检索结果-内蒙古大学图书馆

8th Annual International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2020

作者： Zhao, Jinling Chu, Guomin Yan, Hao Hu, Lei Xue, Yongan National Engineering Research Center for Analysis and Application of Agro-Ecological Big Data Anhui University Hefei230601 China College of Mining Engineering Taiyuan University of Technology Taiyuan030024 China

The development of ground-based, airborne and spaceborne remote sensing has greatly facilitated the identification and diagnosis of various objects. Corresponding algorithms and methods of removing interference from remotely sensed imagery have been proposed. Nevertheless, the studies on anti-interference ability of selected features have not been fully considered. In our study, the hyperspectral reflectance of leaf-scale powdery mildew (Erysiphe graminis) on winter wheat were collected as the testing dataset. A total of seven representative spectral features of Landsat-8 Operational Land Imager (OLI) and GaoFen-1 Wide-Field-View (WFV) was selected, namely, original blue, green, red, near-infrared (NIR) bands and normalized difference vegetation index (NDVI), normalized difference greenness index (NDGI), structure insensitive pigment index (SIPI). Four hyperspectral vegetation indices including red edge (MSR) simple ratio index, NDVI, green band and SIPI were also selected. Three primary background noises including soil, cloud and white poplar (Populus alba L.) were added into the spectral signal. The correlation coefficient (R) between disease severities (0, 1, 2, 3 and 4) and spectral features was used to estimate the anti-interference ability. The results show that there is a generally similar spectral performance for the two sensors, but Landsat-8 OLI is superior to GF-1 WVF in terms of spectral response. The green band was greatly affected with the R values decreasing from 0.77 to 0.35. The MSR and NDVI showed a gradual decrease with the increase of three background noises. The study shows that background noises must be removed when acquiring spectral data and stable spectral features should be also selected by evaluating the anti-interference ability. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Preference Completion with Ranked and Unranked Preferences

引用

Cognitive Computation 2025年第3期17卷 1-21页

作者： Li, Lei Liu, Pan Zhang, Renjie Tao, Zhenchao Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Department of Radiation Oncology The First Affiliated Hospital of USTC Division of Life Sciences and Medicine University of Science and Technology of China Hefei China Department of Radiation Oncology Anhui Provincial Cancer Hospital Hefei China

As for social choice, all alternatives are ranked by agents to form preferences as linear orders. However, in applications, sometimes some alternatives cannot be ranked, or it is unnecessary to rank them, which leads to unranked alternatives. Hence, without loss of generality, by dividing the set of alternatives into three ranked and unranked subsets, including top-k alternatives, intermediate-r alternatives, and last-l alternatives, the Mallows model on ranked and unranked preferences can be analyzed systematically. Technically, a repeated insertion model is adopted during sampling, and probability distributions are derived for ranked and unranked preferences of alternatives. Experimental results verify the accuracy of the probability distributions for different ranked and unranked preferences of alternatives. Furthermore, in order to solve the preference completion problem where agents have multiple partial rankings, a fuzzy preference completion algorithm, Fuzzy-Multi-Rankings, is proposed, which introduces a fuzzy ranking to complete the target agent’s preference in addition to the traditional nearest-neighbor-based methods. Based on the three ranked and unranked preferences, seven cases can be classified and analyzed for fuzzy preference completion. Experiments on the synthetic datasets and MovieLens dataset confirm the effectiveness and efficiency of our proposed Fuzzy-Multi-Rankings algorithm and also verify the accuracy of the evaluated probability distributions for the proposed seven cases.

关键词： Mallows model Unranked preference Fuzzy ranking Preference completion

来源：评论

学校读者我要写书评

暂无评论

Multi-View Fusion based Attribute Network for Multi-Query Vehicle Re-identification

Multi-View Fusion based Attribute Network for Multi-Query Ve...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Weijun Zhang Renjian Li Xiaoyi Zhou Hanqin Shi School of Computer Science and Technology Anhui University Hefei China School of Cyberspace Security Hainan University Haikou China School of Information Engineering (School of Big Data) Xuzhou University of Technology Xuzhou China

In recent years, most re-identification methods use only a single query image to match the target vehicle. However, the limitation of single query image information hinders the performance of vehicle re-identification. In this case, we propose a Multi-View Fusion based Attribute Network (MVANet) for the Multi-Query Vehicle re-identification task. On the one hand, we fuse the information of multiple vehicle views by the Viewpoint Fusion Module to improve the information representation, thus solving the challenge of large intra-class variability caused by viewpoint differences. On the other hand, we use the Attribute Embedding Module to embed attribute information into visual features to address the challenge of small intra-class variability caused by similarity in appearance. In addition, we construct a new dataset HFVeRi for the Multi-Query Vehicle re-identification task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-rank Fusion Network for Multi-modality Person Re-identification

