检索结果-内蒙古大学图书馆

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Zhou, Yiquan Chen, Meng Lei, Yi Zhu, Jihua Zhao, Weifeng Xi'an Jiaotong University School of Software Engineering Xi'an China School of Computer Science Xi'an China Tencent Music Entertainment Lyra Lab Shenzhen China

ISBN: (纸本)9798350306897

This paper presents the T02 team's system for the Singing Voice Conversion Challenge 2023 (SVCC2023). Our system entails a VITS-based SVC model, incorporating three modules: a feature extractor, a voice converter, and a postprocessor. Specifically, the feature extractor provides F0 contours and extracts speaker-independent linguistic content from the input singing voice by leveraging a HuBERT model. The voice converter is employed to recompose the speaker timbre, F0, and linguistic content to generate the waveform of the target speaker. Besides, to further improve the audio quality, a fine-tuned DSPGAN vocoder is introduced to resynthesise the waveform. Given the limited target speaker data, we utilize a two-stage training strategy to adapt the base model to the target speaker. During model adaptation, several tricks, such as data augmentation and joint training with auxiliary singer data, are involved. Official challenge results show that our system achieves superior performance, especially in the cross-domain task, ranking 1st and 2nd in naturalness and similarity, respectively. Further ablation justifies the effectiveness of our system design. © 2023 IEEE.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

A Neural Architecture Search Method with Multi-Dimensional Correlation Representation for Fault Diagnosis 9

A Neural Architecture Search Method with Multi-Dimensional C...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Liu, Yumeng Wang, Tingqi Zheng, Xu Tian, Ling Wang, Hongan Institute of Software Chinese Academy of Sciences Beijing Key Laboratory of Human-Computer Interaction Beijing China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu China

ISBN: (纸本)9798350319804

As deep learning has become more widely used for fault diagnosis, the shortcomings of model transferability and human model design costs are growing increasingly evident. The current work has tackled each of these two issues. Domain adaptation methods can provide transportability by mapping data to a common domain. For the consumption of manually constructed networks, Neural Architecture Search (NAS) is an intelligent solution that automatically select the ideal network structure. Unfortunately, there is little work to connect these two methodologies in fault diagnosis. Furthermore, these approaches are incapable in extracting internal correlations from instrumental signal data. In this paper, we propose a transferrable NAS fault diagnosis method, which maximizes savings in manual costs. We also integrate graph neural networks (GNN) in a stepwise manner into the NAS and domain adaptation to provide a multi-dimension correlation representation. Firstly, we structure the signal data into graph based on temporal relationships. Then, NAS designs automatically for selecting the optimal network structure and useful features. In NAS, graph encoder of GNN is used to establish internal relationships. Finally, domain adaptation provides transferability. At the same time, GNN's weights in domain adaptation help to further mine data internal associations. We tested our method on two publicly available datasets and performed comparisons. The experimental results show the proposed method has superior performance. © 2023 IEEE.

关键词： Domain Adaptation Fault Diagnosis Graph Neural Network Neural Architecture Search

来源：评论

学校读者我要写书评

暂无评论

General Optimal Trajectory Planning:Enabling Autonomous Vehicles with the Principle of Least Action

引用

engineering 2024年第2期33卷 63-76页

作者： Heye Huang Yicong Liu Jinxin Liu Qisong Yang Jianqiang Wang David Abbink Arkady Zgonnikov School of Vehicle and Mobility Tsinghua UniversityBeijing 100084China Department of Cognitive Robotics Faculty of MechanicalMaritime and Materials Engineering(3mE)Delft University of TechnologyDelft 2628Netherlands Department of Software Technology Faculty of Electrical EngineeringMathematics and Computer ScienceDelft University of TechnologyDelft 2628Netherlands Xi’an Institute of High-Technology Xi’an 710051China

This study presents a general optimal trajectory planning(GOTP)framework for autonomous vehicles(AVs)that can effectively avoid obstacles and guide AVs to complete driving tasks safely and ***,we employ the fifth-order Bezier curve to generate and smooth the reference path along the road *** coordinates are then transformed to achieve the curvature continuity of the generated *** the road constraints and vehicle dynamics,limited polynomial candidate trajectories are generated and smoothed in a curvilinear coordinate ***,in selecting the optimal trajectory,we develop a unified and auto-tune objective function based on the principle of least action by employing AVs to simulate drivers’behavior and summarizing their manipulation characteristics of“seeking benefits and avoiding losses.”Finally,by integrating the idea of receding-horizon optimization,the proposed framework is achieved by considering dynamic multi-performance objectives and selecting trajectories that satisfy feasibility,optimality,and *** simulations and experiments are performed,and the results demonstrate the framework’s feasibility and effectiveness,which avoids both dynamic and static obstacles and applies to various scenarios with multi-source interactive traffic ***,we prove that the proposed method can guarantee real-time planning and safety requirements compared to drivers’manipulation.

