检索结果-内蒙古大学图书馆

High Efficiency Wiener Filter-based Point Cloud Quality Enhancement for MPEG G-PCC

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wei, Yuxuan Wang, Zehan Guo, Tian Liu, Hao Shen, Liquan Yuan, Hui Shandong University School of Control Science and Engineering Jinan250061 China Ministry of Education Key Laboratory of Machine Intelligence and System Control Jinan250061 China Yantai University School of Computer and Control Engineering Yantai264005 China Shanghai University Shanghai Institute for Advanced Communication and Data Science Shanghai200072 China

Point clouds, which directly record the geometry and attributes of scenes or objects by a large number of points, are widely used in various applications such as virtual reality and immersive communication. However, due to the huge data volume and unstructured geometry, efficient compression of point clouds is very crucial. The Moving Picture Expert Group is establishing a geometry-based point cloud compression (G-PCC) standard for both static and dynamic point clouds in recent years. Although lossy compression of G-PCC can achieve a very high compression ratio, the reconstruction quality is relatively low, especially at low bitrates. To mitigate this problem, we propose a high efficiency Wiener filter that can be integrated into the encoder and decoder pipeline of G-PCC to improve the reconstruction quality as well as the rate-distortion performance for dynamic point clouds. Specifically, we first propose a basic Wiener filter, and then improve it by introducing coefficients inheritance and variance-based point classification for the Luma component. Besides, to reduce the complexity of the nearest neighbor search during the application of the Wiener filter, we also propose a Morton code-based fast nearest neighbor search algorithm for efficient calculation of filter coefficients. Experimental results demonstrate that the proposed method can achieve average Bjøntegaard delta rates of -6.1%, -7.3%, and -8.0% for Luma, Chroma Cb, and Chroma Cr components, respectively, under the condition of lossless-geometry-lossy-attributes configuration compared to the latest G-PCC encoding platform (i.e., geometry-based solid content test model version 7.0 release candidate 2) by consuming affordable computational complexity. © 2025 IEEE. All rights reserved.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Syntax-enhanced pre-trained model 59

Syntax-enhanced pre-trained model

引用

Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

作者： Xu, Zenan Guo, Daya Tang, Duyu Su, Qinliang Shou, Linjun Gong, Ming Zhong, Wanjun Quan, Xiaojun Jiang, Daxin Duan, Nan School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Microsoft Research Asia Beijing China Microsoft Search Technology Center Asia Beijing China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781954085527

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens. © 2021 Association for Computational Linguistics

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Feature-Based Local Ensemble Framework for Multi-Agent Reinforcement Learning

Feature-Based Local Ensemble Framework for Multi-Agent Reinf...

引用

International Symposium on Computer Science and Intelligent Controls (ISCSIC)

作者： Xinyu Zhao Jianxiang Liu Faguo Wu Xiao Zhang School of Mathematical Sciences Beihang University Beijing China Institute for Artificial Intelligence Beihang University Beijing China Zhongguancun Laboratory Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing China Key Laboratory of Mathematics Informatics and Behavioral Semantics (LMIB) Beihang University Beijing China Zhongguancun Laboratory Beijing China

ISBN: (数字)9798350380286

ISBN: (纸本)9798350380293

The use of centralized value networks is an important training method in multi-agent reinforcement learning (MARL). Existing methods usually utilize value decomposition to enable agents to achieve localized learning. However, these methods do not take into account sample efficiency, and the introduction of additional networks will also bring more computational costs. Therefore, it is necessary to introduce the ensemble idea of making full use of the replay buffer. The general ensemble learning approach is to introduce sub-models into the value network, and its application in multi-agent systems is not yet mature. In this paper, we firstly implement a multi-agent ensemble technique with locally shared parameters in the network by introducing a feature-based grouping mechanism. Secondly, we propose random and feature-based grouping principles and design a dimension reduction scheme for action-state space. Finally, our approach was evaluated on the benchmark platform, Multi-Agent Particle Environment (MPE), and compared with baseline algorithms. The results demonstrated that our method exhibited notable advantages in terms of achieving higher scores and converging rapidly.

