检索结果-内蒙古大学图书馆

20th International Conference on Optical Communications and Networks, ICOCN 2022

作者： Guo, Yuanzhi Xue, Xuwei Guo, Bingli Dang, Daohang Zhao, Yisong Ding, Rui Zhao, Jiapeng Zhang, Hangang Chen, Bin Li, Chenhui Huang, Shanguo Bupt State Key Laboratory of Information Photonics and Optical Communications Beijing China School of Computer Science and Information Engineering Hefei University of Technology Hefei China College of Information Science and Electronic Engineering Zhejiang University China Zhejiang Lab Hangzhou China

An arrayed waveguide grating router based all-optical switching network is proposed to accelerate the communication phase of distributed reinforcement learning training. Experimental investigations validate 465ns work... 详细信息

ISBN: (数字)9781665458986

ISBN: (纸本)9781665458986

关键词： Optical switches

来源：评论

学校读者我要写书评

暂无评论

Leveraging Predicate and Triplet Learning for Scene Graph Generation

arXiv

引用

arXiv 2024年

作者： Li, Jiankai Wang, Yunhong Guo, Xiefan Yang, Ruijie Li, Weixin IRIP Lab School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Complex & Critical Software Environment Beihang University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China

Scene Graph Generation (SGG) aims to identify entities and predict the relationship triplets in visual scenes. Given the prevalence of large visual variations of subject-object pairs even in the same predicate, it can be quite challenging to model and refine predicate representations directly across such pairs, which is however a common strategy adopted by most existing SGG methods. We observe that visual variations within the identical triplet are relatively small and certain relation cues are shared in the same type of triplet, which can potentially facilitate the relation learning in SGG. Moreover, for the long-tail problem widely studied in SGG task, it is also crucial to deal with the limited types and quantity of triplets in tail predicates. Accordingly, in this paper, we propose a Dual-granularity Relation Modeling (DRM) network to leverage fine-grained triplet cues besides the coarse-grained predicate ones. DRM utilizes contexts and semantics of predicate and triplet with Dual-granularity Constraints, generating compact and balanced representations from two perspectives to facilitate relation recognition. Furthermore, a Dual-granularity Knowledge Transfer (DKT) strategy is introduced to transfer variation from head predicates/triplets to tail ones, aiming to enrich the pattern diversity of tail classes to alleviate the long-tail problem. Extensive experiments demonstrate the effectiveness of our method, which establishes new state-of-the-art performance on Visual Genome, Open Image, and GQA datasets. Our code is available at https://***/jkli1998/DRM Copyright © 2024, 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

SCPS:A Secure and Copyright-Preserving System for IIoT Based on Hyperledger Fabric 9

SCPS:A Secure and Copyright-Preserving System for IIoT Based...

引用

9th International Conference on Advanced Cloud and Big Data, CBD 2021

作者： Peng, Jiahui Li, Chunpei Yuan, Bo Meng, Hongwei Yu, Feng Li, Xianxian Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining Security GuiLin China Beihang University Development Environment School of Computer Science and Engineering State Key Laboratory of Software Beijing100191 China Xiong'An Intelligent City Innovation Federation Blockchain Lab Beijing China

ISBN: (纸本)9781665407458

Data, a key asset in Industrial Internet of Things(IIoT), has fueled the emergence of a new data trading in-dustry, which can be collected and traded for better development of IIoT. However, copyright protection is not considered in traditional transactions, resulting in the loss of copyright control of the data after the data was sold. A large number of piracy activities will reduce the enthusiasm of data owners to collect data. The solution we proposed was to use blockchain and smart contract to achieve a decentralized and secure copyright protection scheme. The Trusted Execution Environment(TEE) helped our system realized the piracy tracking. To be specific, our solution effectively achieves a secure and copyright protection system of IIoT data, we realize the real simulation on Hyperledger Fabric shows the good performance of our system. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Leveraging Predicate and Triplet Learning for Scene Graph Generation

Leveraging Predicate and Triplet Learning for Scene Graph Ge...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jiankai Li Yunhong Wang Xiefan Guo Ruijie Yang Weixin Li IRIP Lab School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Complex & Critical Software Environment Beihang University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

关键词： Visualization Head Triples (Data structure) Semantics Genomics Tail Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

EEG-based Emotion Recognition in Immersive Virtual Reality: Meeting the Requirement of Accuracy and Computational Efficiency 23

EEG-based Emotion Recognition in Immersive Virtual Reality: ...

