检索结果-内蒙古大学图书馆

Research on Element Extraction of Personified Sentences Based on Enhanced Characters 20

学校读者我要写书评

暂无评论

Research on Element Extraction of Personified Sentences Base...

20th Chinese National Conference on computational Linguistics, CCL 2021

作者： Li, Jing Wang, Suge Chen, Xin Wang, Dian School of Computer and Information Technology Shanxi University Shanxi Taiyuan030006 China Key Laboratory Computational Intelligence Chinese Information Processing of Ministry of Education Shanxi University Shanxi Taiyuan030006 China

In the appreciation questions of prose reading comprehension, the appreciation examination of anthropomorphic sentences is quite frequent. At present, the existing work only identification and extracts the ontological elements in the personification sentence, which has the problem of incomplete element extraction. Especially, when there are multiple ontologies in the sentence, the corresponding relationship between the personification word and each ontological element needs to be identified. In order to solve these problems, this paper proposes a method of identification and element extraction of personification sentences based on character feature enhancement. Using the characteristics of specific areas, the vector enhanced is represented for the sentence, the conditional random field model is used to identify the ontological and anthropomorphic elements in personification sentences. On this basis, the self-attention mechanism is used to detect the relationship between the elements, information exchange of between the element synchronization and relation synchronization mechanism is used to update input of element identification and relation detection. The experimental results show that the proposed method is better than other models for the extraction of on a self-built anthropomorphic dataset. © 2021 China National Conference on computational Linguistics Published under Creative Commons Attribution 4.0 International License

关键词： Synchronization

Ensemble Selector Mixed with Pareto Optimality to Feature Reduction

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Yin, Zhenyu Yang, Xibei Wang, Pingxin Yu, Hualong Qian, Yuhua School of Computer Jiangsu University of Science and Technology Jiangsu Zhenjiang212100 China School of Science Jiangsu University of Science and Technology Jiangsu Zhenjiang212100 China School of Economics and Management Jiangsu University of Science and Technology Jiangsu Zhenjiang212100 China Institute of Big Data Science and Industry Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Shanxi Taiyuan030006 China

Among various tasks of feature reduction, how to search qualified features and then construct the corresponding reduct which satisfies a given constraint is a hot topic. Constraint is the pre-defined condition in feature reduction, it rules two crucial aspects: 1) when the process of searching can be terminated to construct reduct;2) whether a feature/set of features should be added into reduct pool or not. Obviously, such a task of feature reduction is constraint-dependent. However, some limitations may naturally emerge: 1) constraint-independent features are ignored;2) fixed constraint hinders the diverse evaluations of features;3) selected features based on single constraint are powerless to data perturbation. Therefore, an Ensembler Mixed with Pareto Optimality (EmPo) is developed in this study. Firstly, the principle of Restricted Pareto Optimality is proposed to identify constraint-independent features before performing constraint related searching, which indicates a two-stages strategy to feature reduction. Naturally, diverse evaluations of features are achieved in such a process. Secondly, a data perturbation w.r.t. either sample or feature aspect is employed to obtain multiple reductions of features. The objective is to further improve the stability of the classification results based on those multiple reducts. It should also be emphasized that EmPo is a general framework, and most existing approaches to feature reduction can be embedded into it to further improve their performances. Finally, the effectiveness of our EmPo is validated over 20 datasets within 4 different ratios of noisy label. © 2023, The Authors. All rights reserved.

关键词： Pareto principle

UMFA: A photorealistic style transfer method based on U-Net and multi-layer feature aggregation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Rao, Dongyu Wu, Xiao-Jun Li, Hui Kittler, Josef Xu, Tianyang Jiangnan University Jiangsu Provincial Engineerinig Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Lihu Avenue Wuxi214122 China University of Surrey Centre for Vision Speech and Signal Processing GuildfordGU2 7XH United Kingdom

In this paper, we propose a photorealistic style transfer network to emphasize the natural effect of photo realistic image stylization. In general, distortion of the image content and lacking of details are two typical issues in the style transfer field. To this end, we design a novel framework employing the U-Net structure to maintain the rich spatial clues, with a multi-layer feature aggregation (MFA) method to simultaneously provide the details obtained by the shallow layers in the stylization processing. In particular, an encoder based on the dense block and a decoder form a symmetrical structure of U-Net are jointly staked to realize an effective feature extraction and image reconstruc tion. Besides, a transfer module based on MFA and "adaptive instance normalization" (AdaIN) is inserted in the skip connection positions to achieve the stylization. Accordingly, the stylized image possesses the texture of a real photo and preserves rich content details without introducing any mask or post-processing steps. The experimental results on public datasets demonstrate that our method achieves a more faithful structural similarity with a lower style loss, reflecting the effectiveness and merit of our approach. © 2021, CC0.

