检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Pei, Jialun Cheng, Tianyang Fan, Deng-Ping Tang, He Chen, Chuanbo Van Gool, Luc School of Computer Science and Technology Hust China School of Software Engineering Hust China Computer Vision Lab Eth Zurich Switzerland

We present OSFormer, the first one-stage transformer framework for camouflaged instance segmentation (CIS). OSFormer is based on two key designs. First, we design a location-sensing transformer (LST) to obtain the location label and instance-aware parameters by introducing the location-guided queries and the blend-convolution feed-forward network. Second, we develop a coarse-to-fine fusion (CFF) to merge diverse context information from the LST encoder and CNN backbone. Coupling these two components enables OSFormer to efficiently blend local features and long-range context dependencies for predicting camouflaged instances. Compared with two-stage frameworks, our OSFormer reaches 41% AP and achieves good convergence efficiency without requiring enormous training data, i.e., only 3,040 samples under 60 epochs. Code link: https://***/PJLallen/OSFormer. Copyright © 2022, The Authors. All rights reserved.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

A Method for Depth Camera Calibration Based on Motion Capture System

A Method for Depth Camera Calibration Based on Motion Captur...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Jianchu Lin Ming Zhao Guojun Yin Haiping Zhou Toshboev Hudoyberdi Bo Jiang Faculty of Computer and Software Engineering Huaiyin Institue of Technology Huai’an China Faculty of Art and Design Huaiyin Institue of Technology Huai’an China Jiangsu Eazytec Co. LTD Yixin China

With the rapid development of 3D computer vision technology, depth cameras have been widely used. Depth camera calibration is mainly constrained by two aspects: (1) alignment of depth data, and (2) distortion in RGB images. Under the condition of unknown camera intrinsic parameters, a method for RGBD commercial camera calibration is studied based on an optical motion capture system. The proposed approach utilizes the projection from the motion capture space to the depth camera’s field of view, establishing a coupled parameter model for the camera’s CCD photosensitive elements to improve the calibration of the depth camera. Experimental results demonstrate a 33% reduction in errors in the central region of the camera’s field of view compared to commonly Least Squares (LS) calibration methods. Moreover, the method exhibits faster computation speed, enabling efficient real-time calibration of depth cameras with unknown parameters in practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching

arXiv

引用

arXiv 2024年

作者： Huang, Xiaofei Chen, Wenting Liu, Jie Lu, Qisheng Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Medical report generation is crucial for clinical diagnosis and patient management, summarizing diagnoses and recommendations based on medical imaging. However, existing work often overlook the clinical pipeline involved in report writing, where physicians typically conduct an initial quick review followed by a detailed examination. Moreover, current alignment methods may lead to misaligned relationships. To address these issues, we propose DAMPER, a dual-stage framework for medical report generation that mimics the clinical pipeline of report writing in two stages. In the first stage, a MeSH-Guided Coarse-Grained Alignment (MCG) stage that aligns chest X-ray (CXR) image features with medical subject headings (MeSH) features to generate a rough keyphrase representation of the overall impression. In the second stage, a Hypergraph-Enhanced Fine-Grained Alignment (HFG) stage that constructs hypergraphs for image patches and report annotations, modeling high-order relationships within each modality and performing hypergraph matching to capture semantic correlations between image regions and textual phrases. Finally,the coarse-grained visual features, generated MeSH representations, and visual hypergraph features are fed into a report decoder to produce the final medical report. Extensive experiments on public datasets demonstrate the effectiveness of DAMPER in generating comprehensive and accurate medical reports, outperforming state-of-the-art methods across various evaluation metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Coarse-grained modeling

来源：评论

学校读者我要写书评

暂无评论

Computational Methods for Inferring and Reconstructing Gene Regulatory Networks

Computational Methods for Inferring and Reconstructing Gene ...

引用

作者： Xianglu Zhou Haiyang Jia College of Computer Science and Technology Jilin University College of Software Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin University

Gene regulatory network(GRN) describes dynamic and complex gene interactions that determine the functions of ***,understanding of GRNs has played a great role in cancer treatment,drug design,and gene ***,the GRN study suffers from a lack of experiment measurement data and the complexity of the *** approaches have evolved in recent years to promote the study of *** this review,we summarized popular Computational approaches for GRN *** started with traditional bioinformatic methods,such as Bayesian networks and mutual information ***,we introduced how today's hot technology in the computer field-machine learning benefited GRN ***-based approaches and other machine-learning methods are elaborated on in this *** discussed not only the advantages and progression brought by various methods but also the drawbacks and limitations,such as the accuracy and robustness of GRN *** expect to inspire readers for improved GRN study approaches via our introduction to this field.

