检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Hongyu Long Xiao Yin Chao Liu Yuansen Xu Tian Tian Fan Ye Key Laboratory of Big Data Intelligent Computing School of Automation/School of Industrial Internet Chongqing University of Posts and Telecommunications Chongqing China School of Automation/School of Industrial Internet Chongqing University of Posts and Telecommunications Chongqing China Economic and Technical Research Institute of State Grid Chongqing Electric Power Company Chongqing China

In response to the unique topographical challenges posed by mountainous environments, this paper investigates a probabilistic model of electric vehicle charging load, taking into account the unique traffic behavior and regional characteristics of mountainous cities. Regarding the traffic behavior, first, a traffic road network model for mountainous cities is proposed. Next, the travel chain theory is combined with the road chain to consider the functional partition of the city, which can better describe the travel patterns and charging behavior of users. Based on the analysis of traffic behavior, by exploring the influences of ambient temperature, road grade, and the undulating nature of mountainous roads, an improved Floyd shortest path algorithm is used for path decision-making, leading to the development of an EV power consumption model specifically tailored for mountainous cities. Based on this model, the prediction of EV load in mountainous cities is subsequently conducted. Overall, this study proposes a more realistic EV load prediction model by integrating traffic behavior, regional characteristics and user travel patterns, and the simulation results demonstrate the adaptability as well as the effectiveness of the method for application in mountainous cities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Realizing Emotional Interactions to Learn User Experience and Guide Energy Optimization for Mobile Architectures 22

Realizing Emotional Interactions to Learn User Experience an...

引用

Proceedings of the 55th Annual IEEE/ACM International Symposium on Microarchitecture

作者： Xueliang Li Zhuobin Shi Junyang Chen Yepang Liu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation and Department of Computer Science and Engineering Southern University of Science and Technology China

ISBN: (纸本)9781665462723

In the age of AI, mobile architectures such as smartphones are still "cold machines"; machines do not feel. If the architecture is able to feel users' feelings and runtime user experience (UX), it will accordingly adapt performance/energy to find the optimal system-operating state that consumes the least energy to satisfy users. In this paper, we will utilize users' facial expressions (FEs) to learn their runtime UX. We know that FEs are the natural and direct way for humans to convey their emotions and feelings. Our study reveals that FEs also reflect UX. Our research for the first time quantifies the link between FEs and UX. Leveraging this link, the architecture will be able to use the front camera to see FEs and feel users' UX. Based on UX, the architecture can appropriately provision computing resources. We propose Vi-energy system to realize the above idea. Our evaluation shows that Vi-energy reduces energy consumption by 52.9% at maximum and secures UX.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zero Stability Well Predicts Performance of Convolutional Neural Networks

arXiv

引用

arXiv 2022年

作者： Chen, Liangming Jin, Long Shang, Mingsheng Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences China Chongqing School University of Chinese Academy of Sciences China School of Information Science and Engineering Lanzhou University China

The question of what kind of convolutional neural network (CNN) structure performs well is fascinating. In this work, we move toward the answer with one more step by connecting zero stability and model performance. Specifically, we found that if a discrete solver of an ordinary differential equation is zero stable, the CNN corresponding to that solver performs well. We first give the interpretation of zero stability in the context of deep learning and then investigate the performance of existing first- and second-order CNNs under different zero-stable circumstances. Based on the preliminary observation, we provide a higher-order discretization to construct CNNs and then propose a zero-stable network (ZeroSNet). To guarantee zero stability of the ZeroSNet, we first deduce a structure that meets consistency conditions and then give a zero stable region of a training-free parameter. By analyzing the roots of a characteristic equation, we theoretically obtain the optimal coefficients of feature maps. Empirically, we present our results from three aspects: We provide extensive empirical evidence of different depth on different datasets to show that the moduli of the characteristic equation's roots are the keys for the performance of CNNs that require historical features;Our experiments show that ZeroSNet outperforms existing CNNs which is based on high-order discretization;ZeroSNets show better robustness against noises on the input. The source code is available at https://***/LongJin-lab/ZeroSNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-View Mutual Learning Network for Multimodal Fake News Detection

SSRN

引用

SSRN 2023年

作者： Cui, Wei Zhang, Xuerui Shang, Mingsheng College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China School of Electronic Information and Communication Engineering Chongqing Aerospace Polytechnic Chongqing400021 China

Multimodal fake news is more deceptive than unimodal content and often has adverse social and economic impacts. However, most existing methods learn modal features from a single perspective, without considering simultaneously learning and sharing knowledge across modalities from different perspectives. Our work presents a novel Multi-View Mutual Learning (MVML) network for multimodal fake news detection, which explores the semantic relationship between words and scenes, as well as words and objects, and investigates the semantic connection that exists between global concepts and local objects from multiple perspectives. We first construct text-scenes and text-objects graphs respectively, and perform intra-graph inference to obtain multi-view features. Then, the multi-view fusion layer based on the cross-view attention mechanism interactively models the cross-view dependencies between the image and text. The extracted features before feeding into the final classifier are further processed via a feed-forward attention module, which adaptively reweights and aggregates the features for redundancy reduction. In addition, to exploit the respective advantages of two multi-view classifiers, we propose a mutual learning mechanism that allows them to perform knowledge distillation and align the learning targets. The proposed MVML is thoroughly assessed on four publicly available benchmark datasets, and the findings demonstrate that it outperforms the existing standard approaches. © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Deconfound Semantic Shift and Incompleteness in Incremental Few-shot Semantic Segmentation 39

Deconfound Semantic Shift and Incompleteness in Incremental ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wu, Yirui Xia, Yuhang Li, Hao Yuan, Lixin Chen, Junyang Liu, Jun Lu, Tong Wan, Shaohua Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computing and Communication Lancaster University Lancaster United Kingdom National Key Lab for Novel Software Technology Nanjing University Nanjing China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China

ISBN: (纸本)157735897X

Incremental few-shot semantic segmentation (IFSS) expands segmentation capacity of the trained model to segment new-class images with few samples. However, semantic meanings may shift from background to object class or vice versa during incremental learning. Moreover, new-class samples often lack representative attribute features when the new class greatly differs from the pre-learned old class. In this paper, we propose a causal framework to discuss the cause of semantic shift and incompleteness in IFSS, and we deconfound the revealed causal effects from two aspects. First, we propose a Causal Intervention Module (CIM) to resist semantic shift. CIM progressively and adaptively updates prototypes of old class, and removes the confounder in an intervention manner. Second, a Prototype Refinement Module (PRM) is proposed to complete the missing semantics. In PRM, knowledge gained from the episode learning scheme assists in fusing features of new-class and old-class prototypes. Experiments on both PASCAL-VOC 2012 and ADE20k benchmarks demonstrate the outstanding performance of our method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards open-world text-guided face image generation and manipulation

arXiv

引用

arXiv 2021年

作者： Xia, Weihao Yang, Yujiu Xue, Jing-Hao Wu, Baoyuan Tsinghua Shenzhen International Graduate School Tsinghua University China Department of Statistical Science University College London United Kingdom School of Data Science Chinese University of Hongkong Shenzhen China and Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data Shenzhen China

—The existing text-guided image synthesis methods can only produce limited quality results with at most 2562 resolution and the textual instructions are constrained in a small Corpus. In this work, we propose a unified framework for both face image generation and manipulation that produces diverse and high-quality images with an unprecedented resolution at 10242 from multimodal inputs. More importantly, our method supports open-world scenarios, including both image and text, without any re-training, fine-tuning, or post-processing. To be specific, we propose a brand new paradigm of text-guided image generation and manipulation based on the superior characteristics of a pretrained GAN model. Our proposed paradigm includes two novel strategies. The first strategy is to train a text encoder to obtain latent codes that align with the hierarchically semantic of the aforementioned pretrained GAN model. The second strategy is to directly optimize the latent codes in the latent space of the pretrained GAN model with guidance from a pretrained language model. The latent codes can be randomly sampled from a prior distribution or inverted from a given image, which provides inherent supports for both image generation and manipulation from multi-modal inputs, such as sketches or semantic labels, with textual guidance. To facilitate text-guided multi-modal synthesis, we propose the MULTI-MODAL CELEBA-HQ, a large-scale dataset consisting of real face images and corresponding semantic segmentation map, sketch, and textual descriptions. Extensive experiments on the introduced dataset demonstrate the superior performance of our proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Contrastive Learning for Gastroenteroscopy Classification

Multi-scale Contrastive Learning for Gastroenteroscopy Class...

引用

Annual IEEE Symposium on Computer-Based Medical Systems

作者： Dan Li Xuechen Li Zhibin Peng Wenting Chen Linlin Shen Guangyao Wu Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology ShenZhen University Shenzhen China City University of Hong Kong Hong Kong SAR China Shenzhen Institute of Artificial Intelligence & Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University General Hospital

In gastroenteroscopy image analysis, numerous CADs demonstrate that deep learning aids doctors' diagnosis. The shapes and sizes of the lesions are varied. And in the clinic, the dataset appears to be data imbalanced. However, existing methods directly classify by texture and ignore lesions with various shapes and sizes. To address the issue above, we propose a deep neural network, which consists of multi-scale feature extraction, contrastive feature learning and a multi-scale feature fusion module. We train the contrastive feature learning module and multi-scale feature fusion module simultaneously to alleviate the issue of data distribution differences. Thus, the proposed network can better identify various categories. Extensive experiments on the Hyper Kvasir dataset show that the proposed Hybrid-M2CL outperforms the benchmark proposed by the dataset with 5.0% Macro Precision, 3.3% Macro Recall, 3.4% Macro F1-score, 3.3% Micro Precision, 3.6% MCC. In addition, it outperforms the SOTA by 1.1% Macro F1-score, 2.6% MCC, and 2.0% B-ACC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bandwidth Utilization Analysis for TVET Education on Metro-E Campus Network

Bandwidth Utilization Analysis for TVET Education on Metro-E...

引用

Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), International Conference on

作者： Nor Paezah Abdullah Murizah Kassim Sayang Mohd Deni School of Electrical Engineering College of Engineering Universiti Teknologi MARA Shah Alam Selangor Malaysia Institut Kemahiran Tinggi PERDA (PERDA-TECH) Nibong Tebal Pulau Pinang Malaysia Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Shah Alam Selangor Malaysia College of Computing Informatics and Media Studies Universiti Teknologi MARA Shah Alam Selangor Malaysia

ISBN: (数字)9798350391183

ISBN: (纸本)9798350391190

This paper presents a bandwidth utilization analysis and internet application usage for Technical and Vocational Education and Training (TVET) education on the Metro-E campus network. Despite upgrading high-speed Internet from 50Mbps to 150Mbps, the campus is still experiencing internet link congestion, affecting the Quality of Services (QoS). Campus QoS was analyzed, and data was collected over three months on a campus Metro-E network at the primary Internet gateway. The results show the bandwidth consumption for the Integrated Performance Modeling Environment (IPME). Inbound network capacity usage peaks at 100 % and then drops to 30% of available capacity, demonstrating that the network experiences both high and low demand times. However, Unifi broadband shows that inbound data usage ranges from 72% to 100%. The high demand for inbound Unifi traffic could suggest a critical service or a strong reliance on Unifi for inbound communication. PERDA-TECH students use most of the total 22014300.81MB of inbound data from online applications. They use these internet apps for E-learning and online simulation, YouTube, TikTok, and Facebook for multimedia and creative learning, and FTP applications for transferring files across websites or enhancing information. This research is significant in deploying QoS bandwidth management, policing, and shaping future QoS for TVET education on the Metro-E campus network.

关键词： Wide area networks Training Video on demand Social networking (online) Bandwidth Quality of service User experience Internet Web sites Security

来源：评论

学校读者我要写书评

暂无评论

Differentiable top-k with optimal transport 34

Differentiable top-k with optimal transport

引用

34th Conference on Neural Information Processing Systems, NeurIPS 2020

作者： Xie, Yujia Dai, Hanjun Chen, Minshuo Dai, Bo Zhao, Tuo Zha, Hongyuan Wei, Wei Pfister, Tomas College of Computing Georgia Tech United States Google Brain College of Engineering Georgia Tech United States School of Data Science Shenzhen Research Institute of Big Data CUHK Shenzhen China Google Cloud AI

The top-k operation, i.e., finding the k largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining. However, if the top-k operation is implemented in an algorithmic way, e.g., using bubble algorithm, the resulting model cannot be trained in an end-to-end way using prevalent gradient descent algorithms. This is because these implementations typically involve swapping indices, whose gradient cannot be computed. Moreover, the corresponding mapping from the input scores to the indicator vector of whether this element belongs to the top-k set is essentially discontinuous. To address the issue, we propose a smoothed approximation, namely the SOFT (Scalable Optimal transport-based diFferenTiable) top-k operator. Specifically, our SOFT top-k operator approximates the output of the top-k operation as the solution of an Entropic Optimal Transport (EOT) problem. The gradient of the SOFT operator can then be efficiently approximated based on the optimality conditions of EOT problem. We apply the proposed operator to the k-nearest neighbors and beam search algorithms, and demonstrate improved performance. © 2020 Neural information processing systems foundation. All rights reserved.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection

arXiv

引用

arXiv 2024年

作者： Liang, Hanzhe Xie, Guoyang Hou, Chengbin Wang, Bingshu Gao, Can Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Audencia Financial Technology Institute Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Intelligent Manufacturing CATL Ningde China School of Computing and Artificial Intelligence Fuyao University of Science and Technology Fuzhou China School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

3D anomaly detection has recently become a significant focus in computer vision. Several advanced methods have achieved satisfying anomaly detection performance. However, they typically concentrate on the external structure of 3D samples and struggle to leverage the internal information embedded within samples. Inspired by the basic intuition of why not look inside for more, we introduce a straightforward method named Internal Spatial Modality Perception (ISMP) to explore the feature representation from internal views fully. Specifically, our proposed ISMP consists of a critical perception module, Spatial Insight Engine (SIE), which abstracts complex internal information of point clouds into essential global features. Besides, to better align structural information with point data, we propose an enhanced key point feature extraction module for amplifying spatial structure feature representation. Simultaneously, a novel feature filtering module is incorporated to reduce noise and redundant features for further aligning precise spatial structure. Extensive experiments validate the effectiveness of our proposed method, achieving object-level and pixel-level AUROC improvements of 4.2% and 13.1%, respectively, on the Real3D-AD benchmarks. Note that the strong generalization ability of SIE has been theoretically proven and is verified in both classification and segmentation tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

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：