检索结果-内蒙古大学图书馆

DPA-2:a large atomic model as a multitask learner

npj Computational Materials 2024年第1期10卷 185-199页

作者： Duo Zhang Xinzijian Liu Xiangyu Zhang Chengqian Zhang Chun Cai Hangrui Bi Yiming Du Xuejian Qin Anyang Peng Jiameng Huang Bowen Li Yifan Shan Jinzhe Zeng Yuzhi Zhang Siyuan Liu Yifan Li Junhan Chang Xinyan Wang Shuo Zhou Jianchuan Liu Xiaoshan Luo Zhenyu Wang Wanrun Jiang Jing Wu Yudi Yang Jiyuan Yang Manyi Yang Fu-Qiang Gong Linshuang Zhang Mengchao Shi Fu-Zhi Dai Darrin M.York Shi Liu Tong Zhu Zhicheng Zhong Jian Lv Jun Cheng Weile Jia Mohan Chen Guolin Ke Weinan E Linfeng Zhang Han Wang AI for Science Institute BeijingP.R.China DP Technology BeijingP.R.China Academy for Advanced Interdisciplinary Studies Peking UniversityBeijingP.R.China State Key Lab of Processors Institute of Computing TechnologyChinese Academy of SciencesBeijingP.R.China University of Chinese Academy of Sciences BeijingP.R.China HEDPS CAPTCollege of EngineeringPeking UniversityBeijingP.R.China Ningbo Institute of Materials Technology and Engineering Chinese Academy of SciencesNingboP.R.China CAS Key Laboratory of Magnetic Materials and Devices and Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Chinese Academy of SciencesNingboP.R.China School of Electronics Engineering and Computer Science Peking UniversityBeijingP.R.China Shanghai Engineering Research Center of Molecular Therapeutics&New Drug Development School of Chemistry and Molecular EngineeringEast China Normal UniversityShanghaiP.R.China Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine and Department of Chemistry and Chemical BiologyRutgers UniversityPiscatawayNJUSA Department of Chemistry Princeton UniversityPrincetonNJUSA College of Chemistry and Molecular Engineering Peking UniversityBeijingP.R.China Yuanpei College Peking UniversityBeijingP.R.China School of Electrical Engineering and Electronic Information Xihua UniversityChengduP.R.China State Key Laboratory of Superhard Materials College of PhysicsJilin UniversityChangchunP.R.China Key Laboratory of Material Simulation Methods&Software of Ministry of Education College of PhysicsJilin UniversityChangchunP.R.China International Center of Future Science Jilin UniversityChangchunP.R.China Key Laboratory for Quantum Materialsof Zhejiang Province Department of PhysicsSchool of ScienceWestlake UniversityHangzhouP.R.China Atomistic Simulations Italian Institute of TechnologyGenovaItaly State Key Laboratory of Physical Chemistry of Solid Surface iChEMCollege of Chemistry and Chemical EngineeringXiame

The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and ***-driven potential energy models havedemonstrated the capability to conduct large-scale,long-duration simulations with the accuracy of ab initio electronic structure ***,the model generation process remains a bottleneck for large-scale *** propose a shift towards a model-centric ecosystem,wherein a large atomic model(LAM),pretrained across multiple disciplines,can be efficiently fine-tuned and distilled for various downstream tasks,thereby establishing a new framework for molecular *** this study,we introduce the DPA-2 architecture as a prototype for ***-trained on a diverse array of chemical and materials systemsusing a multi-task approach,DPA-2demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning *** approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

