检索结果-内蒙古大学图书馆

Facial-sketch Synthesis:A New Challenge

Machine Intelligence Research 2022年第4期19卷 257-287页

作者： Deng-Ping Fan Ziling Huang Peng Zheng Hong Liu Xuebin Qin Luc Van Gool Computer Vision Laboratory ETH ZürichZürich 8092Switzerland Information and Communication Engineering University of TokyoTokyo 113-8654Japan Computer Vision Mohamed bin Zayed University of Artificial IntelligenceAbu DhabiUAE Digital Content and Media Sciences Research Division National Institute of InformaticsTokyo 101-8430Japan

This paper aims to conduct a comprehensive study on facial-sketch synthesis(FSS).However,due to the high cost of obtaining hand-drawn sketch datasets,there is a lack of a complete benchmark for assessing the development of FSS algorithms over the last *** first introduce a high-quality dataset for FSS,named FS2K,which consists of 2104 image-sketch pairs spanning three types of sketch styles,image backgrounds,lighting conditions,skin colors,and facial ***2K differs from previous FSS datasets in difficulty,diversity,and scalability and should thus facilitate the progress of FSS ***,we present the largest-scale FSS investigation by reviewing 89 classic methods,including 25 handcrafted feature-based facial-sketch synthesis approaches,29 general translation methods,and 35 image-to-sketch *** addition,we elaborate comprehensive experiments on the existing 19 cutting-edge ***,we present a simple baseline for FSS,named *** only two straightforward components,i.e.,facialaware masking and style-vector expansion,our FSGAN surpasses the performance of all previous state-of-the-art models on the proposed FS2K dataset by a large ***,we conclude with lessons learned over the past years and point out several unsolved *** code is available at https://***/DengPingFan/FSGAN.

关键词： Facial sketch synthesis(FSS) facial sketch dataset benchmark attribute style transfer

来源：评论

学校读者我要写书评

暂无评论

Optimizing Real Estate Recommendations with Elasticsearch and Machine Learning Techniques 25th

Optimizing Real Estate Recommendations with Elasticsearch a...

引用

25th International Conference on Web Information Systems Engineering, WISE 2024

作者： Sbiaa, Fatma Boufares, Nadia Kotel, Sonia Maalel, Ahmed RIADI Laboratories National School of Computer Sciences University of Manouba Manouba Tunisia Polytechnic School of Sousse Sousse Tunisia Higher Institute of Applied Sciences and Technology of Sousse University of Sousse Sousse Tunisia

ISBN: (纸本)9789819605699

In the rapidly evolving real estate industry, providing highly accurate and personalized recommendations has become paramount. Precision in these recommendations is crucial to meet the unique needs of potential buyers and ensure that sellers effectively reach their target audiences. By offering tailored property suggestions, user experience is significantly improved, leading to greater satisfaction and engagement for both buyers and sellers. This paper presents an innovative recommendation system designed for real estate websites. It aims to enhance user satisfaction and engagement through targeted property suggestions. Our proposed system leverages Elasticsearch in combination with machine learning techniques to deliver precise recommendations. We detail the system architecture and its processes. Evaluations conducted on real-world datasets demonstrate better recommendation accuracy and user engagement compared to traditional methods. This combination leads to significant improvements in real estate performance and opens up opportunities for future research. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Estimation With Normalized Logits For Out-of-distribution Detection

Uncertainty-Estimation With Normalized Logits For Out-of-dis...

引用

2023 International Conference on computer, Artificial Intelligence, and Control Engineering, CAICE 2023

作者： Huang, Mouxiao Qiao, Yu The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

