检索结果-内蒙古大学图书馆

3rd International Conference on High Performance Computing and Communication engineering, HPCCE 2023

作者： Jiang, Dexun Hao, Jianglong Chen, Yuanlong Li, Xingling Liu, Jie School of Information Engineering Harbin University Harbin150086 China Heilongjiang Provincial Key Laboratory of the Intelligent Perception and Intelligent Software Harbin University Harbin150086 China School of Software Harbin Institute of Technology Harbin150090 China School of Water Conservancy & Civil Engineering Northeast Agricultural University Harbin150030 China

ISBN: (数字)9781510674653

ISBN: (纸本)9781510674646

Cataract, the leading cause of global blindness, represents a focal concern within the field of blindness prevention. Its diagnosis primarily relies on the observation of lens opacification under slit-lamp examination, coupled with best-corrected visual acuity assessment. With the rapid evolution of artificial intelligence, the ophthalmic domain has increasingly incorporated AI technologies;however, research in the realm of cataracts remains relatively limited. This study employs computer vision segmentation techniques to obtain precise images of cataractous lens nuclei and utilizes deep learning methodologies for training and validation, yielding commendable results in the realm of graded diagnostic accuracy. The application of computer vision for meticulous cataractous lens nuclear region-of-interest imaging, coupled with adept deep learning methodologies, has demonstrated notable efficacy in achieving superior diagnostic outcomes. © 2024 SPIE.

关键词： Lenses

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithm for Person Re-Identification Based on Dual Network Architecture

引用

Computers, Materials & Continua 2025年第5期83卷 2889-2905页

作者： Meng Zhu Xingyue Wang Honge Ren Abeer Hakeem Linda Mohaisen College of Information Engineering Harbin UniversityHarbin150086China Heilongjiang Provincial Key Laboratory of the Intelligent Perception and Intelligent Software Harbin UniversityHarbin150086China College of Computer and Control Engineering Northeast Forestry UniversityHarbin150040China Heilongjiang Forestry Intelligent Equipment Engineering Research Center Northeast Forestry UniversityHarbin150040China Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia

Changing a person’s posture and low resolution are the key challenges for person re-identification(ReID)in various deep learning *** this paper,we introduce an innovative architecture using a dual attention network that includes an attentionmodule and a joint measurement module of spatial-temporal *** proposed approach can be classified into two main ***,the spatial attention feature map is formed by aggregating features in the spatial ***,the same operation is carried out on the channel dimension to formchannel attention ***,the receptive field size is adjusted adaptively tomitigate the changing person posture ***,we use a joint measurement method for the spatial-temporal information to fully harness the data,and it can also naturally integrate the information into the visual features of supervised ReID and hence overcome the low resolution *** experimental results indicate that our proposed algorithm markedly improves the accuracy in addressing changing human postures and low-resolution issues compared with contemporary leading *** proposed method shows superior outcomes on widely recognized benchmarks,which are the Market-1501,MSMT17,and DukeMTMC-reID ***,the proposed algorithmattains a Rank-1 accuracy of 97.4% and 94.9% mAP(mean Average Precision)on the Market-1501 ***,it achieves a 94.2% Rank-1 accuracy and 91.8% mAP on the DukeMTMC-reID dataset.

关键词： Person reidentification ReID computer vision self-attention spatial-temporal information

来源：评论

学校读者我要写书评

暂无评论

A Lightweight and High-Fidelity Model for Generalized Audio-Driven 3D Talking Face Synthesis 27th

A Lightweight and High-Fidelity Model for Generalized Audi...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Liu, Shunce Zhong, Yuwei Wang, Huixuan Peng, Jingliang Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China School of Information Science and Engineering University of Jinan Jinan China School of Software and Microelectronics Peking University Beijing China School of Software Shandong University Jinan China

ISBN: (纸本)9783031781247

We present LW-GeneFace, a lightweight and high-fidelity model for generalized audio-driven facial animation, in this paper. We develop this model by reducing the size while maintaining the synthetic quality of GeneFace, an audio-driven facial animation model known for its high fidelity and generalization capabilities. Specifically, we compress the first and the third stages of GeneFace as they dominate the model size. In the first stage, we propose a lightweight version of the WaveNet-based network inspired by MobileNetV3 and DP-block. It utilizes depthwise separable convolution and dual-path feature extraction to compress the network while maintaining effective feature extraction. The shared network structure in the dual-path feature extraction further reduces model complexity and improves training efficiency. In the third stage, we generate realistic 3D renderings at reduced model size by introducing novelties in RAD-NeRF. Technically, we reduce the hash table sizes in the grid-based encoding modules, as well as present a lightweight bottleneck MLP architecture to increase the non-linearity of the model. Experimental results demonstrate that LW-GeneFace achieves state-of-the-art performance with both model size and synthetic quality considered. The source code of LW-GeneFace will be released after acceptance of this paper. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Local Neighborhood Window Laplacian Eigenmaps 24

