback in Videos 38

Temporal Sentence Grounding with Relevance Feedback in Video...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Dong, Jianfeng Peng, Xiaoman Liu, Daizong Qu, Xiaoye Yang, Xun Bao, Cuizhu Wang, Meng Zhejiang Gongshang University China Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology China Peking University China Huazhong University of Science and Technology China University of Science and Technology of China China Hefei University of Technology China

As a widely explored multi-modal task, Temporal Sentence Grounding in videos (TSG) endeavors to retrieve a specific video segment matched with a given query text from a video. The traditional paradigm for TSG generally assumes that relevant segments always exist within a given video. However, this assumption is restrictive and unrealistic in real-world applications where the existence of a query-related segment is uncertain, easily resulting in erroneous grounding. Motivated by the research gap and practical application, this paper introduces a new task, named Temporal Sentence Grounding with Relevance Feedback (TSG-RF) in videos, which accommodates the possibility that a video may or may not include a segment related to the query. This task entails localizing precise video segments that semantically align with the query text when such content is present, while delivering definitive feedback on the non-existence of related segments when absent. Moreover, we propose a novel Relation-aware Temporal Sentence Grounding (RaTSG) network for addressing this challenging task. This network first reformulates the TSG-RF task as a foreground-background detection problem by investigating whether the query-related semantics exist in both frame and video levels. Then, a multi-granularity relevance discriminator is exploited to produce precise video-query relevance feedback and a relation-aware segment grounding module is employed to selectively conduct the grounding process, dynamically adapting to the presence or absence of query-related segments in videos. To validate our RaTSG network, we reconstruct two popular TSG datasets, establishing a rigorous benchmark for TSG-RF. experimental results demonstrate the effectiveness of our proposed RaTSG for the TSG-RF task. Our source code is available at https://***/HuiGuanLab/RaTSG. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars

引用

JOURNAL OF FOOD eNGINeeRING 2024年 379卷

作者： Chen, Yufei Fu, Jun Weng, Xin Chen, Jiaoni Hu, Ruifen Zhu, Yunfang Zhejiang Gongshang Univ Sch Comp Sci & Technol Hangzhou 310018 Peoples R China Zhejiang Key Lab Big data & Future E Commerce Hangzhou 310018 Peoples R China Zhejiang Univ Inst Cyber Syst & Control State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China

Volatile flavor is a key indicator of food quality which can directly affect consumer preference and purchase intention. electronic nose is considered as a promising intelligent sensory analysis tool for food flavor assessment, however, extracting effective features from the gas sensor array is still a major challenge, which largely determines the performance of subsequent classifiers. Here, a parallel long short-term memory (LSTM) network is proposed as a feature extractor for automatically extracting features from the whole time series of sensor responses in flavor discrimination of five Chinese vinegars. The network was trained by the temporal data from the sensor array and yielded different feature patterns corresponding to different vinegars, which were then fed to other conventional classifiers for pattern recognition. We also evaluated the influence of the extracted feature dimension that is related to the dimension of the hidden state of the LSTM layer on the classification performance. The results indicate that a larger dimension of extracted feature is unnecessary for promoting classification accuracy, instead, the optimum dimension 4 of the hidden state gives the highest accuracy of 95.8% in this application under the softmax evaluator. Moreover, much higher accuracies were obtained when combined with other sophisticated classifiers such as support vector machine. The results demonstrate that the proposed network is competent to extract features directly and automatically from the temporal data of the electronic nose.

关键词： electronic nose Feature extraction Long short -term memory network Time series data Chinese vinegar Food flavor

来源：评论

学校读者我要写书评

暂无评论

Dynamic Adapter with Semantics Disentangling for Cross-lingual Cross-modal Retrieval

arXiv

引用

arXiv 2024年

作者： Cai, Rui Dong, Zhiyu Dong, Jianfeng Wang, Xun The College of Computer Science and Technology Zhejiang Gongshang University Hangzhou China Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology Hangzhou China

existing cross-modal retrieval methods typically rely on large-scale vision-language pair data. This makes it challenging to efficiently develop a cross-modal retrieval model for under-resourced languages of interest. Therefore, Cross-lingual Cross-modal Retrieval (CCR), which aims to align vision and the low-resource language (the target language) without using any human-labeled target-language data, has gained increasing attention. As a general parameter-efficient way, a common solution is to utilize adapter modules to transfer the vision-language alignment ability of Vision-Language Pretraining (VLP) models from a source language to a target language. However, these adapters are usually static once learned, making it difficult to adapt to target-language captions with varied expressions. To alleviate it, we propose Dynamic Adapter with Semantics Disentangling (DASD), whose parameters are dynamically generated conditioned on the characteristics of the input captions. Considering that the semantics and expression styles of the input caption largely influence how to encode it, we propose a semantic disentangling module to extract the semantic-related and semantic-agnostic features from the input, ensuring that generated adapters are well-suited to the characteristics of input caption. extensive experiments on two image-text datasets and one video-text dataset demonstrate the effectiveness of our model for cross-lingual cross-modal retrieval, as well as its good compatibility with various VLP models. Code - https://***/HuiGuanLab/DASD. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Blockchain Traceability Platform Based on Green Agricultural Products 15th

Blockchain Traceability Platform Based on Green Agricultural...