关键词： Deep learning

Differentiable neural architecture learning for efficient neural network design

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Guo, Qingbei Wu, Xiao-Jun Kittler, Josef Feng, Zhiquan Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan250022 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Automated neural network design has received ever-increasing attention with the evolution of deep convolutional neural networks (CNNs), especially involving their deployment on embedded and mobile platforms. One of the biggest problems that neural architecture search (NAS) confronts is that a large number of candidate neural architectures are required to train, using, for instance, reinforcement learning and evolutionary optimisation algorithms, at a vast computation cost. Even recent differentiable neural architecture search (DNAS) samples a small number of candidate neural architectures based on the probability distribution of learned architecture parameters to select the final neural architecture. To address this computational complexity issue, we introduce a novel architecture parameterisation based on scaled sigmoid function, and propose a general Differentiable Neural Architecture Learning (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks. Specifically, for stochastic supernets as well as conventional CNNs, we build a new channel-wise module layer with the architecture components controlled by a scaled sigmoid function. We train these neural network models from scratch. The network optimization is decoupled into the weight optimization and the architecture optimization, which avoids the interaction between the two types of parameters and alleviates the vanishing gradient problem. We address the non-convex optimization problem of neural architecture by the continuous scaled sigmoid method with convergence guarantees. Extensive experiments demonstrate our DNAL method delivers superior performance in terms of neural architecture search cost, and adapts to conventional CNNs (e.g., VGG16 and ResNet50), lightweight CNNs (e.g., MobileNetV2) and stochastic supernets (e.g., ProxylessNAS). The optimal networks learned by DNAL surpass those produced by the state-of-the-art methods on the benchmark CIFAR-10 and ImageN

关键词： Deep neural networks

Multi-modal Remote Sensing Image Registration via Modality Perception and Self-Supervised Position Estimation

学校读者我要写书评

暂无评论

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Xiao, Yun Zhang, Chunlei Jiang, Bo Chen, Yuan Tang, Jin Anhui University Key Laboratory of Intelligent Computing & Signal Processing (Anhui University) Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Hefei 230601 China Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei 230601 China Anhui University School of Internet Hefei 230601 China

Multi-modal remote sensing images registration ensures that images from different sensors or modalities are spatial and informational consistent for effective comparison and analysis. However, due to the non-linear modality gaps that exist between images, making it difficult to focus only on the spatial position differences of the images and ignore the modality gaps. In this paper, to address this issue, we propose a new framework for Multi-Modal remote sensing image Registration, named MMRNet. The proposed framework comprises the following main aspects. First, a novel self-supervised Positional Misalignment Estimator (PME) is designed for multi-modal image registration. PME is able to efficiently overcome the modality gaps and learn the positional differences between multi-modal images more reliably, optimizing the registration loss by minimizing the positional differences directly. Then, a new paradigm of modality translation, termed Modality Perception Module (MPM), is introduced to effectively learn modality gaps and perform modality translation in the case of positional misalignment. Finally, we further design the modality perception guidance loss to supervise the modality translation task, which can encourage the fidelity of the generated pseudo-modality images. Our registration network integrates both rigid registration model and non-rigid registration model. Experimental results demonstrate that the proposed registration framework can obtain obviously superior performance in both rigid and non-rigid image registration tasks on optical-SAR data, optical-map data and optical-infrared data. © 1980-2012 IEEE.

关键词： image registration modality translation Multi-modal learning remote sensing processing rigid and non-rigid transformation

An edge-based model for non-Markovian sexually transmitted infections in coupled network

学校读者我要写书评

暂无评论

International Journal of Biomathematics 2020年第2期13卷 119-153页

作者： Xiaofeng Luo Junyuan Yang Zhen Jin School of Computer and Information Technology Shanxi University Taiyuan 030006P.R.China Complex System Research Center Shanxi University Taiyuan 030006ShanxiP.R.China Shanxi Key Laboratory of Mathematical Techniques and Big DataAnalysis on Disease Control and Prevention Shanxi University Taiyuan 030006ShanxiP.R.China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Taiyuan 030006 P.R.China

In this paper,allowing for general transmission and recovery times distributions,we proposed an edge-based age-structured-like compartmental model for STIs(EBACMS)in a coupled *** considered sexual transmissions between men with also heterosexual ***,we gave the general approach of proving the nonnegativity of solutions for the system coupling ordinary and partial differen-tial equations,which can be applied to all edge-based compartment *** then analyzed the epidemic threshold Ro with different distributions which couples the thresholds of the single-layer and bipartite networks in the percolation *** also studied the global stability of disease-free equilibrium with R0<1 and the final epidemic size F(the proportion of the population experiencing infection during the epidemic)with R0>*** addition,numerical simulations indicated that given a fixed exponential transmission distribution,a higher variance(with same mean)in general recovery distribution gives smaller R0 and *** analysis on Ro and F in terms of the parameters illustrated that male-to-male transmission routes have a greater impact on Rg and F than the heterosexual transmission routes for the Markovian transmission process and arbitrary recovery *** results provide a good theoretical guideline to consider the distributions of real-world STIs.