关键词： DPA establishing thereby

来源：评论

学校读者我要写书评

暂无评论

Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment

Efficient and Effective Weakly-Supervised Action Segmentatio...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Angchi Xu Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Weakly-supervised action segmentation is a task of learning to partition a long video into several action segments, where training videos are only accompanied by transcripts (ordered list of actions). Most of existing methods need to infer pseudo segmentation for training by serial alignment between all frames and the transcript, which is time-consuming and hard to be parallelized while training. In this work, we aim to escape from this inefficient alignment with massive but redundant frames, and instead to directly localize a few action transitions for pseudo segmentation generation, where a transition refers to the change from an action segment to its next adjacent one in the transcript. As the true transitions are submerged in noisy boundaries due to intra-segment visual variation, we propose a novel Action-Transition-Aware Boundary Alignment (ATBA) framework to efficiently and effectively filter out noisy boundaries and detect transitions. In addition, to boost the semantic learning in the case that noise is inevitably present in the pseudo segmentation, we also introduce video-level losses to utilize the trusted video-level supervision. Extensive experiments show the effectiveness of our approach on both performance and training speed. 1 1 Code is available at https://***/iSEE-laboratory/CVPR24_ATBA.

关键词： Training Visualization Computer vision Semantics Noise Robustness Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

NECA: Neural Customizable Human Avatar

NECA: Neural Customizable Human Avatar

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Junjin Xiao Qing Zhang Zhan Xu Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Adobe Research

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Human avatar has become a novel type of 3D asset with various applications. Ideally, a human avatar should be fully customizable to accommodate different settings and environments. In this work, we introduce NECA, an approach capable of learning versatile human representation from monocular or sparse-view videos, enabling granular customization across aspects such as pose, shadow, shape, lighting and texture. The core of our approach is to represent humans in complementary dual spaces and predict disentangled neural fields of geometry, albedo, shadow, as well as an external lighting, from which we are able to derive realistic rendering with high-frequency details via volumetric rendering. Extensive experiments demonstrate the advantage of our method over the state-of-the-art methods in photorealistic rendering, as well as various editing tasks such as novel pose synthesis and relighting. Our code is available at https://***/iSEE-laboratory/NECA.

关键词： Geometry Computer vision Three-dimensional displays Codes Shape Avatars Lighting

来源：评论

学校读者我要写书评

暂无评论

Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment

arXiv

引用

arXiv 2024年

作者： Xu, Angchi Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

Weakly-supervised action segmentation is a task of learning to partition a long video into several action segments, where training videos are only accompanied by transcripts (ordered list of actions). Most of existing methods need to infer pseudo segmentation for training by serial alignment between all frames and the transcript, which is time-consuming and hard to be parallelized while training. In this work, we aim to escape from this inefficient alignment with massive but redundant frames, and instead to directly localize a few action transitions for pseudo segmentation generation, where a transition refers to the change from an action segment to its next adjacent one in the transcript. As the true transitions are submerged in noisy boundaries due to intra-segment visual variation, we propose a novel Action-Transition-Aware Boundary Alignment (ATBA) framework to efficiently and effectively filter out noisy boundaries and detect transitions. In addition, to boost the semantic learning in the case that noise is inevitably present in the pseudo segmentation, we also introduce video-level losses to utilize the trusted video-level supervision. Extensive experiments show the effectiveness of our approach on both performance and training speed. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

A Survey of Internet of Things in Healthcare 29th

A Survey of Internet of Things in Healthcare

引用

29th International Conference on Computational and Experimental engineering and Sciences, ICCES 2023

作者： Chen, Shuwen Wang, Jiaji Song, Zhijun School of Physics and Information Engineering Jiangsu Second Normal University Nanjing211200 China School of Computing and Mathematical Sciences University of Leicester LeicesterLE1 7RH United Kingdom Jiangsu Province Engineering Research Center of Basic Education Big Data Application Nanjing211200 China State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China

ISBN: (纸本)9783031449468

With the rapid development of computers, Internet of Things (IoT) technology is becoming more and more closely integrated with the healthcare sector. This article introduces two major applications of IoT in healthcare: hospital information management and remote healthcare. In digitizing the healthcare industry, it is a great challenge to avoid the leakage of private medical data. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Memristive feature and mechanism induced by laser-doping in defect-free 2D semiconductor materials