引用

15th eAI International Conference on Mobile Multimedia Communications, MobiMedia 2022

作者： Tian, Xiao Yao, Yu-Ge Xu, Hui-Tong Xie, Ying-Jie Wei, Li-Jie Xie, Guo-jie Wu, Ting Gao, Yan-Wei Jining Normal University Inner Mongolia Ulanqab012000 China Baotou Big Data Research Institute National Engineering Laboratory for E-Commerce Transaction Technology Inner Mongolia Baotou014014 China Zhejiang Key Laboratory of Open Data Hangzhou310000 China Hangzhou Innovation Institute Beihang University Hangzhou310051 China

ISBN: (纸本)9783031239014

This paper designs and completes a blockchain traceability platform based on green agricultural products. Using item coding technology, cryptography technology, blockchain, big data and other new generation information technologies, green agricultural products (especially Ulanqab potatoes, oats and other geographical indication products) from growth to harvest to circulation throughout the life cycle. The key data can be trusted and stored in the blockchain, providing consumers with real-time agricultural product traceability query services, and providing agricultural and animal husbandry departments with effective agricultural product quality and safety supervision and management mechanisms and means. With the help of QR code as the mobile Internet entrance, link online and offline, design O2O e-commerce transaction system, form a closed loop of planting, traceability and sales, digitally control the quality of authentic agricultural products, and empower the brand value of agricultural products. Realize the whole chain supervision of green products from planting source to circulation through a perfect traceability system, improve product safety and quality, enhance the market's popularity and recognition of agricultural products in the region, form effective protection of agricultural product geographical indication products, and achieve agricultural economic development "Increase quality and efficiency", and then promote the construction of smart agricultural big data projects. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Agricultural products

来源：评论

学校读者我要写书评

暂无评论

A Coding Management System for Traceability of Chinese Agricultural Products Based on Blockchain 15th

A Coding Management System for Traceability of Chinese Agric...

引用

15th eAI International Conference on Mobile Multimedia Communications, MobiMedia 2022

作者： Jiao, Li-Xian Yu, Yan-Dong Liu, Yin-Bo An, Da Yao, Yu-Ge Lan, Zhu-qing Xie, Guo-jie Wu, Ting Jia, Xiao-han Jining Normal University Inner Mongolia012000 China Beijing Zhongsheng Huaan Information Technology Co. Ltd. Beijing100089 China Zhejiang Key Laboratory of Open Data Hangzhou310000 China Hangzhou Innovation Institute Beihang University Hangzhou310051 China National Engineering Laboratory for E-Commerce Transaction Technology Baotou Big Data Research Institute Inner Mongolia014014 China

ISBN: (纸本)9783031239014

In recent years, food safety has become an increasingly serious topic around the world. Problems such as pesticides, heavy metal pollution, and chemical additives in various agricultural products have attracted widespread attention. Therefore, reliable green agricultural products are urgently demanded by consumers. To this end, this paper uses item coding technology and a new generation of information technology such as blockchain to analyze the key data of the entire life cycle of green agricultural products (especially Ulanqab potatoes, oats and other geographical indication products) from growth to harvest to circulation. Blockchain trusted certificate. Through a complete traceability supervision system, product safety and quality will be improved, the market’s visibility and recognition of agricultural products in the region will be enhanced, and the "quality and efficiency" of agricultural economic development will be achieved, thereby promoting the construction of smart agricultural big data projects. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Agricultural products

来源：评论

学校读者我要写书评

暂无评论

Representation Alignment Contrastive Regularization for Multi-Object Tracking

arXiv

引用

arXiv 2024年

作者： Chen, Shu-Jie Liu, Zhong-Lin Dong, Jian-Feng Zhou, Di Zhejiang GongShang University JiaoGong Road 149 Hangzhou310012 China Key Laboratory of Big Data and Future E-Commerce Technology Hangzhou310012 China Zhejiang Uniview Technologies Co. Ltd. Hangzhou310051 China

Achieving high-performance in multi-object tracking algorithms heavily relies on modeling spatio-temporal relationships during the data association stage. Mainstream approaches encompass rule-based and deep learning-based methods for spatio-temporal relationship modeling. While the former relies on physical motion laws, offering wider applicability but yielding suboptimal results for complex object movements, the latter, though achieving high-performance, lacks interpretability and involves complex module designs. This work aims to simplify deep learning-based spatio-temporal relationship models and introduce interpretability into features for data association. Specifically, a lightweight single-layer transformer encoder is utilized to model spatio-temporal relationships. To make features more interpretative, two contrastive regularization losses based on representation alignment are proposed, derived from spatio-temporal consistency rules. By applying weighted summation to affinity matrices, the aligned features can seamlessly integrate into the data association stage of the original tracking workflow. experimental results showcase that our model enhances the majority of existing tracking networks’ performance without excessive complexity, with minimal increase in training overhead and nearly negligible computational and storage costs. Our code is available at https://***/liuzhonglincc/RATracker. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：