检索结果-内蒙古大学图书馆

Next Generation Data-driven Networks (NGDN), International Conference on

作者： Yujie Fan Huan Luo Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

ISBN: (数字)9798350388374

ISBN: (纸本)9798350388381

Three-dimensional semantic understanding using only several multi-view images can largely reduce the communication burden on the network. In addition, while point clouds are extensively studied for 3D scene understanding, utilization of multi-view image data offers rich visual details and texture information. However, challenges persist in lifting 2D semantic features to 3D space and leveraging language for segmentation. Inspired by recent advancements, this paper proposes a method that combines CLIP features and SAM masks to create a feature field capable of segmenting objects via natural language text across 2D multi-view and 3D Gaussian splatting. It offers a promising function for extracting 3D assets for game engines and the metaverse. Our method involves mask generation from video frames, extracting physical scales via RGB Nerf with masks, and organizing hierarchical information for semantic comprehension. In the training process, affinity features maintain scale properties and guide CLIP feature generation with auto weights blending for semantic robustness. A straightforward 3D splatting CLIP feature approach and canonical text methodology enhance query robustness across 2D multi-view and 3D splatting through relevance score calculation based on text CLIP features for inference. Experimental results demonstrate promising improvements in semantic understanding of 3D scenes.

关键词： Training Image segmentation Vocabulary Visualization Three-dimensional displays Semantics Natural languages Neural radiance field Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

A Survey of SDN Data Plane Attacks and Defense Strategies 23

A Survey of SDN Data Plane Attacks and Defense Strategies

引用

2nd International Conference on Networks, Communications and information Technology, CNCIT 2023

作者： Zhang, Wenxiu Jing, Shan Zhao, Chuan School of Information Science and Engineering University of Jinan Jinan China Shandong Provincial Key Laboratory of Network-based Intelligent Computing Jinan China Quan Cheng Laboratory Jinan China

ISBN: (纸本)9798400700620

The Software-Defined Networking (SDN) paradigm proposes the decoupling of control and data planes and a centralized software-oriented management approach based on a central controller, easing the development of new applications and services, and fundamentally changed the network architecture. This paper introduces the present situation of SDN and its data plane research, but as with traditional networks, there are multiple vulnerabilities in the security aspects of the SDN architecture, which can be used to perform malicious operations with these vulnerabilities to affect the network and its services. In this paper, the SDN data plane security issues are mainly discussed, the attacks on the SDN data plane are summarized, and the existing attack defense policies are summarized and compared. Finally, the research direction of SDN data plane security is proposed and the whole paper is summarized. CCS CONCEPTS •Security and privacy •Network security •Security protocols © 2023 ACM.

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Training Method to Ensemble Bi-Linear Models for Knowledge Graph Completion

An End-to-End Training Method to Ensemble Bi-Linear Models f...

引用

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Cen, Si Liu, Han Liu, Chao Zou, Xiaoying Dai, Guoquan Wang, Xizhao College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

ISBN: (纸本)9798350303780

The study of ensemble learning in knowledge graph embedding (KGE) shows that combining multiple individual KGE models can perform better on knowledge graph completion. However, existing KGE ensemble methods ignore the creation of model diversity because these methods independently train individual models, which are short of training interaction. To create rich model diversity, we propose a novel training method for ensemble bilinear models (EBM) for the problem of knowledge graph completion. EBM uses a weighted loss to allow individual KGE models to interact during training. In this way, the relations in the knowledge graph can be automatically modeled by the most appropriate model from the KGE individual ones. The experiments on knowledge graph completion show that EBM has richer diversity and performs better than the single bilinear model and the ensemble methods without interaction. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Y-Mol: A Multiscale Biomedical Knowledge-Guided Large Language Model for Drug Development

arXiv

引用

arXiv 2024年

作者： Ma, Tengfei Lin, Xuan Li, Tianle Li, Chaoyi Chen, Long Zhou, Peng Cai, Xibao Yang, Xinyu Zeng, Daojian Cao, Dongsheng Zeng, Xiangxiang College of Computer Science and Electronic Engineering Hunan University China Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Xiangtan University China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University China Xiangya School of Pharmaceutical Sciences Central South University China