关键词： Autonomous vehicle Trajectory planning Multi-performance objectives Principle of least action

来源：评论

学校读者我要写书评

暂无评论

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

引用

International Journal of computer Vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science Wenzhou-Kean University Wenzhou325060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore639798 Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215400 China Jarvis Research Center Tencent YouTu Lab Shenzhen518703 China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Robust Adversarial Defenses in Federated Learning: Exploring the Impact of Data Heterogeneity

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 6005-6018页

作者： Li, Qian Wu, Di Zhou, Dawei Lin, Chenhao Liu, Shuai Wang, Cong Shen, Chao Xi’an Jiaotong University Ministry of Education Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an 710049 China Xi’an Jiaotong University School of Computer Science and Technology Xi’an 710049 China Xidian University Xi’an 710071 China Xi’an Jiaotong University School of Software Xi’an 710049 China City University of Hong Kong Department of Computer Science Hong Kong

Federated Learning (FL) enables geographically distributed clients to collaboratively train machine learning models by exchanging local model parameters while preserving data privacy. In practice, FL faces two critical challenges. First, it is vulnerable to security issues as malicious clients would artificially harm the functionality of FL by launching poisoning attacks. Second, the inherent data heterogeneity among clients (termed Non-IID data in FL) naturally arises from distributed data ownership and significantly degrades model convergence and accuracy. However, with studies separately devoted to these two research lines, the interplay between data heterogeneity and security remains poorly understood. In this paper, we systematically investigate the relationship between data heterogeneity and adversarial robustness in FL. Specifically, we propose novel data partitioning algorithms that simulate Label-Conditional Non-IID and Feature-Conditional Non-IID with quantifiable heterogeneity levels. Further, we conduct extensive experiments to evaluate classical defense methods in the practical FL environment under state-of-the-art untargeted attacks. With results in various settings, we separately analyze the connection between Non-IID to defenses and attacks. Regarding attacks, with similar effects on models, Non-IID impacts the training in a different way compared with attacks. The interaction between attacks and Non-IID provides an opportunity to cause severe damage to FL. Regarding defenses, Non-IID induces heterogeneity in model distribution among clients which raises the difficulty of maintaining fidelity and robustness for defense methods. © 2005-2012 IEEE.

关键词： Adversarial Defenses Federated Learning Poisoning attacks Security

来源：评论

学校读者我要写书评

暂无评论

QUEST: quadruple multimodal contrastive learning with constraints and self-penalization 24

QUEST: quadruple multimodal contrastive learning with constr...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Qi Song Tianxiang Gong Shiqi Gao Haoyi Zhou Jianxin Li School of Software Beihang University School of Computer Science and Engineering Beihang University School of Software Beihang University and Zhongguancun Laboratory Beijing School of Computer Science and Engineering Beihang University and Zhongguancun Laboratory Beijing

ISBN: (纸本)9798331314385

Multimodal contrastive learning (MCL) has recently demonstrated significant success across various tasks. However, the existing MCL treats all negative samples equally and ignores the potential semantic association with positive samples, which limits the model's ability to achieve fine-grained alignment. In multi-view scenarios, MCL tends to prioritize shared information while neglecting modality-specific unique information across different views, leading to feature suppression and suboptimal performance in downstream tasks. To address these limitations, we propose a novel contrastive framework named QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization. In the QUEST framework, we propose quaternion contrastive objectives and orthogonal constraints to extract sufficient unique information. Meanwhile, a shared information-guided penalization is introduced to ensure that shared information does not excessively influence the optimization of unique information. Our method leverages quaternion vector spaces to simultaneously optimize shared and unique information. Experiments on multiple datasets show that our method achieves superior performance in multimodal contrastive learning benchmarks. On public benchmark, our approach achieves state-of-the-art performance, and on synthetic shortcut datasets, we outperform existing baseline methods by an average of 97.95% on the CLIP model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Depth Map through Weighted Combination of Guided Image Filters in Shape-From-Focus 2

Enhancement of Depth Map through Weighted Combination of Gui...

