检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Haodong Shi Zhao Kang Ke Yan Sicong Liu Yichen Xin School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute for Advanced Study UESTC Shenzhen China KASHI Institute of Electronics and Information Industry Kashi China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Community detection is a crucial task in complex network analysis, and existing game-theoretic-based community detection methods struggle to achieve a balance between local and global competition and cooperation. This paper introduce a Dual-scale Game theoretical Framework (Dual-GTF) for community detection. First, a new modularity function is proposed, enabling each node to incorporate additional expansion information at the community scale by collaborating closely with the individual scale modularity function. Subsequently, leveraging cooperative and competitive strategies informed by realistic empiricism, this paper integrate community-scale information to facilitate effective role division within communities. Evaluations of real-world datasets demonstrate that this approach, Dual-GTF, achieves superior convergence and performance results in most cases.

关键词： Measurement Social networking (online) Collaboration Games Complex networks Nash equilibrium Cybernetics Convergence

来源：评论

学校读者我要写书评

暂无评论

A Rationale-Centric Framework for Human-in-the-loop Machine Learning 60

A Rationale-Centric Framework for Human-in-the-loop Machine ...

引用

60th Annual Meeting of the Association for Computational Linguistics, ACL 2022

作者： Lu, Jinghui Yang, Linyi Namee, Brian Mac Zhang, Yue The Insight Centre for Data Analytics University College Dublin Ireland School of Computer Science University College Dublin Ireland School of Engineering Westlake University China Institute of Advanced Technology Westlake Institute for Advanced Study China SenseTime Research

ISBN: (纸本)9781955917216

We present a novel rationale-centric framework with human-in-the-loop - Rationales-centric Double-robustness Learning (RDL) - to boost model out-of-distribution performance in few-shot learning scenarios. By using static semi-factual generation and dynamic human-intervened correction, RDL exploits rationales (i.e. phrases that cause the prediction), human interventions and semi-factual augmentations to decouple spurious associations and bias models towards generally applicable underlying distributions, which enables fast and accurate generalisation. Experimental results show that RDL leads to significant prediction benefits on both in-distribution and out-of-distribution tests compared to many state-of-the-art benchmarks-especially for few-shot learning scenarios. We also perform extensive ablation studies to support in-depth analyses of each component in our framework. © 2022 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

Fuzzy Logic-Based Probabilistic Forecasting of Short-term Trajectory for Autonomous Vehicles

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Wang, Leilei Deng, Xiaoheng Gui, Jinsong Wan, Shaohua Xi'an University of Technology School of Computer Science and Engineering Xi'an710048 China Central South University School of Electronic Information Changsha410075 China Central South University Shenzhen Research Institute Shenzhen518057 China University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518038 China

The rapid advancement of Intelligent Transportation Systems (ITS) has led to the widespread adoption of autonomous vehicles as common consumer electronics. Accurate and real-time vehicle trajectory forecasting significantly enhances the potential of these vehicles. However, traditional time series forecasting methods are susceptible to noise and require linear sequences, making them inadequate for integrating traffic rules and environmental factors. This limitation often results in unreliable multi-modal predictions and reduced prediction accuracy. To address these challenges, this paper introduces a Probabilistic Trajectory Forecasting approach (PTFO), specifically designed for short-term trajectory forecasting. By analyzing actual vehicle trajectory data, we applied fuzzy logic to demonstrate that vehicle trajectories follow a Gaussian distribution in the short term. Based on this finding, we further categorize vehicle trajectory motion into two distinct modes: single mode and complex mode, to better capture the variability in vehicular motion. Additionally, we conduct a thorough investigation into how vehicular spatial relationships and extrinsic factors influence trajectory predictions, thereby improving prediction accuracy. The PTFO algorithm's strengths lie in its ability to incorporate various motion modes and hidden factors affecting future trajectories. Simulation results indicate that the PTFO algorithm outperforms other probabilistic trajectory forecasting techniques. © 1975-2011 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Multi-Attribute Dynamic Learning for 3D Face Reconstruction and Dense Alignment in the Unconstrained Environment

Multi-Attribute Dynamic Learning for 3D Face Reconstruction ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Lei Li Fuqiang Liu Qi Wang Jiahao Li Junyuan Wang Xiang Li Yanni Wang College of Electronic and Information Engineering Tongji University Shanghai China School of Computer Science and Technology Huaibei Normal University Huaibei China Institute for Advanced Study Tongji University Shanghai China School of Information Science and Technology Fudan University Shanghai China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