Large Language Models (LLMs) have recently demonstrated remarkable performance in general tasks across various fields. However, their effectiveness within specific domains such as drug development remains challenges. To solve these challenges, we introduce Y-Mol, forming a well-established LLM paradigm for the flow of drug development. Y-Mol is a multiscale biomedical knowledge-guided LLM designed to accomplish tasks across lead compound discovery, pre-clinic, and clinic prediction. By integrating millions of multiscale biomedical knowledge and using LLaMA2 as the base LLM, Y-Mol augments the reasoning capability in the biomedical domain by learning from a corpus of publications, knowledge graphs, and expert-designed synthetic data. The capability is further enriched with three types of drug-oriented instructions: description-based prompts from processed publications, semantic-based prompts for extracting associations from knowledge graphs, and template-based prompts for understanding expert knowledge from biomedical tools. Besides, Y-Mol offers a set of LLM paradigms that can autonomously execute the downstream tasks across the entire process of drug development, including virtual screening, drug design, pharmacological properties prediction, and drug-related interaction prediction. Our extensive evaluations of various biomedical sources demonstrate that Y-Mol significantly outperforms general-purpose LLMs in discovering lead compounds, predicting molecular properties, and identifying drug interaction events. The source code is available at https://***/r/Y-Mol. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Towards Multi-Label Open Set Diagnosis for Medical Images 22

Towards Multi-Label Open Set Diagnosis for Medical Images

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Pang, Shijie Zhao, Yuze Zhao, Rui-Wei Feng, Rui Academy for Engineering and Technology Fudan University Shanghai China School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (纸本)9798331520526

In real clinical scenarios, diagnosis algorithms may face the complex concurrent presence of multiple common, rare, or even unknown disease conditions. In particular, rare disease categories may be underrepresented or even absent from the class-imbalanced training set, leaving safe and trustworthy diagnostic decision-making extremely challenging. In this work, we first formalize the medical image diagnosis as a multi-label open set recognition under class-imbalanced training data and propose a novel Multi-label Open set Diagnosis (MOSD) solution to address this problem. Our MOSD first employs a Balanced Multi-label Data Augmentation (BMDA) module to augment multi-label image data to alleviate the class imbalance in model training more effectively. Then it also boasts a Multi-label Evidential Deep Learning (MEDL) module with tailored learning objectives to better estimate the uncertainty for multi-label open set prediction. Experimental results on the ODIR-5K benchmark successfully demonstrate its superiority in both close set known class classification and open set unknown class detection. © 2025 IEEE.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation

Imagine Before Go: Self-Supervised Generative Map for Object...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sixian Zhang Xinyao Yu Xinhang Song Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The Object Goal navigation (ObjectNav) task requires the agent to navigate to a specified target in an unseen environment. Since the environment layout is unknown, the agent needs to infer the unknown contextual objects from partially observations, thereby deducing the likely location of the target. Previous end-to-end RL methods capture contextual relationships through implicit representations while they lack notion of geometry. Alternatively, modular methods construct local maps for recording the observed geometric structure of unseen environment, however, lacking the reasoning of contextual relation limits the exploration efficiency. In this work, we propose the self-supervised generative map (SGM), a modular method that learns the explicit context relation via self-supervised learning. The SGM is trained to leverage both episodic observations and general knowledge to reconstruct the masked pixels of a cropped global map. During navigation, the agent maintains an incomplete local semantic map, meanwhile, the unknown regions of the local map are generated by the pretrained SGM. Based on the generated map, the agent sets the predicted location of the target as the goal and moves towards it. Experiments on Gibson, MP3D and HM3D show the effectiveness of our method. The code is available at https://***/sx-zhang/SGM.

关键词： Training Geometry Navigation Large language models Semantics Layout Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Point Pattern Matching Based on Spectra of Directed Graphs

引用

Chinese Journal of Electronics 2023年第4期20卷 662-666页

作者： LIANG Dong ZHU Ming FAN Yizheng YAN Pu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China

We present a novel algorithm for point pattern matching by means of spectra of directed graphs. Given a feature point-set, we construct a weighted directed graph and skew-symmetric matrix associated with the graph. By using spectral decomposition of the matrix, we give a spectral representation of the feature points with half of the eigenvectors. We theoretically analyze that our method can well deal with the matching problem under affine transformation. The expreiments applied to synthetic data and real-world images show the effectiveness of our method.

