检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Minghui Wang, Xianlong Yu, Zhifei Hu, Shengshan Zhou, Ziqi Zhang, Longling Zhang, Leo Yu School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Convolution-based unlearnable examples (UEs) employ class-wise multiplicative convolutional noise to training samples, severely compromising model performance. This fire-new type of UEs have successfully countered all defense mechanisms against UEs. The failure of such defenses can be attributed to the absence of norm constraints on convolutional noise, leading to severe blurring of image features. To address this, we first design an Edge Pixel-based Detector (EPD) to identify convolution-based UEs. Upon detection of them, we propose the first defense scheme against convolution-based UEs, COrrupting these samples via random matrix multiplication by employing bilinear INterpolation (COIN) such that disrupting the distribution of class-wise multiplicative noise. To evaluate the generalization of our proposed COIN, we newly design two convolution-based UEs called VUDA and HUDA to expand the scope of convolution-based UEs. Extensive experiments demonstrate the effectiveness of detection scheme EPD and that our defense COIN outperforms 11 state-of-the-art (SOTA) defenses, achieving a significant improvement on the CIFAR and ImageNet datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Approaches to Address Occlusion and Small Target Challenges in Restaurant Rat Detection

Approaches to Address Occlusion and Small Target Challenges ...

引用

Computer Applications and Information Technology (ISCAIT), International Symposium on

作者： Yanqing Li Zhanxiang Lai Hanyu Lou Junhan He Yixin Zhong Wen Xin School of Public Health Xiamen University Xiamen China School of Marine Science and Technology Northwestern Polytechnical University Xi’an China School of Software Northwestern Polytechnical University Xi’an China School of Lilac Harbin Institute of Technology Harbin China School of Computer and Big Data Heilongjiang University Harbin China School of Information Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798331542856

ISBN: (纸本)9798331542863

In this study, an improved target detection algorithm is proposed for the problem of rat detection in restaurant environments. The restaurant environment is characterized by obvious light changes, complex occlusion, and ground reflections, which bring more challenges to the accurate detection of rats. For this reason, we make the following improvements to the YOLOv5 algorithm. First, we introduce the Glare Suppression Module, which utilizes an adaptive feature correction method to reduce the interference of highly reflective areas such as oil and water stains on the ground on the detection model, and to improve the recognition ability of the rat target in low-contrast scenes. Secondly, combined with the Background Adaptive Modeling (BAM) technology, the stability and generalization ability of the model is improved by dynamically learning the background features of the restaurant environment to reduce the false detections caused by the activities of the restaurant personnel, changes in the tables and chairs, and other factors. The experimental results show that the improved YOLOv5 algorithm can effectively improve the precision and recall rate of rat detection, reduce the false detection rate, and ensure the real-time performance in the restaurant environment, which provides efficient and reliable technical support for restaurant hygiene monitoring and pest rat prevention and control.

关键词： YOLO Adaptation models Prevention and mitigation Rodents Rats Feature extraction Reflection Real-time systems Reliability Personnel

来源：评论

学校读者我要写书评

暂无评论

Fast-Speed Image Recognition System on Retail Commodity Image

Fast-Speed Image Recognition System on Retail Commodity Imag...

引用

IEEE International Conference on e-Business engineering (ICEBE)

作者： Meiju Hu Xiaojing Zhong School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education

ISBN: (纸本)9781665444194

In recent years, image recognition technology has been widely used in commodity recognition in smart containers and retail shelves. However, as the number of images received by smart terminals is increasing, more and more commodity categories need to be recognized. The image recognition technology adopted by the industry now requires a large number of images, and the modeling time is very long, which cannot meet the requirements for fast and accurate recognition. In this paper, we design and implement a fast-speed image recognition system that can cover all categories of retail commodities to solve the problem. We use DenseNet to strengthen the feature extraction of commodities collected by cameras. At the same time, we utilize a large number of commodity images accumulated in the production system as the primary database to achieve the effect of identifying all categories of commodity. The proposed system can quickly model new commodity images and new packaging of commodities through matching with the database. The experimental results show that the system can overcome the limitation of the number of images and shorten the modeling time. Furthermore, the accuracy rate is not affected in a complex environment.