关键词： Training Dimensionality reduction Computer science Reinforcement learning Stability analysis Explosions Computational efficiency Ensemble learning Multi-agent systems Intelligent control

来源：评论

学校读者我要写书评

暂无评论

Multimodal surface material classification based on ensemble learning with optimized features 22

Multimodal surface material classification based on ensemble...

引用

22nd IEEE International Conference on E-Health Networking, Application and Services, HEALTHCOM 2020

作者： Liu, Xiang Wu, Hancheng Fang, Senlin Yi, Zhengkun Wu, Xinyu CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen Key Laboratory of Smart Sensing and Intelligent Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

ISBN: (纸本)9781728162676

In this paper, we propose a novel method for multimodal material classification based on ensemble learning and optimized features. The proposed method consists of three key steps. Firstly, we extract a set of features for each modality. Compared to existing methods, the extracted features are relatively simple but more effective when they are incorporated into the classifiers. Then, the feature selection algorithms, including Multi-Cluster Feature Selection (MCFS) and Laplacian Score (LS) are employed to reduce the feature dimension due to the curse of dimensionality. Finally, an ensemble learning method is proposed to integrate the merits of different feature selection methods. The effectiveness of the proposed method is demonstrated on the LMT-108 surface material dataset which includes multiple modalities such as sound, acceleration, and image. The experimental results have shown that our approach performs better than the competing methods. © 2021 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Resource-Aware Multi-Criteria Vehicle Participation for Federated Learning in Internet of Vehicles

SSRN

引用

SSRN 2023年

作者： Wen, Jie Zhang, Jingbo Zhang, Zhixia Cui, Zhihua Cai, Xingjuan Chen, Jinjun The Shanxi Key Laboratory of Advanced Control and Equipment intelligence Taiyuan University of Science and Technology Shanxi Taiyuan China The Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan University of Science and Technology Shanxi Taiyuan China The State Key Lab for Novel Software Technology Nanjing University China Department of Computing Technologies Swinburne University of Technology Melbourne Australia

Federated learning (FL), as a safe distributed training mode, provides strong support for the edge intelligence of the Internet of Vehicles (IoV) to realize efficient collaborative control and safe data sharing. However, due to the resource limitation and the instability of training environment in the complex IoV, ideal performance of FL cannot be achieved. Since considering the actual resource constraints and federated task requirements, the diversified device selection criteria make the resource-aware vehicle selection problem become a multi-criteria selection problem. To effectively support FL for IoV, the resource-aware multi-criteria vehicle selection problem was described as a many-objective optimization problem, and proposed a resource-aware many-objective vehicle selection model (RA-MaOVSM) to optimize resource efficiency. The RA-MaOVSM considering heterogeneous resources (like computation resources, communication resources, energy resources and data resources) of on-board devices in IoV, and realizes the joint optimization of learning efficiency, energy cost and global performance. Additionally, a novel probability distribution combination game strategy is applied to many-objective evolutionary algorithm (MaOEA) for improving the model solving performance. Simulation results demonstrate that RA-MaOVSM can effectively optimize the IoV resources and FL model performance, and the designed algorithm exhibits good convergence and distribution, achieving a good balance among multiple device selection criteria. © 2023, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

A Novel Duo-Stage driven Deep Neural Network Approach for Mitigating Electrode Shift Impact on Myoelectric Pattern Recognition Systems

A Novel Duo-Stage driven Deep Neural Network Approach for Mi...

引用

IEEE International Workshop on Medical Measurement and Applications (MEMEA)

作者： Frank Kulwa Oluwarotimi Williams Samuel Mojisola Grace Asogbon Tolulope Tofunmi Oyemakinde Olumide Olayinka Obe Guanglin Li CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Institute of Advanced Technology (SIAT) Chinese Academy of Sciences (CAS) Shenzhen Guangdong China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen Guangdong China School of Computing and Engineering University of Derby Derby United Kingdom Department of Computer Science Federal University of Technology Akure Nigeria

A major barrier to the commercialization of pattern recognition (PR)-based myoelectric prostheses is the lack of robustness to confounding factors such as electrode shift which has been lingering for years. To overcome this challenge, a novel Duo-Stage Convolutional Neural Network (DS-CNN) is proposed. The DS-CNN is comprised of two cascaded stages in which the first stage deciphers the occurrence of a particular kind of shift upon which a requisite CNN model is triggered in the second stage for accurate decoding of individual motion intent, which is necessary for initiating robust control of the prostheses. The proposed scheme works on raw EMG signals as input which reduces the preprocessing time that would be required in conventional machine learning-based PR schemes, to effectively mitigate both transverse and longitudinal shifts using the same network architecture. This approach was validated for four distinct electrode shift conditions (with shifts in the range of 7.50mm-10.05mm) in a dataset obtained from 18 able-bodied subjects that performed 8 classes of targeted hand gestures. The experimental results show that the proposed dual-stage driven deep neural network model can adequately resolve the effects of electrode shift with classification accuracy near the No-shift scenario (< 1.70% difference between shift mitigation and No shift scenarios). These outcomes suggest that our method can provide a practical solution for adaptation to electrode shift, thus improving the robustness of the EMG pattern recognition systems in both clinical and commercial settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Knowledge Distillation

Multi-Label Knowledge Distillation

引用

International Conference on Computer Vision (ICCV)

作者： Penghui Yang Ming-Kun Xie Chen-Chen Zong Lei Feng Gang Niu Masashi Sugiyama Sheng-Jun Huang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China School of Computer Science and Engineering Nanyang Technological University Singapore RIKEN Center for Advanced Intelligence Project The University of Tokyo Tokyo Japan

Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning. However, these methods can hardly be extended to the multi-label learning scenario, where each instance is associated with multiple semantic labels, because the prediction probabilities do not sum to one and feature maps of the whole example may ignore minor classes in such a scenario. In this paper, we propose a novel multi-label knowledge distillation method. On one hand, it exploits the informative semantic knowledge from the logits by dividing the multi-label learning problem into a set of binary classification problems; on the other hand, it enhances the distinctiveness of the learned feature representations by leveraging the structural information of label-wise embeddings. Experimental results on multiple benchmark datasets validate that the proposed method can avoid knowledge counteraction among labels, thus achieving superior performance against diverse comparing methods. Our code is available at: https://***/penghui-yang/L2D.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discriminative distillation to reduce class confusion in continual learning

arXiv

引用

arXiv 2021年

作者： Zhong, Changhong Cui, Zhiying Wang, Ruixuan Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou510000 China

Successful continual learning of new knowledge would enable intelligent systems to recognize more and more classes of objects. However, current intelligent systems often fail to correctly recognize previously learned classes of objects when updated to learn new classes. It is widely believed that such downgraded performance is solely due to the catastrophic forgetting of previously learned knowledge. In this study, we argue that the class confusion phenomena may also play a role in downgrading the classification performance during continual learning, i.e., the high similarity between new classes and any previously learned classes would also cause the classifier to make mistakes in recognizing these old classes, even if the knowledge of these old classes is not forgotten. To alleviate the class confusion issue, we propose a discriminative distillation strategy to help the classify well learn the discriminative features between confusing classes during continual learning. Experiments on multiple natural image classification tasks support that the proposed distillation strategy, when combined with existing methods, is effective in further improving continual learning. Copyright © 2021, The Authors. All rights reserved.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Aggregated contextual transformations for high-resolution image inpainting

arXiv

引用

arXiv 2021年

作者： Zeng, Yanhong Fu, Jianlong Chao, Hongyang Guo, Baining School of Computer Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Microsoft Research