3D face reconstruction and dense alignment have been challenging problems in unconstrained environments. Existing methods usually designed neural networks to regress the 62 facial attribute parameters that determine identity, expression, and pose, while the different sensitivities of different facial attributes to the varying unconstrained environment were not considered. To exploit this for the purpose of improving the dense alignment and face reconstruction accuracy, we propose a multi-attribute dynamic learning network (MADLNet) to recalibrate the label confidence for different facial attributes according to their sensitivities to the environment, which allows the model to adaptively refine their understanding of facial attributes without adding extra parameters. Specifically, we first randomly generate a number of hard samples with occlusion rates ranging from 0% to 60%. This creates challenging samples reflecting the different occlusion responses of different facial attributes. Then, we define sensitivities to occlusion for different facial attributes to recalibrate the confidence of facial multi-attribute labels so as to disentangle the optimization process. Finally, we calculate the multi-scale similarity between input samples and the created challenging samples to fine-tune label confidence, which addresses the misalignment problem between occlusion rates and semantic information caused by random occlusion operation. Extensive experiments conducted on the AFLW2000-3D and AFLW datasets effectively confirm the efficacy of our approach.

关键词： Adaptation models Solid modeling Three-dimensional displays Sensitivity Semantics Neural networks Indexes

来源：评论

学校读者我要写书评

暂无评论

A Fast Algorithm for Finding the Roots of Polynomials over Finite fields

A Fast Algorithm for Finding the Roots of Polynomials over F...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Pingping Li Leilei Yu Linqi Song Hanxu Hou School of Computer Science & Technology Dongguan University of Technology Dongguan China Shenzhen Institute for Advanced Study University of Electronic Science & Technology of China Department of Computer Science City University of Hong Kong Hong Kong China School of Electrical Engineering & Intelligentization Dongguan University of Technology Dongguan China

Finding all roots of polynomials over finite fields is a crucial problem in algebraic coding techniques, such as decoding BCH codes and Reed-Solomon codes. The current commonly used methods are Chien search or fast Fourier transform (FFT), which evaluates all elements in a finite field and results in field multiplications whose number increases linearly with the field size. In this paper, we propose a new approach that enables the multiplicative complexity to grow sub-linearly with the field size. To our knowledge, this is the currently lowest multiplicative complexity for this problem. Additionally, the proposed approach maintains the additive complexity similar to that of FFT-based method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solving Aspect Category Sentiment Analysis as a Text Generation Task

Solving Aspect Category Sentiment Analysis as a Text Generat...

引用

2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021

作者： Liu, Jian Teng, Zhiyang Cui, Leyang Liu, Hanmeng Zhang, Yue School of Computer Science Fudan University China School of Engineering Westlake University China Institute of Advanced Technology Westlake Institute for Advanced Study China

ISBN: (纸本)9781955917094

Aspect category sentiment analysis has attracted increasing research attention. The dominant methods make use of pre-trained language models by learning effective aspect category-specific representations, and adding specific output layers to its pre-trained representation. We consider a more direct way of making use of pre-trained language models, by casting the ACSA tasks into natural language generation tasks, using natural language sentences to represent the output. Our method allows more direct use of pre-trained knowledge in seq2seq language models by directly following the task setting during pre-training. Experiments on several benchmarks show that our method gives the best reported results, having large advantages in few-shot and zero-shot settings. © 2021 Association for Computational Linguistics

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Enabling Smart Cities with Cognition Based Intelligent Route Decision in Vehicles Empowered with Deep Extreme Learning Machine

引用

computers, Materials & Continua 2021年第1期66卷 141-156页

作者： Dildar Hussain Muhammad Adnan Khan Sagheer Abbas Rizwan Ali Naqvi Muhammad Faheem Mushtaq Abdur Rehman Afrozah Nadeem School of Computational Sciences Korea Institute for Advanced StudySeoul02455Korea Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan School of Computer Science National College of Business Administration&EconomicsLahore54000Pakistan Department of Unmanned Vehicle Engineering Sejong UniversitySeoul05006Korea Department of Information Technology Khwaja Fareed University of Engineering and Information TechnologyRahim Yar Khan64200Pakistan