关键词： Industries Training Production systems Image recognition Costs databases Packaging

来源：评论

学校读者我要写书评

暂无评论

ABFS: Natural Robustness Testing for LLM-based NLP software

arXiv

引用

arXiv 2025年

作者： Xiao, Mingxuan Xiao, Yan Ji, Shunhui Li, Yunhe Xue, Lei Zhang, Pengcheng Key Laboratory of Water Big Data Technology of Ministry of Water Resources the College of Computer Science and Software Engineering Hohai University No. 8 Focheng West Road Jiangning District Nanjing211100 China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University No.66 Gongchang Road Xinhu Street Guangming District Shenzhen528406 China

Owing to the exceptional performance of Large Language Models (LLMs) in Natural Language Processing (NLP) tasks, LLM-based NLP software has rapidly gained traction across various domains, such as financial analysis and content moderation. However, these applications frequently exhibit robustness deficiencies, where slight perturbations in input (prompt+example) may lead to erroneous outputs. Current robustness testing methods face two main limitations: (1) low testing effectiveness, limiting the applicability of LLM-based software in safety-critical scenarios, and (2) insufficient naturalness of test cases, reducing the practical value of testing outcomes. To address these issues, this paper proposes ABFS, a straightforward yet effective automated testing method that, for the first time, treats the input prompts and examples as a unified whole for robustness testing. Specifically, ABFS formulates the testing process as a combinatorial optimization problem, employing Best-First Search to identify successful test cases within the perturbation space and designing a novel Adaptive control strategy to enhance test case naturalness. We evaluate the robustness testing performance of ABFS on three datasets across five threat models. On Llama2-13b, the traditional StressTest achieves only a 13.273% success rate, while ABFS attains a success rate of 98.064%, supporting a more comprehensive robustness assessment before software deployment. Compared to baseline methods, ABFS introduces fewer modifications to the original input and consistently generates test cases with superior naturalness. Furthermore, test cases generated by ABFS exhibit stronger transferability and higher testing efficiency, significantly reducing testing costs. © 2025, CC BY-NC-ND.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

GK: A Graphormer Architecture Based Knowledge Graph Reasoning Model for Link Prediction

GK: A Graphormer Architecture Based Knowledge Graph Reasonin...

引用

IEEE International Conference on big data and Cloud Computing (BdCloud)

作者： Yueiia Wu Jian-tao Zhou Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing College of Computer Science Inner Mongolia University National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China

Knowledge Graph has become a dominant research field in graph theory, but its incompleteness and sparsity hinder its application in various fields. Knowledge Graph Reasoning aims to alleviate these problems by deducing new knowledge or identifying false knowledge from existing knowledge. Recently, the Graph Convolution Network (GCN) based method is one of the most advanced methods to realize knowledge graph reasoning. However, it still suffers from some problems such as incomplete neighbor information aggregation and slow training speed. This paper proposes a knowledge graph reasoning model named GK for the link prediction task, which obtains better performance than existing GCN-based methods by introducing Graphormer into knowledge reasoning. The GK first proposes that nodes and their surroundings can be regarded as a hierarchical architecture that enables the model to capture more practical reasoning information to improve prediction accuracy. In addition, to accelerate the training speed of the model on the large-scale Knowledge Graph, we present a faster shortest path-finding method F-SPF in the edge coding process. Extensive experimental results show that the GK model can obtain the state-of-the-art prediction results of current GCN-based methods and can improve the training speed.

关键词： Training Knowledge engineering Knowledge graphs Predictive models Prediction algorithms Feature extraction Cognition

来源：评论

学校读者我要写书评

暂无评论

Video Summarization with a Dual Attention Capsule Network

Video Summarization with a Dual Attention Capsule Network

引用

International Conference on Pattern Recognition

作者： Hao Fu Hongxing Wang Jianyu Yang School of Big Data and Software Engineering Chongqing University Chongqing China School of Rail Transportation Soochow University Suzhou Jiangsu China

In this paper, we address the problem of video summarization, which aims at selecting a subset of video frames as a summary to represent the original video contents compactly and completely. We propose a simple but effective supervised approach with a dual attention capsule network towards this end. Unlike existing LSTM based methods, it pays attention to short- and long-term dependencies among video frames through an elaborate dual self-attention architecture, which can handle longer-term dependencies and admit parallel computing. To reconcile the outputs of dual self-attention, we rely on a two-stream capsule network to learn the underlying frame selection criteria. Experiments on real-world datasets show the advantages of the proposed approach compared with state-of-the-art methods.