引用

Journal of Semiconductors 2024年第7期45卷 85-91页

作者： Xiaoshan Du Shu Wang Qiaoxuan Zhang Shengyao Chen Fengyou Yang Zhenzhou Liu Zhengwei Fan Lijun Ma Lei Wang Lena Du Zhongchang Wang Cong Wang Bing Chen Qian Liu College of Electronic and Information Engineering Shandong University of Science and TechnologyQingdao 266590China National Center for Nanoscience and Technology&University of Chinese Academy of Sciences Beijing 100190China Hebei University of Water Resources and Electric Engineering Electrical Automation Department Cangzhou 061001China The MOE Key Laboratory of Weak-Light Nonlinear Photonics and International Sino-Slovenian Join Re-search Center on Liquid Crystal Pho-tonics TEDA Institute of Applied Physics and School of PhysicsNankai UniversityTianjin 300457China College of Mathematics and Physics Shandong Advanced Optoelectronic Materials and Technologies Engineering LaboratoryQingdao Uni-versity of Science and TechnologyQingdao 266061China Department of Physics Capital Normal UniversityBeijing 100048China Department of Advanced Materials and Computing International Iberian Nanotechnology Laboratory(INL)4715-330 BragaPortugal College of Mathematics and Physics Beijing University of Chemical TechnologyBeijing 100029China

Memristors as non-volatile memory devices have gained numerous attentions owing to their advantages in storage,in-memory computing, synaptic applications, etc. In recent years, two-dimensional(2D) materials with moderate defects have been discovered to exist memristive feature. However, it is very difficult to obtain moderate defect degree in 2D materials, and studied on modulation means and mechanism becomes urgent and essential. In this work, we realized memristive feature with a bipolar switching and a configurable on/off ratio in a two-terminal MoS_(2) device(on/off ratio ~100), for the first time, from absent to present using laser-modulation to few-layer defect-free MoS_(2)(about 10 layers), and its retention time in both high resistance state and low resistance state can reach 2×10^(4) s. The mechanism of the laser-induced memristive feature has been cleared by dynamic Monte Carlo simulations and first-principles calculations. Furthermore, we verified the universality of the laser-modulation by investigating other 2D materials of TMDs. Our work will open a route to modulate and optimize the performance of 2D semiconductor memristive devices.

关键词： 2D-material memristor laser doping laser direct writing memristive mechanism

来源：评论

学校读者我要写书评

暂无评论

Unusual thermal properties of graphene origami crease:A molecular dynamics study

引用

Green Energy & Environment 2022年第1期7卷 86-94页

作者： Ning Wei Yang Chen Kun Cai Yingyan Zhang Qingxiang Pei Jin-Cheng Zheng Yiu-Wing Mai Junhua Zhao Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment and Technology Jiangnan UniversityWuxi214122China Shanghai Institute of Applied Mathematics and Mechanics Shanghai Key Laboratory of Mechanics in Energy EngineeringShanghai UniversityShanghai200072China School of Engineering RMIT UniversityBundooraVIC3083Australia Institute of High Performance Computing A^(*)STAR138632Singapore Department of Physics and the Collaborative Innovation Center for Optoelectronic Semiconductors and Efficient Devices Xiamen UniversityXiamen361005China Xiamen University Malaysia 439000SepangSelangorMalaysia Centre for Advanced Materials Technology(CAMT) School of AerospaceMechanical and Mechatronic Engineering J07The University of SydneySydneyNSW2006Australia

Graphene is a two-dimensional material that can be folded into diverse and yet interesting nanostructures like macro-scale paper *** of graphene not only makes different morphological configurations but also modifies their mechanical and thermal *** by paper origami,herein we studied systemically the effects of creases,where sp^(2)to sp^(3)bond transformation occurs,on the thermal properties of graphene origami using molecular dynamics(MD)*** MD simulation results show that tensile strain reduces(not increases)the interfacial thermal resistance owing to the presence of the *** unusual phenomenon is explained by the micro-heat flux migration and stress *** findings on the graphene origami enable the design of the next-generation thermal management devices and flexible electronics with tuneable properties.