关键词： Technological innovation Directed graphs Medical services Matrix decomposition Pattern matching Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Nanobook Structure Driven by Polymerase-Triggered DNA Strand Displacement 1

引用

17th International Conference on Bio-Inspired computing: Theories and Applications, BIC-TA 2022

作者： Chen, Kuiting Chen, Zhekun Xie, Chun Pan, Linqiang Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

Due to its high degree of customization, DNA origami provides a versatile platform with which to engineer nanoscale structures and devices. Reconfigurable nanodevices driven by DNA strand displacement accomplish the task of transition between different conformations, endowing DNA origami with application values. Herein, we propose a strategy to regulate the conformation of DNA origami using the polymerase-triggered DNA strand displacement (PTSD) reaction. We design a book-shaped DNA origami structure consisting of four pages connected into a cuboid shape. The PTSD reactions initiated by different primer strands selectively remove the connecting strand, transforming the nano book into a two-page or a four-page conformation. We utilize three primer strands to remove thirty-five connecting strands and construct three conformations of the identical DNA origami, illustrating that the PTSD reaction is an effective tool for the reconfiguration of DNA origami. The statistical results of TEM images prove the effectiveness of the proposed method. Our work on the development of PTSD-driven reconfigurable nanostructure will offer a new way to create intelligent materials for advanced nanotechnology applications. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

Factors influencing COVID-19 infection in the countries around the world 4

Factors influencing COVID-19 infection in the countries arou...

引用

4rth International Conference on Applied Mathematics, Modelling, and intelligent computing, CAMMIC 2024

作者： Sun, Ning Xiong, Jianling Tang, Tian School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin541004 China Key Laboratory of Cognitive Radio and Information Processing Ministry of Education Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9781510681637

This paper aims to analyze the impact of various factors on COVID-19 infection rates across different countries. Data on social, demographic, and economic indicators (comprising 16 variables) from 195 countries, as well as infection and mortality data up to January 8, 2023, were collected. Methodologies including factor analysis, cluster analysis, multiple stepwise linear regression, and random forest were applied. Factor analysis revealed four distinct categories (humanity, vaccination, economics, and living), while cluster analysis identified a total of 14 cluster categories. Results indicated that humanity had the most significant impact on both human infections and deaths, followed by economics, vaccination, and living conditions. Moreover, vaccination protection was found to be limited, with advanced age and poor living conditions identified as significant risk factors for infection. © 2024 SPIE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Tube Masking-Based MAE Pre-Training for Three-Dimensional Lumbar Vertebrae Segmentation 9

Tube Masking-Based MAE Pre-Training for Three-Dimensional Lu...

引用

9th International Conference on intelligent computing and Signal processing, ICSP 2024

作者： Liu, Yang Chen, Jian Jin, Shuhua Wei, Shijie Hai, Jinjin Qi, Xin Li, Yongli Yan, Bin Pla Strategy Support Force Information Engineering University Henan Key Laboratory of Imaging and Intelligent Processing Zhengzhou China Zhengzhou University Henan Key Laboratory of Imaging and Intelligent Processing Pla Strategy Support Force Information Engineering University School of Cyber Science and Engineering Zhengzhou China Xinxiang Medical University Henan Provincial People's Hospital Department of Radiology Zhengzhou China Henan Provincial People's Hospital Henan Key Laboratory of Chronic Disease Management Department of Health Magement Zhengzhou China

ISBN: (纸本)9798350376548

QCT is commonly used for performing Bone mineral density (BMD) measurement in clinical practice, with professional doctors annotating the L1 vertebra region. However, the annotation consumes a significant amount of effort and time. Mask autoencoders (MAE) based pre-training can decrease the amount of labels and achieve a comparable performance for automated image segmentation. However, the random masking strategy of the MAE is not really suitable for 3D images. Given the considerable similarity among adjacent slices in 3D images, random masking could inadvertently cause the network to latch onto similar or identical features. Therefore, we propose a DMU-Net network that combines tube masking with MAE pre-training, and utilize UNetr network to finetune the pre-trained model on the L1 vertebrae segmentation task. This paper makes a comparative evaluation of the DMU-Net network against both conventional MAE pre-training with UNetr fine-tuning network and only UNetr for segmentation. The results demonstrate that DMU-Net outperforms other networks. © 2024 IEEE.

关键词： Image segmentation

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：