关键词： Coupled network EBCM non-Markovian process sexually transmitted disease epidemic age-structured

Utility-Oriented Underwater Image Quality Assessment Based on Transfer Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Weiling Lin, Rongfu Liao, Honggang Zhao, Tiesong Gu, Ke Le Callet, Patrick Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou350108 China Peng Cheng Laboratory Shenzhen518000 China The Faculty of Information Technology Beijing University of Technology Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Équipe Image Perception et Interaction Laboratoire des Sciences du Numérique de Nantes Université de Nantes France

The widespread image applications have greatly promoted the vision-based tasks, in which the Image Quality Assessment (IQA) technique has become an increasingly significant issue. For user enjoyment in multimedia systems, the IQA exploits image fidelity and aesthetics to characterize user experience;while for other tasks such as popular object recognition, there exists a low correlation between utilities and perceptions. In such cases, the fidelity-based and aesthetics-based IQA methods cannot be directly applied. To address this issue, this paper proposes a utility-oriented IQA in object recognition. In particular, we initialize our research in the scenario of underwater fish detection, which is a critical task that has not yet been perfectly addressed. Based on this task, we build an Underwater Image Utility Database (UIUD) and a learning-based Underwater Image Utility Measure (UIUM). Inspired by the top-down design of fidelity-based IQA, we exploit the deep models of object recognition and transfer their features to our UIUM. Experiments validate that the proposed transfer-learning-based UIUM achieves promising performance in the recognition task. We envision our research provides insights to bridge the researches of IQA and computer vision. Copyright © 2022, The Authors. All rights reserved.

关键词： Multimedia systems

Bayesian network model for learning arithmetic concepts

学校读者我要写书评

暂无评论

International Journal of Performability Engineering 2019年第3期15卷 939-948页

作者： Lv, Yali Jing, Tong Qian, Yuhua Liang, Jiye Wu, Jianai Miao, Junzhong School of Information Management Shanxi University of Finance and Economics Taiyuan030006 China Key Laboratory of Computational Intelligence Chinese Information Processing of Ministry of Education Shanxi University Taiyuan030006 China

An object usually belongs to multiple concepts, but some concepts can be judged directly while other concepts need to be inferred indirectly. To learn some arithmetic concepts from positive integer number sets, we address an arithmetic concept Bayesian network (ACBN) model by taking advantage of Bayesian networks. Specifically, we first give an ACBN model to represent the arithmetic concept knowledge and their direct relationships, and then we design an ACBN model learning algorithm based on domain knowledge. Furthermore, to infer indirectly some arithmetic concepts, we design the learning method of evidence concepts based on the idea of k-nearest neighbors, and then we propose the inference algorithm of the ACBN model. Finally, the experimental results demonstrate that the ACBN model can effectively learn some daily arithmetic concepts. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Bayesian networks

Few-Shot Medical Image Segmentation with High-Fidelity Prototypes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Song Yan, Shaxu Qi, Xiaozhi Gao, Jianxin Ye, Mao Zhang, Jianwei Zhu, Xiatian IMI Group School of Health Sciences and Engineering University of Shanghai for Science and Technology Shanghai China TAMS Group Department of Informatics Universität Hamburg Hamburg Germany School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Surrey Institute for People-Centred Artificial Intelligence Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom Shenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China

Few-shot Semantic Segmentation (FSS) aims to adapt a pretrained model to new classes with as few as a single labelled training sample per class. Despite the prototype based approaches have achieved substantial success, existing models are limited to the imaging scenarios with considerably distinct objects and not highly complex background, e.g., natural images. This makes such models suboptimal for medical imaging with both conditions invalid. To address this problem, we propose a novel Detail Self-refined Prototype Network (DSPNet) to constructing high-fidelity prototypes representing the object foreground and the background more comprehensively. Specifically, to construct global semantics while maintaining the captured detail semantics, we learn the foreground prototypes by modelling the multi-modal structures with clustering and then fusing each in a channel-wise manner. Considering that the background often has no apparent semantic relation in the spatial dimensions, we integrate channel-specific structural information under sparse channel-aware regulation. Extensive experiments on three challenging medical image benchmarks show the superiority of DSPNet over previous state-of-the-art methods. The code and data are available at https://***/tntek/DSPNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation