检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jianping Jiang Xinyu Zhou Bingxuan Wang Xiaoming Deng Chao Xu Boxin Shi National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University AI Innovation Center School of Computer Science Peking University National Key Lab of General AI School of Intelligence Science and Technology Peking University Chinese Academy of Sciences Institute of Software University of Chinese Academy of Sciences

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Reliable hand mesh reconstruction (HMR) from commonly-used color and depth sensors is challenging es-pecially under scenarios with varied illuminations and fast motions. Event camera is a highly promising alternative for its high dynamic range and dense temporal resolution properties, but it lacks salient texture appearance for hand mesh reconstruction. In this paper, we propose EvRGBHand - the first approach for 3D hand mesh reconstruction with an event camera and an RGB camera compensating for each other. By fusing two modalities of data across time, space, and information dimensions, EvRGBHand can tackle overexposure and motion blur issues in RGB-based HMR and foreground scarcity as well as background overflow issues in event-based HMR. We further propose EvRGBDegrader, which allows our model to generalize effectively in challenging scenes, even when trained solely on standard scenes, thus reducing data acquisition costs. Experiments on real-world data demonstrate that EvRGBHand can effectively solve the challenging issues when using either type of camera alone via retaining the merits of both, and shows the potential of generalization to outdoor scenes and another type of event camera. For code, models, and dataset, please refer to https://***/.***/.

关键词： Costs Three-dimensional displays Image color analysis Cameras Sensors Pattern recognition Reliability

来源：评论

学校读者我要写书评

暂无评论

Deep Spiking Neural Networks with High Representation Similarity Model Visual Pathways of Macaque and Mouse

arXiv

引用

arXiv 2023年

作者： Huang, Liwei Ma, Zhengyu Yu, Liutao Zhou, Huihui Tian, Yonghong National Engineering Research Center of Visual Technology School of Computer Science Peking University China Department of Networked Intelligence Peng Cheng Laboratory China

Deep artificial neural networks (ANNs) play a major role in modeling the visual pathways of primate and rodent. However, they highly simplify the computational properties of neurons compared to their biological counterparts. Instead, Spiking Neural Networks (SNNs) are more biologically plausible models since spiking neurons encode information with time sequences of spikes, just like biological neurons do. However, there is a lack of studies on visual pathways with deep SNNs models. In this study, we model the visual cortex with deep SNNs for the first time, and also with a wide range of state-of-the-art deep CNNs and ViTs for comparison. Using three similarity metrics, we conduct neural representation similarity experiments on three neural datasets collected from two species under three types of stimuli. Based on extensive similarity analyses, we further investigate the functional hierarchy and mechanisms across species. Almost all similarity scores of SNNs are higher than their counterparts of CNNs with an average of 6.6%. Depths of the layers with the highest similarity scores exhibit little differences across mouse cortical regions, but vary significantly across macaque regions, suggesting that the visual processing structure of mice is more regionally homogeneous than that of macaques. Besides, the multi-branch structures observed in some top mouse brain-like neural networks provide computational evidence of parallel processing streams in mice, and the different performance in fitting macaque neural representations under different stimuli exhibits the functional specialization of information processing in macaques. Taken together, our study demonstrates that SNNs could serve as promising candidates to better model and explain the functional hierarchy and mechanisms of the visual system. Copyright © 2023, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

MDG:Multilingual Co-speech Gesture Generation with Low-level Audio Representation and Diffusion Models

MDG:Multilingual Co-speech Gesture Generation with Low-level...

引用

International Conference on Asian Language Processing (IALP)

作者： Jie Yang Feilong Bao Inner Mongolia University Hohhot China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology College of Computer Science

ISBN: (数字)9798331540852

ISBN: (纸本)9798331540869

Co-speech gesture generation is crucial for enhancing human-computer interaction. Most existing research focuses on English, overlooking multilingual speech and the ability to generalize across languages. Additionally, these studies often rely on pre-trained audio feature extraction models, insufficient for non-English languages. To address these issues, we introduce MDG, a novel diffusion model-based method for speech-driven gesture generation using a multilingual dataset. Our approach incorporates Language ID to distinguish between languages and utilizes low-level audio features to improve multilingual generalization. Extensive experiments demonstrate that MDG significantly outperforms baseline models in multilingual co-speech gesture generation. For more details, please visit our demo page 1 .