Adaptive Local Neighborhood Window Laplacian Eigenmaps

引用

13th International Conference on Computing and Pattern Recognition, ICCPR 2024

作者： Xu, Jiayi Huang, Qirui Zhao, Yang Pei, Jihong Yang, Xuan College of Electronics and Information Engineering Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen Guangdong China College of Computer Science and Software Engineering Shenzhen University Shenzhen Guangdong China

ISBN: (纸本)9798400717482

Manifold learning method is a dimensionality reduction method that treats the data in non-Euclidean space as a Euclidean space in a local scope. However, most existing manifold learning methods cannot obtain the true neighborbood relationship of each sample point well. Therefore, we propose a manifold learning method based on adaptive local neighborhood. This method can adaptively select a neighborhood window. It can be approximated as a local Euclidean space based on the sample characteristics. To implement this method, a specific manifold learning method, named Laplacian Eigenmap of Adaptive Local Neighborhood Window (ALNWLE) is proposed. ALNWLE mainly contains two modules, namely the manifold structure learning module (MSLM) and the manifold structure pattern recognition module (MSPR). MSLM constructs an adaptive local neighborhood adjacency matrix to constrain the learning of the manifold structure. MSPR uses the interpolation method to recognize new sample patterns. The adaptive local neighborhood method proposed in this paper is a general method which is applicable to any manifold learning method. © 2024 Copyright held by the owner/author(s).

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Neural Networks Based Behavioral Modeling of Dual-Band RF Power Amplifiers using Augmented BiLSTM Structures 6

Neural Networks Based Behavioral Modeling of Dual-Band RF Po...

引用

6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024

作者： Ahmed, Majid Dalbah, Ahmad Hammi, Oualid Ghannouchi, Fadhel M. College of Engineering American University of Sharjah Department of Electrical Engineering Sharjah United Arab Emirates University of Calgary Intelligent RF Radio Laboratory Department of Electrical and Software Engineering CalgaryAB Canada

ISBN: (纸本)9798350344349

This paper introduces a novel Bidirectional Long-Short-Term-Memory (BiLSTM) based Artificial Neural Network (ANN) model for the behavioral modeling of the nonlinear distortions observed in dual-band radiofrequency power amplification systems. Addressing the demand for energy-efficient and green wireless infrastructures in the era of multi-band transmissions, the proposed Augmented BiLSTM uses selected features of the input signals in each band to concurrently predict the output waveform in each band. Experimental benchmarking against the established 2D-Memory Polynomial (2D-MP) model, conducted with a ZHL-5W-2G S+ power amplifier prototype driven by concurrent dual-band 5G signals, reveals that the proposed model is able to achieve comparable performance. In addition to its accuracy, the main advantage of the proposed neural network based model lies in its ability to simultaneously model the amplifier's behavior in both bands with a single trainable structure. This contrasts with conventional analytically defined models, which require a dedicated structure per signal transmission band. © 2024 IEEE.

关键词： Power amplifiers

来源：评论

学校读者我要写书评

暂无评论

CNN channel pruning via gradient integration and knowledge distillation 17

CNN channel pruning via gradient integration and knowledge d...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Lian, Suyun Zhao, Yang Cai, Jiajian Pei, Jihong Shenzhen University The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

ISBN: (纸本)9798350387384

With the advancement of artificial intelligence technology, intelligent applications have permeated all aspects of human life, including automatic driving, intelligent security, and face recognition. Convolutional neural networks (CNNs) are essential models for AI, but their complexity increases with more available data. The complex models are unsuitable for edge devices like wearables and smartphones due to high memory and computational requirements. In this paper, the compact model is achieved by pruning some redundant output channels. To effectively measure the validity of the output channels, this paper proposes a channel pruning algorithm based on gradient integration, which combines the gradient of the channel with the model output and the channel's values. This pruning could destroy model accuracy, so knowledge distillation is introduced during fine-tuning to leverage the original model's reasoning ability. Experiments show that our approach improves accuracy by 0.51% while reducing parameters by 30.1% and FLOPs by 26% in the VGG16 model. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Step Feasibility-Aware and Error-Correctable Entailment Tree Generation 30