引用

7th International Conference on Digital Signal Processing, ICDSP 2023

作者： Pei, Guanxiong Fan, Cunhang Li, Taihao Jin, Jia Wang, Rui Research Institute of Artificial Intelligence Zhejiang Lab China School of Computer Science and Technology Anhui University China Laboratory of Applied Brain and Cognitive Sciences Shanghai International Studies University China School of Business and Management Shanghai International Studies University China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences China

ISBN: (纸本)9781450398626

Virtual reality technology provides a strong sense of immersion and interactivity. It is widely used in the fields of anxiety relief, fear therapy, and depression regulation. However, objectively evaluating the emotional intervention effect of virtual reality technology is a difficult problem. The main purpose of this paper is to explore the use of EEG signals to identify individual emotional states in virtual reality scenarios and to improve the computational efficiency and recognition accuracy of emotional valence. To induce the target emotional state of the participants, we established a relatively standard emotion-induced virtual reality video library. The EEG data of the participants were collected synchronously as they watched the virtual reality video. The results show that the emotion recognition performance of multiple features (energy spectrum, differential entropy, differential asymmetry, and rational asymmetry) is better than that of a single feature. The radial basis function neural network (RBFNN) performed better than the deep belief network (DBN). RBFNN achieves the highest average classification accuracy of 91.1%. By combining the feature selection (F-test) method with the RBFNN, an ideal classification performance can be maintained with computational efficiency improvements. Furthermore, it is demonstrated that the features extracted from the theta band outperform features extracted from other bands in emotional valence decoding. These results may contribute to the application of EEG-based affective computing technology in the field of psychological rehabilitation and assessment. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Interactive deep clustering via value mining 24

Interactive deep clustering via value mining

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Honglin Liu Peng Hu Changqing Zhang Yunfan Li Xi Peng College of Computer Science Sichuan University Chengdu China College of Intelligence and Computing Tianjin University Tianjin China and Tianjin Key Lab of Machine Learning Tianjin China College of Computer Science Sichuan University Chengdu China and State Key Laboratory of Hydraulics and Mountain River Engineering Sichuan University Chengdu China

ISBN: (纸本)9798331314385

In the absence of class priors, recent deep clustering methods resort to data augmentation and pseudo-labeling strategies to generate supervision signals. Though achieved remarkable success, existing works struggle to discriminate hard samples at cluster boundaries, mining which is particularly challenging due to their unreliable cluster assignments. To break such a performance bottleneck, we propose incorporating user interaction to facilitate clustering instead of exhaustively mining semantics from the data itself. To be exact, we present Interactive Deep Clustering (IDC), a plug-and-play method designed to boost the performance of pre-trained clustering models with minimal interaction overhead. More specifically, IDC first quantitatively evaluates sample values based on hardness, representativeness, and diversity, where the representativeness avoids selecting outliers and the diversity prevents the selected samples from collapsing into a small number of clusters. IDC then queries the cluster affiliations of high-value samples in a user-friendly manner. Finally, it utilizes the user feedback to finetune the pre-trained clustering model. Extensive experiments demonstrate that IDC could remarkably improve the performance of various pre-trained clustering models, at the expense of low user interaction costs. The code could be accessed at ***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grid4D: 4D Decomposed Hash Encoding for High-fidelity Dynamic Gaussian Splatting

arXiv

引用

arXiv 2024年

作者： Xu, Jiawei Fan, Zexin Yang, Jian Xie, Jin PCA Lab VCIP College of Computer Science Nankai University China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Intelligence Science and Technology Nanjing University Suzhou China