关键词： Gene Regulatory Network Bioinformatics Machine Learning

来源：评论

学校读者我要写书评

暂无评论

GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning

arXiv

引用

arXiv 2024年

作者： Wu, Tao Cao, Xinwen Wang, Chao Qiao, Shaojie Xian, Xingping Yuan, Lin Cui, Canyixing Liu, Yanbing The School of Cybersecurity and Information Law Chongqing University of Posts and Telecommunications Chongqing400065 China The School of Software Engineering Chengdu University of Information Technology Chengdu610225 China The School of Computer and Information Science Chongqing Normal University Chongqing401331 China Yunnan Key Laboratory of Software Engineering Yunnan650504 China

Graph Neural Networks (GNNs) have demonstrated significant application potential in various fields. However, GNNs are still vulnerable to adversarial attacks. Numerous adversarial defense methods on GNNs are proposed to address the problem of adversarial attacks. However, these methods can only serve as a defense before poisoning, but cannot repair poisoned GNN. Therefore, there is an urgent need for a method to repair poisoned GNN. In this paper, we address this gap by introducing the novel concept of model repair for GNNs. We propose a repair framework, Repairing Robustness of Graph Neural Networks via Machine Unlearning (GraphMU), which aims to fine-tune poisoned GNN to forget adversarial samples without the need for complete retraining. We also introduce a unlearning validation method to ensure that our approach effectively forget specified poisoned data. To evaluate the effectiveness of GraphMU, we explore three fine-tuned subgraph construction scenarios based on the available perturbation information: (i) Known Perturbation Ratios, (ii) Known Complete Knowledge of Perturbations, and (iii) Unknown any Knowledge of Perturbations. Our extensive experiments, conducted across four citation datasets and four adversarial attack scenarios, demonstrate that GraphMU can effectively restore the performance of poisoned GNN. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Dual Antenna-Based Line Crossing Detection with UHF RFID

引用

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Chen, Xingyu Wang, Xuan Xun, Kai Wang, Xia Liu, Jia Zhao, Zhihong Chen, Lijun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Engineering Jinling Institute of Technology Nanjing China Principal of Suzhou City College Suzhou China

Line crossing detection is to check whether people or objects go across a given barrier line, which is quite common and important in our daily life, such as the electronic article surveillance (EAS) checkpoint in a retail store or the finish line in track and field. Although existing solutions to line crossing detection have achieved great advancement, they do not function well when multiple objects or people cross the line at the same time. In this paper, we propose a new radio frequency identification (RFID)-based solution called RF-Line to line crossing detection, especially for multiobject scenarios. The biggest challenge is that the RFID reader's coverage zone is invisible and irregular;we cannot roughly take the time when a tag is seen by the reader for the first time as the time when line crossing occurs. In RF-Line, we deploy two antennas opposite to each other and collect the RF phase profiles of two antennas at the same time. By a series of geometric transformations and mathematical derivations, we find that summing up the two phase profiles will get a new phase curve, in which the inflection point of the curve is the time of line crossing. In addition, we address the problem of turning back or long stay on the barrier line. We implement RF-Line with commodity RFID systems. Extensive experiments show that RF-Line can achieve accurate line crossing detection with a small error of 6.1 cm, with no need for any system calibration or complicated deployment. © 2023 Xingyu Chen et al.

关键词： Retail stores

来源：评论

学校读者我要写书评

暂无评论

A Self-play and Sentiment-Emphasized Comment Integration Framework Based on Deep Q-Learning in a Crowdsourcing Scenario : Extended Abstract

A Self-play and Sentiment-Emphasized Comment Integration Fra...

引用

International Conference on Data engineering

作者： Huan Rong Victor S. Sheng Tinghuai Ma Yang Zhou Mznah Al-Rodhaan School of Artificial Intelligence Nanjing University of Information Science & Technology Nanjing China Department of Computer Science Texas Tech University Lubbock USA School of Computer & Software Nanjing University of Information Science & Technology Nanjing China Department of Computer Science & Software Engineering Auburn University Auburn USA College of Computer & Information Sciences King Saud University Riyadh Kingdom of Saudi Arabia

Crowdsourcing is a sourcing model where individuals or organizations obtain goods and services from a large, relatively open and often rapidly evolving group of internet users. The most common way that crowdsourcing can facilitate machine learning is to annotate instances with labels [1] . However, the same instance may have inconsistent class labels, in the eyes of various annotators. Therefore, current efforts in crowdsourcing mainly focus on the truth inference or label integration, to remove inconsistent labels or to alleviate biased labeling. In turn, instances with the integrated labels could facilitate the training on machine learning models. The future direction of crowdsourcing is to apply more fine-grained truth inference methods to different application domains [2] . Consequently, we evolve toward another challenging problem of comment integration. That is, how can we integrate or summarize the core opinions of multiple product comments obtained from users, rather than the discrete labels.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enabling Generalized Zero-Shot Vulnerability Classification