Step Feasibility-Aware and Error-Correctable Entailment Tree...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Song, Junyue Wu, Xin Cai, Yi School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

ISBN: (纸本)9782493814104

An entailment tree is a structured reasoning path that clearly demonstrates the process of deriving hypotheses through multiple steps of inference from known premises. It enhances the interpretability of QA systems. Existing methods for generating entailment trees typically employ iterative frameworks to ensure reasoning faithfulness. However, they often suffer from the issue of false feasible steps, where selected steps appear feasible but actually lead to incorrect intermediate conclusions. Moreover, the existing iterative frameworks do not consider error-prone search branches, resulting in error propagation. In this work, we propose SPEH: an iterative entailment tree generation framework with Step fesibility Perception and state Error Handling mechanisms. Step Feasibility Perception enables the model to learn how to choose steps that are not false feasible. State Error Handling includes error detection and backtracking, allowing the model to correct errors when entering incorrect search branches. Experimental results demonstrate the effectiveness of our approach in improving the generation of entailment trees. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation 30

A Logical Pattern Memory Pre-trained Model for Entailment Tr...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Yuan, Li Cai, Yi Ren, Haopeng Wang, Jiexin School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

ISBN: (纸本)9782493814104

Generating coherent and credible explanations remains a significant challenge in the field of AI. In recent years, researchers have delved into the utilization of entailment trees to depict explanations, which exhibits a reasoning process of how a hypothesis is deduced from the supporting facts. However, existing models often overlook the importance of generating intermediate conclusions with logical consistency from the given facts, leading to inaccurate conclusions and undermining the overall credibility of entailment trees. To address this limitation, we propose the logical pattern memory pre-trained model (LMPM). LMPM incorporates an external memory structure to learn and store the latent representations of logical patterns, which aids in generating logically consistent conclusions. Furthermore, to mitigate the influence of logically irrelevant domain knowledge in the Wikipedia-based data, we introduce an entity abstraction approach to construct the dataset for pre-training LMPM. The experimental results highlight the effectiveness of our approach in improving the quality of entailment tree generation. By leveraging logical entailment patterns, our model produces more coherent and reasonable conclusions that closely align with the underlying premises. Code and Data are released at https://***/YuanLi95/T5-LMPM. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Grounded Multimodal Procedural Entity Recognition for Procedural Documents: A New Dataset and Baseline 30

Grounded Multimodal Procedural Entity Recognition for Proced...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Ren, Haopeng Zeng, Yushi Cai, Yi Ye, Zhenqi Yuan, Li Zhu, Pinli School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

ISBN: (纸本)9782493814104

Much of commonsense knowledge in real world is in the form of procudures or sequences of steps to achieve particular goals. In recent years, knowledge extraction on procedural documents has attracted considerable attention. However, they often focus on procedural text but ignore a common multimodal scenario in the real world. Images and text can complement each other semantically, alleviating the semantic ambiguity suffered in text-only modality. Motivated by these, in this paper, we explore a problem of grounded multimodal procedural entity recognition (GMPER), aiming to detect the procedural entity and the corresponding bounding box groundings in images (i.e., visual entities). A new dataset (Wiki-GMPER) is built and extensive experiments are conducted to evaluate the effectiveness of our proposed model. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A survey for light field super-resolution

引用

High-Confidence Computing 2024年第1期4卷 118-129页

作者： Mingyuan Zhao Hao Sheng Da Yang Sizhe Wang Ruixuan Cong Zhenglong Cui Rongshan Chen Tun Wang Shuai Wang Yang Huang Jiahao Shen State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Key Laboratory of Data Science and Intelligent Computing International Innovation InstituteBeihang UniversityHangzhou 311115China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentation,and LF ***,there is a contradiction between spatial and angular resolution during the LF image acquisition *** overcome the above problem,researchers have gradually focused on the light field super-resolution(LFSR).In the traditional solutions,researchers achieved the LFSR based on various optimization frameworks,such as Bayesian and Gaussian *** learning-based methods are more popular than conventional methods because they have better performance and more robust generalization *** this paper,the present approach can mainly divided into conventional methods and deep learning-based *** discuss these two branches in light field spatial super-resolution(LFSSR),light field angular super-resolution(LFASR),and light field spatial and angular super-resolution(LFSASR),***,this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these ***,we discuss the potential innovations of the LFSR to propose the progress of our research field.

关键词： Light field super-resolution Convolutional neural network Transformer Sub-aperture image Epipolar-plane image

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：