ISBN: (纸本)9781510665040

Out-of-distribution (OOD) detection is critical for preventing deep learning models from making incorrect predictions, especially in safety-critical applications such as medical diagnosis and autonomous driving. However, neural networks often suffer from overconfidence, making high confidence predictions for OOD data that are never seen during training and may be irrelevant to training data. Determining the reliability of the prediction is still a difficult and challenging task. To address this challenge, we propose a new method called Uncertainty-Estimation with Normalized Logits (UE-NL) for robust learning and OOD detection. The method has three main benefits: (1) Neural networks with UE-NL treat every in-distribution (ID) sample equally by predicting the uncertainty score of input data and the uncertainty is added into softmax function to adjust the learning strength of easy and hard samples during training phase, making the model learn robustly and accurately. (2) UE-NL enforces a constant vector norm on the logits to decouple the effect of the increasing output’s norm from optimization process, which causes the overconfidence issue to some extent. (3) UE-NL provides a new metric, the magnitude of uncertainty score, to detect OOD data. Experiments demonstrate that UE-NL outperforms existing methods on common OOD benchmarks and is more robust to noisy ID data that may be misjudged as OOD data by other methods. © 2023 SPIE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Recognition and Classification of Apple and Sugarcane Plant Leaf Diseases using SVM with DAE Models 2

Recognition and Classification of Apple and Sugarcane Plant ...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Sunil Kumar, V. Jyothi, A.P. Sumanth, S. Nagamani, H.S. Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Ramaiah University of Applied Sciences Faculty of Engineering and Technology Department of Cse Peenya Bengaluru India Department of Computer Science and Computer Applications Kolar India Department of Computer Science Karnataka Bengaluru India

ISBN: (纸本)9798350382952

For this leaf disease study, apple and sugarcane plants are identified and classified using a mix of character features and in-depth automated coding. Farm sugar cane leaves were copied for the online apple Plant Village Dataset. Pre-process images to reduce size and improve HLG filters. Image segmentation using DWT and GLCM feature extraction follows. Like the Low-Low (LL) band, DWT images produce 4-orthogonal subbands. Deep Auto Encoder and SVM algorithms retrieved subgroup functions and identified diseases from training data. If classification findings are ignored, the division stage receives data with HL, LH, and HH bands to explain approach consistency. Deep Auto encoder classifies illness using training data after extracting sub-band features. The Auto Encoder and SVM classifier demonstrated that the proposed model outperformed alternatives in LL band. Other subbands performed worse than the LL band. This study found that LL sub band data provided fine image data for better sickness categorization than HH, HL, and LH sub band data. © 2024 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Integrated dominating and hit set-inspired unequal clusteringbased data aggregation in wireless sensor networks

引用

International Journal of Intelligent Computing and Cybernetics 2022年第4期15卷 642-655页

作者： G.Vennira Selvi V.Muthukumaran A.C.Kaladevi S.Satheesh Kumar B.Swapna Department of Computer Science and Engineering Global Institute of Engineering and TechnologyVelloreIndia Department of Mathematics School of Applied SciencesREVA UniversityBangaloreIndia Department of Computer Science and Engineering Sona College of TechnologySalemIndia Department of Computer Science School of Applied SciencesREVA UniversityBangaloreIndia Department of Electronics and Communication Engineering Dr MGR Educational and Research InstituteChennaiIndia

Purpose-In wireless sensor networks,improving the network lifetime is considered as the prime objective that needs to be significantly addressed during data *** the traditional data aggregation techniques,cluster-based dominating set algorithms are identified as more effective in aggregating data through cluster ***,the existing cluster-based dominating set algorithms suffer from a major drawback of energy deficiency when a large number of communicating nodes need to collaborate for transferring the aggregated ***,due to this reason,the energy of each communicating node is gradually decreased and the network lifetime is also *** increase the lifetime of the network,the proposed algorithm uses two sets:Dominating set and hit ***/methodology/approach-The proposed algorithm uses two sets:Dominating set and hit *** dominating set constructs an unequal clustering,and the hit set minimizes the number of communicating nodes by selecting the optimized cluster head for transferring the aggregated data to the base *** simulation results also infer that the proposed optimized unequal clustering algorithm(OUCA)is greater in improving the network lifetime to a maximum amount of 22%than the existing cluster head selection approach considered for ***-In this paper,lifetime of the network is prolonged by constructing an unequal cluster using the dominating set and electing an optimized cluster head using hit *** dominator set chooses the dominator based on the remaining energy and its node degree of each *** optimized cluster head is chosen by the hit set to minimize the number of communicating nodes in the *** proposed algorithm effectively constructs the clusters with a minimum number of communicating nodes using the dominating and hit *** simulation result confirms that the proposed algorithm prolonging the lifetime of the network efficiently when compared with the existing algorithms.