关键词： Graphene Origami Bond transformation Interfacial thermal resistance Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Confidence-guided Source Label Refinement and Class-aware Pseudo-Label Thresholding for Domain-Adaptive Semantic Segmentation

Confidence-guided Source Label Refinement and Class-aware Ps...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Hongwei Chu Meng Shen Jiawen Peng Andy J Ma School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Domain-Adaptive Semantic Segmentation (DASS) aims to transfer a segmentation model trained on a labeled source domain to an unlabeled target domain. Most existing methods overlook the errors in the source labels and directly utilize the erroneous source labels for training. This may result in wrong source domain knowledge being wrongly transferred to the target domain, which leads to similar classes cannot be separated well in the target domain. To this end, we propose a novel Confidence-guided Online REfinement (CORE) method, which introduces a refinement network trained on the target data to rectify erroneous source labels online. This can effectively avoid transferring erroneous knowledge from the source domain to the target domain. On the other hand, using the same threshold for all classes in the target domain may result in a severe class imbalance in self-training. Therefore, we propose Class-aware Adaptive Thresholding (CAT) to calculate different thresholds for different target classes, which adaptively filter target pixels with high confidence for better adaptation. Our proposed CORE-CAT method can be easily integrated with existing methods and achieves superior performance across various domain-adaptive semantic segmentation benchmarks.

关键词： Training Adaptation models Semantic segmentation Neural networks Adaptive filters Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

A Maximum Distance Separable Code Based RIS-OFDM: Design and Optimization

引用

IEEE Transactions on Wireless Communications 2025年

作者： Huang, Yiqian Yang, Ping Xiao, Yue Xiao, Ming Li, Shaoqian Xiang, Wei University of Electronic Science and Technology of China National Key Laboratory of Science and Technology on Communications Sichuan 611731 China department Sweden La Trobe University School of Computing Engineering and Mathematical Sciences MelbourneVIC3086 Australia

In this paper, we propose a novel orthogonal frequency division multiplexing (OFDM) waveform framework by capitalizing on the benefits of maximum distance separable (MDS) code and the reconfigurable intelligent surface (RIS). The proposed scheme is referred to as MDS-OFDM-RIS. The proposed design scheme consists of (i) an MDS code based amplitude and phase modulation scheme for OFDM transmission, which helps increase the minimum Hamming distance among symbols and improve on the error detection capabilities, (ii) a RIS that is placed near the radio frequency (RF) source, (iii) as well as a reduced-complexity maximum likelihood (RC-ML) detection algorithm at the receiver by utilizing the error detection ability of the MDS codes. We derive an upper bound for the bit error rate (BER) and a closed-form expression of the mutual information. Using the obtained analytical expressions, we formulate two optimization problems and derive the corresponding optimal solutions for RIS phase shifts. It is found that the two optimization problems share the same optimal solution, which indicates that the obtained RIS phase shifts optimize the system BER and channel capacity simultaneously. Simulation results show that compared with conventional OFDM systems, the proposed system can better combat multipath fading and provide higher channel capacity, especially when the RIS phase shifts are optimal. Moreover, the accuracy and low complexity of the proposed RC-ML detection scheme are demonstrated by numerical results. © 2002-2012 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

St-Tnet: An Spatio-Temporal Joint Transformer Network for Csi Feedback in Fdd-Mimo Systems

SSRN

引用

SSRN 2024年

作者： Wang, Linyu Cao, Yize Xiang, Jianhong Harbin Engineering University China College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Key Laboratory of Advanced Ship Communication and Information Technology Harbin Engineering University Harbin150001 China Agile and Intelligent Computing Key Laboratory Chengdu610000 China

In recent years, deep learning methods have been shown to have strong potential and superiority in reducing channel state information (CSI) feedback overhead and further improving feedback accuracy to maximize the performance benefits of massive MIMO in frequency division duplex (FDD) mode. As the CSI matrices are transformed into sequences for input to the Transformer model, the rearrangement leads to the loss of the original physical location relationships. Based on this problem, this paper proposes a transformer decoder based on spatio-temporal joint (ST-T). We employ a spatial attention mechanism to compensate for this information loss and focus on key spatial features more accurately, further exploiting the potential of single- and two-layer transformers in reconstructing CSI matrices. The results are validated by simulations based on DCRNet and CLNet encoders, which show that higher performance can be achieved with lower computational load compared to other lightweight models. © 2024, The Authors. All rights reserved.

关键词： Channel state information

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：