Image inpainting that completes large free-form missing regions in images is a promising yet challenging task. State-of-the-art approaches have achieved significant progress by taking advantage of generative adversarial networks (GAN). However, these approaches can suffer from generating distorted structures and blurry textures in high-resolution images (e.g., 512 × 512). The challenges mainly drive from (1) image content reasoning from distant contexts, and (2) fine-grained texture synthesis for a large missing region. To overcome these two challenges, we propose an enhanced GAN-based model, named Aggregated COntextual-Transformation GAN (AOT-GAN), for high-resolution image inpainting. Specifically, to enhance context reasoning, we construct the generator of AOT-GAN by stacking multiple layers of a proposed AOT block. The AOT blocks aggregate contextual transformations from various receptive fields, allowing to capture both informative distant image contexts and rich patterns of interest for context reasoning. For improving texture synthesis, we enhance the discriminator of AOT-GAN by training it with a tailored mask-prediction task. Such a training objective forces the discriminator to distinguish the detailed appearances of real and synthesized patches, and in turn facilitates the generator to synthesize clear textures. Extensive comparisons on Places2, the most challenging benchmark with 1.8 million high-resolution images of 365 complex scenes, show that our model outperforms the state-of-the-art by a significant margin in terms of FID with 38.60% relative improvement. A user study including more than 30 subjects further validates the superiority of AOT-GAN. We further evaluate the proposed AOT-GAN in practical applications, e.g., logo removal, face editing, and object removal. Results show that our model achieves promising completions in the real-world. We release code and models in https://***/researchmm/AOT-GAN-for-Inpainting. © 2021, CC BY-NC-ND.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Lane Detection Method for Advancing Sustainable Energy Internet

A Lane Detection Method for Advancing Sustainable Energy Int...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Xiting Peng Yang Yang Xiaoyu Zhang Xiaoling Zhang School of Information Science and Engineering Shenyang University of Technology Liaoning Liaohe Laboratory Shenyang Key Laboratory of Advanced Computing and Application Innovation Shenyang China School of Information Science and Engineering Shenyang University of Technology Shenyang China School of Artificial Intelligence Shenyang University of Technology Shenyang Key Laboratory of Industrial Intelligent Chip and Network System Innovation Application Shenyang China

ISBN: (数字)9798331523527

ISBN: (纸本)9798331523534

Artificial intelligence (AI) technology plays a key role in driving the development of a green and smart Energy Internet. As one of the application areas of the Energy Internet, lane detection in intelligent transportation systems can provide accurate real-time traffic data, thus supporting intelligent scheduling and resource optimization, reducing congestion, energy consumption, and emissions, and improving overall energy efficiency. Therefore, deep learning-based lane detection methods can further enhance the intelligence level of the Energy Internet and promote its efficient operation. However, current methods often rely on Convolutional Neural Networks (CNNs), which excel at local feature extraction but struggle to capture global information in complex conditions. In varying light, shadows, and obstacles, CNNs struggle to integrate information, leading to inaccuracies, particularly in dense traffic or complex road structures, where diverse local features result in identification errors and hinder lane continuity. This reduces decision-making efficiency and increases energy consumption. Consequently, we present LFKNet, a lane detection framework designed for the fusion of the Lane Focus Mechanism (LFM) and Kolmogorov-Arnold Network (KAN) to enhance accuracy and robustness. It consists of two key components: the Lane Focus Mechanism , which utilizes the geometrical topology of lanes for improved global fea ture extraction in complex scenarios, and the Kolmogorov-Arnold Network, which employs a learnable nonlinear activation function to optimize performance on complex and nonlinear features. The experiments demonstrate that LFKNet achieves 97.00% accuracy with a 97.76% F1-score on the Tusimple dataset. It also achieves a 79.43% F1-score on the CULane dataset. Overall, LFKNet’s performance validates its effectiveness in lane detection, enabling accurate traffic monitoring and analysis while providing reliable data support for the Energy Internet.

关键词： Energy consumption Accuracy Lane detection Decision making Energy Internet System integration Feature extraction Robustness Topology Artificial intelligence

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：