关键词： Training Human computer interaction Feature extraction Diffusion models Data models Data mining Speech processing

来源：评论

学校读者我要写书评

暂无评论

EMGCN: Enhancement Graph and Multi-head Attention Graph Convolutional Networks for Aspect-based Sentiment Analysis

EMGCN: Enhancement Graph and Multi-head Attention Graph Conv...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Jinhang Chen Rong Yan Inner Mongolia Key Laboratory of Mongolian Information Processing Technology National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian College of Computer Science Inner Mongolia University Hohhot China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Aspect-based Sentiment Analysis (ABSA) task aims to predict the sentiment polarity of specific aspects within sentences, uncovering multiple sentiment-object pairs contained in review sentences. Graph neural networks based on dependency trees are popular for addressing ABSA with high effectiveness and practicality. However, how to better utilize the syntactic structure and semantics within dependency trees still remains big challenge. For this purpose, in this paper, we explore to enhance the ability of capture both syntactic dependencies and semantic information by using semantic-enhanced graphs, and propose a novel model named EMGCN (Enhancement Graph and Multi-head Attention Graph Convolutional Networks) model. Additionally, we further focus on enhancing the context awareness by capturing semantic dependencies through the multi-head self-attention mechanism. Experimental validation on five datasets demonstrate the effectiveness of our proposed model.

关键词： Sentiment analysis Attention mechanisms Graph convolutional networks Reviews Federated learning Semantics Context awareness

来源：评论

学校读者我要写书评

暂无评论

Polarization Reconfigurable Intelligent Metasurface for X- & Ku-band Applications in Communications

Polarization Reconfigurable Intelligent Metasurface for X- &...

引用

Microwave and Antenna Symposium (IMAS), International

作者： Muhammad Sumaid Ahsaan Gul Hassan Nosherwan Shoaib Symeon Nikolaou School of Electrical Engineering and Computer Science (SEECS) National University of Sciences and Technology (NUST) Islamabad Pakistan Department of Electrical Computer Engineering and Informatics Frederick Research Center (FRC) Frederick University Nicosia Cyprus

This article presents a polarization reconfigurable intelligent metasurface (PRIM) to realize on demand switchable cross polarization conversion and circular polarization conversion by linearly incident electromagnetic (EM) wave through globally tuned PIN diode models. The unit cell structure of PRIM consists of I-Shaped structure supported with split circle and biasing lines to control the states of voltage-controlled PIN diodes. The modeled PIN diodes are incorporated in between split circle and on the edges of unit cells. The ON/OFF states of these PIN diodes can switch the polarization state of a wave between linear and circular polarizations. The novel approach ensures the provision of electronically controlled, ultra-wide band (UWB) reflective circular-polarization in one state and cross-polarization in the other, over same functional frequency band of X- and Ku-band. The results demonstrate that in open/off state the metasurface presents cross polarization ranging from 9 GHz to 19 GHz, while in short/on state metasurface presents circular polarization ranging from 10 GHz to 22 GHz. The designed metasurface is fabricated using hardwire-bond technique to replicate functionality of diodes and tested to validate the performance of PRIM.

关键词： Microwave antennas Polarization PIN photodiodes Switches Metasurfaces Stability analysis Distance measurement

来源：评论

学校读者我要写书评

暂无评论

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need

arXiv

引用

arXiv 2024年

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expediting Distributed GNN Training with Feature-only Partition and Optimized Communication Planning

Expediting Distributed GNN Training with Feature-only Partit...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Bingqian Du Jun Liu Ziyue Luo Chuan Wu Qiankun Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Electrical and Computer Engineering The Ohio State University USA Department of Computer Science The University of Hong Kong Hong Kong School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Feature-only partition of large graph data in distributed Graph Neural Network (GNN) training offers advantages over commonly adopted graph structure partition, such as minimal graph preprocessing cost and elimination of cross-worker subgraph sampling burdens. Nonetheless, performance bottleneck of GNN training with feature-only partitions still largely lies in the substantial communication overhead due to cross-worker feature fetching. To reduce the communication overhead and expedite distributed training, we first investigate and answer two key questions on convergence behaviors of GNN model in feature-partition based distribute GNN training: 1) As no worker holds a complete copy of each feature, can gradient exchange among workers compensate for the information loss due to incomplete local features? 2) If the answer to the first question is negative, is feature fetching in every training iteration of the GNN model necessary to ensure model convergence? Based on our theoretical findings on these questions, we derive an optimal communication plan that decides the frequency for feature fetching during the training process, taking into account bandwidth levels among workers and striking a balance between model loss and training time. Extensive evaluation demonstrates consistent results with our theoretical analysis, and the effectiveness of our proposed design.