关键词： Unequal clustering Hit set Dominating set Network lifetime

来源：评论

学校读者我要写书评

暂无评论

ML-Pred-CLL: Machine Learning based prediction of Chronic Lymphocytic Leukemia using protein sequential data

ML-Pred-CLL: Machine Learning based prediction of Chronic Ly...

引用

2022 International Conference on Recent Advances in Electrical Engineering and computer sciences, RAEE and CS 2022

作者： Ahmad, Waqar Hameed, Madiha Bilal, Muhammad Majid, Abdul Pakistan Institute of Engineering and Applied Sciences Pieas Department of Computer and Information Sciences Islamabad Pakistan

ISBN: (数字)9781665491037

ISBN: (纸本)9781665491020

Leukemia is a fatal disease caused by mutation in the blood forming tissues in the bone marrow. Leukemia is the deadliest disease pertaining to cancer. Early detection of leukemia is necessary to increase the chances of survival. In this work, we have proposed Machine Learning based prediction of Chronic Lymphocytic Leukemia (CLL) using protein sequential data (ML-Pred-CLL). In this study, the most frequently mutated genes of CLL - BRAF, MYD88, NOTCHI, and XPOI - were used. The significant features of Chou's Pseudo Amino Acid Composition (PseAAC) and relative/position-based features in protein sequences contributed towards the development of effective chronic lymphocytic leukemia classification model. Several machine learning models i.e. Support Vector Machine(SVM), XGBoost, Random Forest, K Nearest Neighbor(KNN), Logistic Regression, and Naive Bayes, have reported 97.09%, 95.17%, 93.5%, 91.30%, 70.1%, 54.03% accuracy respectively. The models were trained and tested with stratified k-fold cross validation technique. The primary benefit of the suggested ML-Pred-CLL is that it effectively utilizes the discriminant information of mutant genes. Using discriminant knowledge from mutant genes, we explored at a new dimension of early chronic lymphocytic leukemia classification. The proposed ML-Pred-CLL is highly effective for early diagnosis and prognosis of chronic lymphocytic leukemia. Additionally, the suggested ML-Pred-CLL is expected to be a helpful tool for oncologists. © 2022 IEEE.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

In silico study to find a potent inhibitor, Vilazodone, to cure COVID-19 using molecular docking

In silico study to find a potent inhibitor, Vilazodone, to c...

引用

2022 International Conference on Recent Advances in Electrical Engineering and computer sciences, RAEE and CS 2022

作者： Ismail, Muhammad Aqeel, Imra Bilal, Muhammad Majid, Abdul Pakistan Institute of Engineering and Applied Sciences Pieas Department of Computer and Information Sciences Islamabad Pakistan

ISBN: (数字)9781665491037

ISBN: (纸本)9781665491020

The pandemic caused by the coronavirus SARS-COVID-2 has had devastating impact on the world. It has caused a significant number of deaths across the world. Fast spread and lack of vaccine prompted academia to adopt new, fast and reliable methodologies to design new drugs. A combined approach of direct drug design and indirect drug design has been used for molecular docking. In the study, we found a compound, Vilazodone, with a binding energy of -8.40 kcal/mol. The druglikeness properties of this compound are investigated through SWISS ADMET analysis. In this in-silico study, we confirmed this compound is a potential drug candidate against ***, in-vitro and in-vivo studies are required to prove its efficacy. © 2022 IEEE.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Findings of the Third Shared Task on Multilingual Coreference Resolution 7

Findings of the Third Shared Task on Multilingual Coreferenc...

引用

7th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2024

作者： Novák, Michal Dohnalová, Barbora Konopík, Miloslav Nedoluzhko, Anna Popel, Martin Pražák, Ondřej Sido, Jakub Straka, Milan Žabokrtský, Zdeněk Zeman, Daniel Charles University Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics Prague Czech Republic University of West Bohemia Faculty of Applied Sciences Department of Computer Science and Engineering Pilsen Czech Republic