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Hu, Jinghao Guo, Jinsong Luo, Chen Hu, Yang Lanzinger, Matthias Li, Zhanshan Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Software Changchun130012 China University College London Department of Computer Science United Kingdom Amazon United States United Kingdom University of Oxford Department of Computer Science United Kingdom Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Changchun130012 China

Regarding computer security, the growth of code vulnerability types presents a persistent challenge. These vulnerabilities, which may cause severe consequences, necessitate precise classification for effective mitigation. However, the rapid emergence of new vulnerability types complicates the classification process. Traditional methodologies, which often involve human expertise and the manual labeling or generation of example instances, are not only resource-intensive but also struggle to adapt to the dynamic nature of these vulnerabilities. This paper introduces VulnSense, an innovative method that harnesses the capabilities of Generalized Zero-Shot Learning (GZSL) to address the vulnerability classification problem. VulnSense learns about unseen vulnerability classes from the descriptions of these unseen classes, while not requiring to see any instances of these unseen classes. Specifically, VulnSense learns from three main resources: (1) seen classes with labeled code instances;(2) descriptions of these seen classes;and (3) descriptions of "unseen"classes which have no labeled instances. Our experiments underscore VulnSense's superiority over existing GZSL methods in classifying instances of unseen classes. Concurrently, it maintains a performance parity with traditional labeled-example based learning methods in classifying instances of seen vulnerabilities. VulnSense demonstrates the potential of using GZSL for vulnerability classification, while also highlighting challenges that inspire future work. © 2004-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Dual-Tower Model with Semantic Perception and Timespan-Coupled Hypergraph for Next Basket Recommendation

SSRN

引用

SSRN 2023年

作者： Zhou, Yangtao Chu, Hua Li, Qingshan Li, Jianan Zhang, Shuai Zhu, Feifei Hu, Jingzhao Wang, Luqiao Yang, Wanqiang School of Computer Science and Technology XiDian University Xi’an710071 China Intelligent Financial Software Engineering New Technology Joint Laboratory XiDian University Xi’an710071 China Shanghai Fairyland Software Corp. Ltd. Shanghai200233 China

Next Basket Recommendation (NBR) is an essential task within the realm of recommendation systems, dedicated to the anticipation of user preferences in the next moment based on the analysis of users’ historical sequences of engaged baskets. Current NBR models utilize unique identities (IDs) information to represent distinct users and items, and focus on capturing the dynamic preferences of users through sequential encoding techniques such as recurrent neural networks and hierarchical time decay modeling, which have dominated the NBR field for over a decade. However, these models exhibit two significant limitations, resulting in suboptimal representations for both users and items. Firstly, the dependence on unique IDs information for the derivation of user and item representations, ignores the rich semantic relations that interweave the items. Secondly, the majority of NBR models remain bound to modeling an individual user’s historical basket sequence, thereby neglecting the broader vista of global collaborative relations among users and items. To address these limitations, we introduce a dual-tower model with semantic perception and timespan-coupled hypergraph for the next basket recommendation. It is carefully designed to integrate the semantic and collaborative relations into both the user and item representations. Specifically, to capture rich semantic relations effectively, we propose a hierarchical semantic attention mechanism with a large language model to integrate multi-aspect textual semantic features of items for basket representation learning. Simultaneously, to capture global collaborative relations explicitly, we design a timespan-coupled hypergraph convolutional network to efficiently model high-order structural connectivity on hypergraph among users and items. Comprehensive experiments on two public datasets demonstrate that our proposed model significantly outperforms the mainstream NBR models on two classical evaluation metrics, Recall and NDCG. © 20

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Quantum Privacy-Preserving Price E-Negotiation

arXiv

引用

arXiv 2023年

作者： Liu, Wen-Jie Li, Chun-Tang Zheng, Yu Xu, Yong Xu, Yin-Song Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science & Technology Nanjing210044 China School of Computer and Software Nanjing University of Information Science & Technology Nanjing210044 China

Privacy-preserving price e-negotiation (3PEN) is an important topic of secure multi-party computation (SMC) in the electronic commerce field, and the key point of its security is to guarantee the privacy of seller’s and buyer’s prices. In this study, a novel and efficient quantum solution to the 3PEN problem is proposed, where the oracle operation and the qubit comparator are utilized to obtain the comparative results of buyer’s and seller’s prices, and then quantum counting is executed to summarize the total number of products which meets the trading conditions. Analysis shows that our solution not only guarantees the correctness and the privacy of 3PEN, but also has lower communication complexity than those classical ones. © 2023, CC BY.

关键词： Comparators (optical)

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：