Recently, Gaussian splatting has received more and more attention in the field of static scene rendering. Due to the low computational overhead and inherent flexibility of explicit representations, plane-based explicit methods are popular ways to predict deformations for Gaussian-based dynamic scene rendering models. However, plane-based methods rely on the inappropriate low-rank assumption and excessively decompose the space-time 4D encoding, resulting in overmuch feature overlap and unsatisfactory rendering quality. To tackle these problems, we propose Grid4D, a dynamic scene rendering model based on Gaussian splatting and employing a novel explicit encoding method for the 4D input through the hash encoding. Different from plane-based explicit representations, we decompose the 4D encoding into one spatial and three temporal 3D hash encodings without the low-rank assumption. Additionally, we design a novel attention module that generates the attention scores in a directional range to aggregate the spatial and temporal features. The directional attention enables Grid4D to more accurately fit the diverse deformations across distinct scene components based on the spatial encoded features. Moreover, to mitigate the inherent lack of smoothness in explicit representation methods, we introduce a smooth regularization term that keeps our model from the chaos of deformation prediction. Our experiments demonstrate that Grid4D significantly outperforms the state-of-the-art models in visual quality and rendering speed. Project page: https://***/Grid4D-web/. Copyright © 2024, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

NeuVSA: A Unified and Efficient Accelerator for Neural Vector Search

NeuVSA: A Unified and Efficient Accelerator for Neural Vecto...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Ziming Yuan Lei Dai Wen Li Jie Zhang Shengwen Liang Ying Wang Cheng Liu Huawei Li Xiaowei Li Jiafeng Guo Peng Wang Renhai Chen Gong Zhang State Key Lab of Processors Institute of Computing TechnologyCAS University of Chinese Academy of Sciences School of Computer and Information Technology Shanxi University School of Computer Science Peking University Zhongguancun National Laboratory Beijing Key Lab of Network Data Science and Technology Institute of Computing Technology CAS Huawei Technologies Co. Ltd. China

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Neural Vector Search (NVS) has exhibited superior search quality over traditional key-based strategies for information retrieval tasks. An effective NVS architecture requires high recall, low latency, and high throughput to enhance user experience and cost-efficiency. However, implementing NVS on existing neural network accelerators and vector search accelerators is sub-optimal due to the separation between the embedding stage and vector search stage at both algorithm and architecture levels. Fortunately, we unveil that Product Quantization (PQ) opens up an opportunity to break separation. However, existing PQ algorithms and accelerators still focus on either the embedding stage or the vector search stage, rather than both simultaneously. Simply combining existing solutions still follows the beaten track of separation and suffers from insufficient parallelization, frequent data access conflicts, and the absence of scheduling, thus failing to reach optimal recall, latency, and throughput. To this end, we propose a unified and efficient NVS accelerator dubbed NeuVSA based on algorithm and architecture co-design philosophy. Specifically, on the algorithm level, we propose a learned PQ-based unified NVS algorithm that consolidates two separate stages into the same computing and memory access paradigm. It integrates an end-to-end joint training strategy to learn the optimal codebook and index for enhanced recall and reduced PQ complexity, thus achieving smoother acceleration. On the architecture level, we customize a homogeneous NVS accelerator based on the unified NVS algorithm. Each sub-accelerator is optimized to exploit all parallelism exposed by unified NVS, incorporating a structured index assignment strategy and an elastic on-chip buffer to alleviate buffer conflicts for reduced latency. All sub-accelerators are coordinated using a hardware-aware scheduling strategy for boosted throughput. Experimental results show that the joint training strategy improves recall

关键词： Training Quantization (signal) Philosophical considerations Graphics processing units computer architecture Throughput Vectors User experience System-on-chip Indexes

来源：评论

学校读者我要写书评

暂无评论

Near-linear time approximation algorithms for k-means with outliers 24

Near-linear time approximation algorithms for k-means with o...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Junyu Huang Qilong Feng Ziyun Huang Jinhui Xu Jianxin Wang School of Computer Science and Engineering Central South University Changsha China and Xiangjiang Laboratory Changsha China Department of Computer Science and Software Engineering Penn State Erie The Behrend College Department of Computer Science and Engineering State University of New York at Buffalo NY School of Computer Science and Engineering Central South University Changsha China and Xiangjiang Laboratory Changsha China and The Hunan Provincial Key Lab of Bioinformatics Central South University Changsha China