引用

2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022

作者： Ahmed, Zubair Shahzad, Ahsan Ali, Usman Department of Computer & Software Engineering Islamabad Pakistan Korea University of Technology and Education School of Computer Science & Engineering Korea Republic of

ISBN: (纸本)9781665498197

Estimation of depth map plays a key role in a number of computer vision applications. Shape from focus is a monocular approach that uses image focus as a cue to reconstruct 3D shapes. In the literature, a variety of guided image filters have been proposed to enhance the depth map individually. Among them, some have excess computational time burden, and some others produce unsatisfactory results. This paper proposed a framework for the enhancement of depth map by using a weighted combination of selected guided filters in shape from focus. The optimized weights are obtained using the particle swarm optimization approach, and the subset of best-performing filters is identified through a sequential forward search method. The experimental results have demonstrated that the proposed framework provides considerably improved depth maps. © 2022 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation 38

Addressing Asynchronicity in Clinical Multimodal Fusion via ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yao, Wenfang Liu, Chen Yin, Kejing Cheung, William K. Qin, Jing School of Nursing The Hong Kong Polytechnic University Hong Kong Department of Computer Science Hong Kong Baptist University Hong Kong School of Software Engineering South China University of Technology China

Integrating multi-modal clinical data, such as electronic health records (EHR) and chest X-ray images (CXR), is particularly beneficial for clinical prediction tasks. However, in a temporal setting, multi-modal data are often inherently asynchronous. EHR can be continuously collected but CXR is generally taken with a much longer interval due to its high cost and radiation dose. When clinical prediction is needed, the last available CXR image might have been outdated, leading to suboptimal predictions. To address this challenge, we propose DDL-CXR, a method that dynamically generates an up-to-date latent representation of the individualized CXR images. Our approach leverages latent diffusion models for patient-specific generation strategically conditioned on a previous CXR image and EHR time series, providing information regarding anatomical structures and disease progressions, respectively. In this way, the interaction across modalities could be better captured by the latent CXR generation process, ultimately improving the prediction performance. Experiments using MIMIC datasets show that the proposed model could effectively address asynchronicity in multimodal fusion and consistently outperform existing methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MOFC: Network Embedding Based on Multi-Orders Friends Contribution for User Identification 6

MOFC: Network Embedding Based on Multi-Orders Friends Contri...

引用

6th International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2023

作者： Zhang, Jiajing Xu, Neng Chen, Jinlan Ma, Tinghuai School of Electronics and Information Engineering Anhui Jianzhu University China School of Mechanical and Electrical Engineering Anhui Jianzhu University China School of Computer and Software Nanjing University of Information Science & Technology China

ISBN: (纸本)9798400709203

Different social networks are independent of each other, and identifying the same person in different social networks is of great significance for cross-network information dissemination and the construction of a complete portrait of users. Existing methods for user identification via network embedding ignore the different contributions of neighbors and only consider low-order friend relationships. Aiming at these shortcomings, an algorithm of Network Embedding based on Multi-Orders Friends Contribution for User Identification (MOFC) is proposed. Firstly, the difference contribution degree of nodes to their friends is used to assign different weights to the edges between the nodes and their friends. Secondly, the embedding representation vectors of multi-orders friend contribution are used to describe the different orders friend relations of the nodes, and then the representation vectors of different orders are merged to more comprehensively represent network features. Finally, the fusion representation vectors are used as input sample of a neural network to train and build a user identification model. Experiments show that the evaluation indicators of the model have been significantly improved compared with several advanced methods. Compared with the newer and better the CSN_LINE, the accuracy rate of MOFC can be increased by 4.83%, the precision rate can be increased by 6.77%, the recall rate can be increased by 5.49%, the F1-score can be increased by 5.43%. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

Short-Term Electricity Load Forecasting Based on T-CFSFDP Clustering and Stacking-BiGRU-CBAM

引用

computers, Materials and Continua 2025年第1期84卷 1189-1202页

作者： Deng, Mingliang Zhang, Zhao Zhou, Hongyan Chen, Xuebo School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan114051 China

To fully explore the potential features contained in power load data, an innovative short-term power load forecasting method that integrates data mining and deep learning techniques is proposed. Firstly, a density peak fast search algorithm optimized by time series weighting factors is used to cluster and analyze load data, accurately dividing subsets of data into different categories. Secondly, introducing convolutional block attention mechanism into the bidirectional gated recurrent unit (BiGRU) structure significantly enhances its ability to extract key features. On this basis, in order to make the model more accurately adapt to the dynamic changes in power load data, subsets of different categories of data were used for BiGRU training based on attention mechanism, and extreme gradient boosting was selected as the meta model to effectively integrate multiple sets of historical training information. To further optimize the parameter configuration of the meta model, Bayesian optimization techniques are used to achieve automated adjustment of hyperparameters. Multiple sets of comparative experiments were designed, and the results showed that the average absolute error of the method in this paper was reduced by about 8.33% and 4.28%, respectively, compared with the single model and the combined model, and the determination coefficient reached the highest of 95.99, which proved that the proposed method has a better prediction effect. Copyright © 2025 The Authors.

关键词： Neural networks

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：