Low-rank Fusion Network for Multi-modality Person Re-identif...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Ziling He Hanqin Shi Youqing Wu Zhengzheng Tu School of Computer Science and Technology Anhui University Hefei China School of Information Engineering (School of Big Data) Xuzhou University of Technology Xuzhou China School of Computer Science and Technology Hefei Normal University Hefei China

Ideally, multi-modality person re-identification (Re-ID) models can make use of the complementary information contained in different modality images to obtain richer target features under ideal conditions, thus making up for the shortcomings of traditional visible person re-identification in complex environments. However, the advantages of different modalities may not be fully exploited due to incomplete feature learning. Therefore, we propose a low-rank fusion network for multi-modality person Re-ID, which can extract multi-scale features of each modality under the guidance of efficient channel attention (ECA) to capture different details of the target image, and then apply the low-rank feature fusion module to achieve feature complementation between multiple modalities and learn recognition features with strong representational ability. Extensive experiments on multi-modality person Re-ID dataset RGBNT201 comparing to other advanced methods verify the effectiveness of our method in complex environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical features-based targeted aspect extraction from online reviews

引用

Intelligent data Analysis 2021年第1期25卷 205-223页

作者： He, Jin Li, Lei Wang, Yan Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei Anhui China School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China Department of Computing Macquarie University Sydney Australia MiningLamp Academy of Sciences Mininglamp Techonologies Beijing China

With the prevalence of online review websites, large-scale data promote the necessity of focused analysis. This task aims to capture the information that is highly relevant to a specific aspect. However, the broad scope of the aspects of the various products makes this task overarching but challenging. A commonly used solution is to modify the topic models with additional information to capture the features for a specific aspect (referred to as a targeted aspect). However, the existing topic models, either perform the full analysis to capture features as many as possible or estimate the similarity to capture features as coherent as possible, overlook the fine-grained semantic relations between the features, resulting in the captured features coarse and confusing. In this paper, we propose a novel Hierarchical Features-based Topic Model (HFTM) to extract targeted aspects from online reviews, then to capture the aspect-specific features. Specifically, our model can not only capture the direct features posing target-to-feature semantics but also capture the latent features posing feature-to-feature semantics. The experiments conducted on real-world datasets demonstrate that HFTMl outperforms the state-of-the-art baselines in terms of both aspect extraction and document classification. © 2021 - IOS Press. All rights reserved.

关键词： Aspect extraction Focused analysis Online reviews Text mining Topic modeling

来源：评论

学校读者我要写书评

暂无评论

AEFNet: Adaptive Scale Feature Based on Elastic-and-Funnel Neural Network for Healthcare Representation

AEFNet: Adaptive Scale Feature Based on Elastic-and-Funnel N...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Liu, Yang Wu, Jialun Wei, Yuhua Mao, Bing Li, Chen Gong, Tieliang Xi'An Jiaotong University School of Computer Science and Technology National Engineering Lab for Big Data Analytics Shaanxi Xi'an710049 China

ISBN: (纸本)9781665401265

Healthcare Representation learning has been a key element to achieving state-of-the-art performance on healthcare prediction. Recent advances based Electronic Healthcare Records(EHRs) are mostly devoted to extracting temporal progression patterns with temporal model and their variants. Although these works have shown excellent performances in healthcare prediction, the unified temporal pattern may not be suitable for individuals in all healthcare conditions. Moreover, some studies ususally introduce complex Deep Neural Networks models and medical prior knowledge to get compact representation, causing great computational burden. In this paper, we propose a general health care representation model, named AEFNet. We only leverage three simple convolution operations and a set of up and down sampling to ensure performance and model complexity equally, which achieves adaptively extract distinct individual key feature in a light manner. AEFNet can shrink and refine highly suitable scale information adaptively and comletely. Breaking traditional fixed convolution scale or multi-scale, AEFNet achieves scale adaptively to extract the most significant information and context relationship. Finally, We validate our method on the public dataset MIMIC-III, and the evaluation results indicate that our method can significantly outperform other remarkable baseline models. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification

arXiv

引用

arXiv 2024年

作者： Wang, Xianlong Hu, Shengshan Zhang, Yechao Zhou, Ziqi Zhang, Leo Yu Xu, Peng Wan, Wei Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Information and Communication Technology Griffith University SouthportQLD4215 Australia

Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victim models. Recently, defense mechanisms such as adversarial training, image transformation techniques, and image purification have been proposed. However, these schemes are either susceptible to adaptive attacks, built on unrealistic assumptions, or only effective against specific poison types, limiting their universal applicability. In this research, we propose a more universally effective, practical, and robust defense scheme called ECLIPSE. We first investigate the impact of Gaussian noise on the poisons and theoretically prove that any kind of poison will be largely assimilated when imposing sufficient random noise. In light of this, we assume the victim has access to an extremely limited number of clean images (a more practical scene) and subsequently enlarge this sparse set for training a denoising probabilistic model (a universal denoising tool). We then introduce Gaussian noise to absorb the poisons and apply the model for denoising, resulting in a roughly purified dataset. Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach. Extensive experiments demonstrate that our defense approach outperforms 10 state-of-the-art defenses. We also propose an adaptive attack against ECLIPSE and verify the robustness of our defense scheme. Our code is available at https://***/CGCL-codes/ECLIPSE. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-view Feature Complementary for Multi-query Vehicle Re-identification

Multi-view Feature Complementary for Multi-query Vehicle Re-...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Chaobin Zhang Youqing Wu Hanqin Shi ZhengZheng Tu School of Computer Science and Technology Anhui University Hefei China School of Computer Science and Technology Hefei Normal University Hefei China School of Information Engineering (School of Big Data) Xuzhou University of Technology Xuzhou China

Existing vehicle re-identification methods rely mainly on single query, which retrieves images of a given vehicle from other cameras based on the features extracted from a single image. However, the limited information contained in a single vehicle image significantly restricts the performance of vehicle re-identification in complex surveillance networks. In this paper, we propose a more practical and accessible task called multi-query vehicle re-identification, which utilizes multiple vehicle images from different viewpoint to overcome the viewpoint limitation of single query. Based on this task, we propose a novel multi-query feature complementary network (MFCNet), which fuses the information of vehicle images from multiple viewpoint during training to obtain the global features of vehicles. We then use these global features to optimize the local features extracted from a single viewpoint, enhancing the heterogeneity of vehicle features from different viewpoint. During testing, the complementary feature information from different vehicle perspectives is adaptively combined to reduce feature redundancy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embedding VLAD in Transformer for Video Question Answering

引用

Jisuanji Xuebao/Chinese Journal of Computers 2023年第4期46卷 671-689页

作者： Guo, Dan Yao, Shen-Tao Wang, Hui Wang, Meng School of Computer and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230094 China Key Laboratory of Knowledge Engineering with Big Data（Hefei University of Technology） Ministry of Education Hefei230601 China Intelligent Interconnected Systems Laboratory of Anhui Province（Hefei University of Technology） Hefei230601 China

Video question answering（VideoQA）is a typical cross-modal understanding task. Its challenge lies in how to learn appropriate multimodal representation and cross-modal correlation for answer inference. Most existing video question answering methods focus on the latter，e. g.，relationship learning between each video frame or clip and word. In this work， we devote to advanced feature embedding of both video and query. We develop a clustering-based VLAD technique for VideoQA. The novelty of our work is the joint exploitation of temporal aggregation and correlation in multimodality. We propose an end-to-end trainable Transformed VLAD embedding network， named TVLAD-Net. TVLAD-Net constructs a differentiable aggregation network module（i. e.， convolutional Residual-less VLAD Block）to generate compact VLAD descriptors（transforming N frames，clips or words to compact K descriptors while K © 2023 Science Press. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

RETIA: Relation-Entity Twin-Interact Aggregation for Temporal Knowledge Graph Extrapolation

RETIA: Relation-Entity Twin-Interact Aggregation for Tempora...

引用

International Conference on data engineering

作者： Kangzheng Liu Feng Zhao Guandong Xu Xianzhi Wang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Data Science and Machine Intelligence Lab University of Technology Sydney Sydney Australia

Temporal knowledge graph (TKG) extrapolation aims to predict future unknown events (facts) based on historical information, and has attracted considerable attention due to its great practical significance. Accurate representations (embeddings) of entities and relations form the basis of TKG extrapolation. Recent work has been devoted to improving the rationality of entity representations. However, on the one hand, ignoring relation modeling results in incomplete relation representations; therefore, some approaches aggregate only immediately adjacent entities of relations, but this can lead to the "message islands" problem of relation modeling. On the other hand, ignoring the association constraints between relations and entities can make the embeddings of both relations and entities prone to overfitting. To address the abovementioned challenges, we propose an advanced method, namely, RETIA. For the former issue, we generate twin hyperrelation subgraphs for each historical subgraph and then aggregate both the adjacent entities and relations in the hyperrelation subgraphs through a graph convolutional network (GCN). About the latter concern, we propose a twin-interact module (TIM), which provides communication channels for relation aggregation and entity aggregation during the evolution of the historical sequence. Experiments conducted on five public datasets show that RETIA has made great improvements across several evaluation metrics. Our released code is available at https://***/CGCL-codes/RETIA.

关键词：

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：