The fast-paced growth of artificial intelligence provides unparalleled opportunities to improve the efficiency of various industries,including the transportation *** worldwide transport departments face many obstacles following the implementation and integration of different vehicle *** of these tasks is to ensure that vehicles are autonomous,intelligent and able to grow their repository of *** learning has recently been implemented in wireless networks,as a major artificial intelligence branch,to solve historically challenging problems through a data-driven *** this article,we discuss recent progress of applying machine learning into vehicle networks for intelligent route decision and try to focus on this emerging *** Extreme Learning Machine(DELM)framework is introduced in this article to be incorporated in vehicles so they can take human-like *** present GPS compatibility issues make it difficult for vehicles to take real-time decisions under certain *** leads to the concept of vehicle controller making *** proposed DELM based system for self-intelligent vehicle decision makes use of the cognitive memory to store route *** overcomes inadequacy of the current in-vehicle route-finding technology and its *** the relevant route-related information for the ride will be provided to the user based on its *** the DELM method,a high degree of precision in smart decision taking with a minimal error rate is *** investigation,it has been observed that proposed framework has the highest accuracy rate with 70%of training(1435 samples)and 30%of validation(612 samples).Simulation results validate the intelligent prediction of the proposed method with 98.88%,98.2%accuracy during training and validation respectively.

关键词： DELM ANN IoT feedforward route decision prediction smart city

来源：评论

学校读者我要写书评

暂无评论

Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection

arXiv

引用

arXiv 2022年

作者： Xu, Dongli Deng, Jinhong Li, Wen School of Computer Science and Engineering Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China

Average precision (AP) loss has recently shown promising performance on the dense object detection task. However, a deep understanding of how AP loss affects the detector from a pairwise ranking perspective has not yet been developed. In this work, we revisit the average precision (AP) loss and reveal that the crucial element is that of selecting the ranking pairs between positive and negative samples. Based on this observation, we propose two strategies to improve the AP loss. The first of these is a novel Adaptive Pairwise Error (APE) loss that focusing on ranking pairs in both positive and negative samples. Moreover, we select more accurate ranking pairs by exploiting the normalized ranking scores and localization scores with a clustering algorithm. Experiments conducted on the MS-COCO dataset support our analysis and demonstrate the superiority of our proposed method compared with current classification and ranking loss. The code is available at https://***/Xudangliatiger/APE-Loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation

arXiv

引用

arXiv 2022年

作者： Liu, Yahao Deng, Jinhong Tao, Jiale Chu, Tong Duan, Lixin Li, Wen School of Computer Science and Engineering Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China

Existing works typically treat cross-domain semantic segmentation (CDSS) as a data distribution mismatch problem and focus on aligning the marginal distribution or conditional distribution. However, the label shift issue is unfortunately overlooked, which actually commonly exists in the CDSS task, and often causes a classifier bias in the learnt model. In this paper, we give an in-depth analysis and show that the damage of label shift can be overcome by aligning the data conditional distribution and correcting the posterior probability. To this end, we propose a novel approach to undo the damage of the label shift problem in CDSS. In implementation, we adopt class-level feature alignment for conditional distribution alignment, as well as two simple yet effective methods to rectify the classifier bias from source to target by remolding the classifier predictions. We conduct extensive experiments on the benchmark datasets of urban scenes, including GTA5 to Cityscapes and SYNTHIA to Cityscapes, where our proposed approach outperforms previous methods by a large margin. For instance, our model equipped with a self-training strategy reaches 59.3% mIoU on GTA5 to Cityscapes, pushing to a new state-of-the-art. The code will be available at https://***/manmanjun/Undoing UDA. Copyright © 2022, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Learning Group-Disentangled Representation for Interpretable Thoracic Pathologic Prediction

Learning Group-Disentangled Representation for Interpretable...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Li, Hao Wu, Yirui Hu, Hexuan Lu, Hu Lai, Yong Wan, Shaohua Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources China College of Computer and Information Hohai University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China School of Computer Science and Communication Engineering Jiangsu University China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China

ISBN: (纸本)9781665468190

Deep learning methods have shown significant performance in medical image analysis tasks. However, they generally act like 'black box' without explanations in both feature extraction and decision processes, leading to lack of clinical insights and high risk assessments. To aid deep learning in envisioning diseases with visual clues, we propose Representation Group-Disentangling Network (RGD-Net), which can completely disentangle feature space of input X-ray images into several independent feature groups, each corresponding to a specific disease. Taking several semantically related and labeled X-ray images as input, RGD-Net firstly extracts completely group-disentangled representations of diseases through Group-Disentangle Module, which applies group-swap and linking operations to construct latent space by enforcing semantic consistency of attributes. To prevent learning degenerate representations defined as shortcut problem, we further introduce adversarial constricts on mapping from features to diseases, thus avoiding model collapse with former free-form disentanglement. Experiments on chestxray-14 and ChestXpert datasets demonstrate that RGD-Net are effective in predicting diseases with remarkable advantages, which leverage potential factors contributing to different diseases, thus enhancing interpretability in working patterns of deep learning methods. © 2022 IEEE.

关键词： Forecasting

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：