关键词： Fuses Computer architecture Parallel processing Benchmark testing Pattern recognition Labeling

来源：评论

学校读者我要写书评

暂无评论

Deepnodule: Multi-Task Learning of Segmentation Bootstrap for Pulmonary Nodule Detection

Deepnodule: Multi-Task Learning of Segmentation Bootstrap fo...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Jingqin Li Kun Wang Dan Yang Xiaohong Zhang Chen Liu School of Big Data and Software Engineering Chongqing University Chongqing China The First Affiliated Hospital of Army Medical University Chongqing China

ISBN: (纸本)9781728176055;9781728176062

Pulmonary nodule detection and segmentation are the necessary successively steps in lung cancer screening with low-dose computed tomography (CT) scans. However, the state-of-the-art models focus on solving tasks separately, thereby ignore the correlation between each task. Besides, most nodule detectors adopt anchor-based method falling to achieve good performance in low FPs per scan. To overcome those barriers, we present a novel multi-task 3D convolutional network (DeepNodule) for simultaneous nodule detection and segmentation in a shared-and-fined manner. Meanwhile, we utilize the center-point of the predicted segmentation masks to refine the bounding box coordinate and get a more precise nodule location. Furthermore, we design a 3D Gated Channel Transformation convolutional attention block for learning nodule features better. Experiments conducted on LUNA16 dataset demonstrates that DeepNodule obtains competitive performance, with the sensitivity of nodule candidate detection achieving 92.0%, and the accuracy of nodule segmentation reaching 80.04%.

关键词： Three-dimensional displays Correlation Convolution Computed tomography Lung cancer Lung Logic gates

来源：评论

学校读者我要写书评

暂无评论

2D Animation - Q Version of the AIDS Prevention Short Video

2D Animation - Q Version of the AIDS Prevention Short Video

引用

IEEE International Conference on Orange Technologies (ICOT)

作者： Chun-Cheng Wei Hui-Ming Hsieh Long-Chen Hung Ru-Yi Chen Jiang-Fang Huang Xin-Chun Lu Yu-Shan Zhong School of Software and Big Data Changzhou College of Information Technology Changzhou China Department of Computer Science and Multimedia Design Taiwan Shoufu University Tainan Taiwan Department of Electronic Engineering Lunghwa University of Science and Technology Taiwan

ISBN: (纸本)9781665454209

AIDS is a sexually transmitted disease. The medical term is called Acquired Immune Deficiency Syndrome. Medical methods such as cocktail therapy and anticancer drugs can kill AIDS. Although there are currently cured cases, prevention is still required to prevent the infection from expanding; prevention Ways, like the AIDS vaccine or preventive safe sex, can reduce the risk of infection. We hope that through the production of animated short films for viewing, we can help reduce the HIV infection rate. This short film is presented as a story similar to a micro-film by ourselves. And using the modern scene and the character design of the Q version as the material, the story content is made into 2D animation with Adobe Flash CS5.

关键词： Uniform resource locators Video on demand Films Acquired immune deficiency syndrome Music Medical treatment Production

来源：评论

学校读者我要写书评

暂无评论

Active Object Searching Based on Deep Reinforcement Learning

Active Object Searching Based on Deep Reinforcement Learning

引用

作者： Renjie Mao School of Big Data and Software Engineering ChongQing University

Recently,computer vision has progressed a lot and object detection by robot has drawn interests of many *** combining artificial intelligence and traditional industry together,computer vision and object detection has gained remarkable *** robot can detect the still complete images quite efficiently with a considerable accuracy,yet the active object detection and searching is a relatively new *** a robot is able to adjust its position to get a better view of the images,a good policy of the action selection should be payed attention *** this paper,several DQN-like algorithms are introduced and *** in a bid to weaken the estimation bias of them,a Maxmin DQN algorithm is implemented on a household *** comparing the performance of these algorithms,the Maxmin DQN proves to be the best on average.

关键词： object detection reinforcement learning object searching

来源：评论

学校读者我要写书评

暂无评论

Quantum soft likelihood function based on ordered weighted average operator

arXiv

引用

arXiv 2021年

作者： Zhan, Tianxiang He, Yuanpeng Xiao, Fuyuan School of Computer and Information Science Southwest University Chongqing China School of Big Data and Software Engineering Chongqing University Chongqing China

Quantum theory is the focus of current research. Likelihood functions are widely used in many fields. Because the classic likelihood functions are too strict for extreme data in practical applications, Yager proposed soft ordered weighted average (OWA) operator. In the quantum method, probability is represented by Euler's function. How to establish a connection between quantum theory and OWA is also an open question. This article proposes OWA opreator under quantum theory, and discusses the relationship between quantum soft OWA operater and classical soft OWA operator through some examples. Similar to other quantum models, this research has more extensive applications in quantum information. Copyright © 2021, The Authors. All rights reserved.

关键词： data fusion

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：