关键词： Training Time-frequency analysis Costs Computational modeling Distributed databases Bandwidth Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

3D Facial Expressions through Analysis-by-Neural-Synthesis

3D Facial Expressions through Analysis-by-Neural-Synthesis

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： George Retsinas Panagiotis P. Filntisis Radek Daněček Victoria F. Abrevaya Anastasios Roussos Timo Bolkarr Petros Maragos Institute of Robotics Athena Research Center Maroussi Greece MPI for Intelligent Systems Tübingen Germany Institute of Computer Science (ICS) Foundation for Research & Technology - Hellas (FORTH) Greece School of Electrical & Computer Engineering National Technical University of Athens Greece

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

While existing methods for 3D face reconstruction from in-the-wild images excel at recovering the overall face shape, they commonly miss subtle, extreme, asymmetric, or rarely observed expressions. We improve upon these meth-ods with SMIRK (Spatial Modeling for Image-based Reconstruction of Kinesics), which faithfully reconstructs expres-sive 3D faces from images. We identify two key limitations in existing methods: shortcomings in their self-supervised training formulation, and a lack of expression diversity in the training images. For training, most methods employ differentiable rendering to compare a predicted face mesh with the input image, along with a plethora of additional loss functions. This differentiable rendering loss not only has to provide supervision to optimize for 3D face geom-etry, camera, albedo, and lighting, which is an ill-posed optimization problem, but the domain gap between ren-dering and input image further hinders the learning pro-cess. Instead, SMIRK replaces the differentiable rendering with a neural rendering module that, given the ren-dered predicted mesh geometry, and sparsely sampled pix-els of the input image, generates a face image. As the neural rendering gets color information from sampled im-age pixels, supervising with neural rendering-based reconstruction loss can focus solely on the geometry. Further it enables us to generate images of the input identity with varying expressions while training. These are then utilized as input to the reconstruction model and used as supervision with ground truth geometry. This effectively augments the training data and enhances the generalization for di-verse expressions. Our qualitative, quantitative and partic-ularly our perceptual evaluations demonstrate that SMIRK achieves the new state-of-the art performance on accurate expression reconstruction. For our method's source code, demo video and more, please visit our project webpage: https://***/smirk/.

关键词： Training Geometry Solid modeling Three-dimensional displays Accuracy Face recognition Training data

来源：评论

学校读者我要写书评

暂无评论

HealthEdge: A Machine Learning-Based Smart Healthcare Framework for Prediction of Type 2 Diabetes in an Integrated IoT, Edge, and Cloud Computing System 14

HealthEdge: A Machine Learning-Based Smart Healthcare Framew...

引用

14th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2023 and The 6th International Conference on Emerging Data and Industry 4.0, EDI40 2023

作者： Hennebelle, Alain Materwala, Huned Ismail, Leila Melbourne Australia Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center United Arab Emirates University United Arab Emirates Lab School of Computing and Information Systems The University of Melbourne Australia

Diabetes Mellitus has no permanent cure to date and is one of the leading causes of death globally. The alarming increase in diabetes calls for the need to take precautionary measures to avoid/predict the occurrence of diabetes. This paper proposes HealthEdge, a machine learning-based smart healthcare framework for type 2 diabetes prediction in an integrated IoT-edge-cloud computing system. Numerical experiments and comparative analysis were carried out between the two most used machine learning algorithms in the literature, Random Forest (RF) and Logistic Regression (LR), using two real-life diabetes datasets. The results show that RF predicts diabetes with 6% more accuracy on average compared to LR. © 2023 Elsevier B.V.. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

StreamFP: Learnable Fingerprint-guided Data Selection for Efficient Stream Learning

arXiv

引用

arXiv 2024年

作者： Shi, Tongjun Zhang, Shuhao Chen, Binbin He, Bingsheng National Engineering Research Center for Big DataTechnology and System Services Computing Technology and System Lab Cluster Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Singapore University of Technology and Design Singapore National University of Singapore Singapore

Stream Learning (SL) requires models that can quickly adapt to continuously evolving data, posing significant challenges in both computational efficiency and learning accuracy. Effective data selection is critical in SL to ensure a balance between information retention and training efficiency. Traditional rule-based data selection methods struggle to accommodate the dynamic nature of streaming data, highlighting the necessity for innovative solutions that effectively address these challenges. Recent approaches to handling changing data distributions face challenges that limit their effectiveness in fast-paced environments. In response, we propose StreamFP, a novel approach that uniquely employs dynamic, learnable parameters called fingerprints to enhance data selection efficiency and adaptability in stream learning. StreamFP optimizes coreset selection through its unique fingerprint-guided mechanism for efficient training while ensuring robust buffer updates that adaptively respond to data dynamics, setting it apart from existing methods in stream learning. Experimental results demonstrate that StreamFP outperforms state-of-the-art methods by achieving accuracy improvements of 15.99%, 29.65%, and 51.24% compared to baseline models across varying data arrival rates, alongside a training throughput increase of 4.6x. © 2024, CC BY.

关键词： Data accuracy

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：