ISBN: (纸本)9798891761711

The paper presents an overview of the third edition of the shared task on multilingual coreference resolution, held as part of the CRAC 2024 workshop. Similarly to the previous two editions, the participants were challenged to develop systems capable of identifying mentions and clustering them based on identity coreference. This year’s edition took another step towards real-world application by not providing participants with gold slots for zero anaphora, increasing the task’s complexity and realism. In addition, the shared task was expanded to include a more diverse set of languages, with a particular focus on historical languages. The training and evaluation data were drawn from version 1.2 of the multilingual collection of harmonized coreference resources CorefUD, encompassing 21 datasets across 15 languages. 6 systems competed in this shared task. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

IterInv: Iterative Inversion for Pixel-Level T2I Models

IterInv: Iterative Inversion for Pixel-Level T2I Models

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chuanming Tang Kai Wang Joost van de Weijer Institute of Optics and Electronics Computer Vision Center University of Chinese Academy of Sciences Beijing China Computer Vision Center Barcelona Spain Computer Vision Center Universitat Autonoma de Barcelona Barcelona Spain

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Large-scale text-to-image diffusion models have been a ground-breaking development in generating convincing images following an input text prompt. The goal of image editing research is to give users control over the generated images by modifying the text prompt. Current image editing techniques predominantly hinge on DDIM inversion as a prevalent practice rooted in Latent Diffusion Models (LDM). However, the large pretrained T2I models working on the latent space suffer from losing details due to the first compression stage with an autoencoder mechanism. Instead, other mainstream T2I pipeline working on the pixel level, such as Imagen and DeepFloyd-IF, circumvents the above problem. They are commonly composed of multiple stages, typically starting with a text-to-image stage and followed by several super-resolution stages. In this pipeline, the DDIM inversion fails to find the initial noise and generate the original image given that the super-resolution diffusion models are not compatible with the DDIM technique. According to our experimental findings, iteratively concatenating the noisy image as the condition is the root of this problem. Based on this observation, we develop an iterative inversion (IterInv) technique for this category of T2I models and verify IterInv with the open-source DeepFloyd-IF model. Specifically, IterInv employ NTI as the inversion and reconstruction of low-resolution image generation. In stages 2 and 3, we update the latent variance at each timestep to find the deterministic inversion trace and promote the reconstruction process. By combining our method with a popular image editing method, we prove the application prospects of IterInv. The code will be released upon acceptance. The code is available at https://***/Tchuanm/***

关键词： Codes Accuracy Superresolution Pipelines Noise Text to image Diffusion models

来源：评论

学校读者我要写书评

暂无评论

A robust deformed convolutional neural network(CNN)for image denoising

引用

CAAI Transactions on Intelligence Technology 2023年第2期8卷 331-342页

作者： Qi Zhang Jingyu Xiao Chunwei Tian Jerry Chun‐Wei Lin Shichao Zhang School of Economics and Management Harbin Institute of Technology at WeihaiWeihaiChina School of Computer Science Central South UniversityChangshaChina School of Software Northwestern Polytechnical UniversityXi'anShaanxiChina Research&Development Institute Northwestern Polytechnical UniversityShenzhenChina Yangtze River Delta Research Institute Northwestern Polytechnical UniversityTaicangChina Department of Computer Science Electrical Engineering and Mathematical SciencesWestern Norway University of Applied SciencesBergenNorway

Due to strong learning ability,convolutional neural networks(CNNs)have been developed in image ***,convolutional operations may change original distributions of noise in corrupted images,which may increase training difficulty in image *** relations of surrounding pixels can effectively resolve this *** by that,we propose a robust deformed denoising CNN(RDDCNN)in this *** proposed RDDCNN contains three blocks:a deformable block(DB),an enhanced block(EB)and a residual block(RB).The DB can extract more representative noise features via a deformable learnable kernel and stacked convolutional architecture,according to relations of surrounding *** EB can facilitate contextual interaction through a dilated convolution and a novel combination of convolutional layers,batch normalisation(BN)and ReLU,which can enhance the learning ability of the proposed *** address long-term dependency problem,the RB is used to enhance the memory ability of shallow layer on deep layers and construct a clean ***,we implement a blind denoising *** results demonstrate that our denoising model outperforms popular denoising methods in terms of qualitative and quantitative *** can be obtained at https://***/hellloxiaotian/RDDCNN.

关键词： blind denoising CNN deformed block enhanced block

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：