The k-means with outliers problem is one of the most extensively studied clustering problems in the field of machine learning, where the goal is to discard up to z outliers and identify a minimum k-means clustering on the remaining data points. Most previous results for this problem have running time dependent on the aspect ratio Δ(the ratio between the maximum and the minimum pairwise distances) to achieve fast approximations. To address the issue of aspect ratio dependency on the running time, we propose sampling-based algorithms with almost linear running time in the data size, where a crucial component of our approach is an algorithm called Fast-Sampling. Fast-Sampling algorithm can find inliers that well approximate the optimal clustering centers without relying on a guess for the optimal clustering costs, where a 4-approximate solution can be obtained in time $O(\frac{ndk\log\log n}{\epsilon^2})$ with O(k/ε) centers opened and (1 + ε)z outliers discarded. To reduce the number of centers opened, we propose a center reduction algorithm, where an O(1/ε)-approximate solution can be obtained in time $O(\frac{ndk\log \log n}{\epsilon^2} + dpoly(k, \frac{1}{\epsilon})\log(n\Delta))$ with (1 + ε)z outliers discarded and exactly k centers opened. Empirical experiments suggest that our proposed sampling-based algorithms outperform state-of-the-art algorithms for the k-means with outliers problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advances in nuclear detection and readout techniques

引用

Nuclear science and Techniques 2023年第12期34卷 281-358页

作者： Rui He Xiao‑Yang Niu Yi Wang Hong‑Wei Liang Hong‑Bang Liu Ye Tian Hong‑Lin Zhang Chao‑Jie Zou Zhi‑Yi Liu Yun‑Long Zhang Hai‑Bo Yang Ju Huang Hong‑Kai Wang Wei‑Jia Han Bei Cao Gang Chen Cong Dai Li‑Min Duan Rui‑Rui Fan Fang‑Fa Fu Jian‑Hua Guo Dong Han Wei Jiang Xian‑Qin Li Xin Li Zhuo‑Dai Li Yu‑Tie Liang Shun Liao De‑Xu Lin Cheng‑Ming Liu Guo‑Rui Liu Jun‑Tao Liu Ze Long Meng‑Chen Niu Hao Qiu Hu Ran Xiang‑Ming Sun Bo‑Tan Wang Jia Wang Jin‑Xiang Wang Qi‑Lin Wang Yong‑Sheng Wang Xiao‑Chuan Xia Hao‑Qing Xie He‑Run Yang Hong Yin Hong Yuan Chun‑Hui Zhang Rui‑Guang Zhao Ran Zheng Cheng‑Xin Zhao Institute of Modern Physics Chinese Academy of SciencesLanzhou 730000China School of Nuclear Science and Technology University of Chinese Academy of SciencesBeijing 100049China Advanced Energy Science and Technology Guangdong Laboratory Huizhou 516000China Key Laboratory of Particle and Radiation Imaging Department of Engineering PhysicsTsinghua UniversityBeijing 100084China School of Integrated Circuits Dalian University of TechnologyDalian 116020China Guangxi Key Laboratory for Relativistic Astrophysics School of Physical Science and TechnologyGuangxi UniversityNanning 530004China School of Nuclear Science and Technology Lanzhou UniversityLanzhou 730000China State Key Laboratory of Particle Detection and Electronics University of Science and Technology of ChinaHefei 230026China Department of Radiation Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijing 100021China Electronic Engineering School Heilongjiang UniversityHarbin 150080China Spallation Neutron Source Science Center Dongguan 523803China Micro‑electronic Department Harbin Institute of TechnologyHarbin 150001China Purple Mountain Observatory Chinese Academy of SciencesNanjing 210034China Liaoning Academy of Materials Shenyang 110167China Istituto Nazionale di Fisica Nucleare Sezione di PerugiaPerugiaItaly School of Mathematics and Physics Chengdu University of TechnologyChengdu 620035China PLAC Key Laboratory of Quark and Lepton Physics(MOE)Central China Normal UniversityWuhan 430079China School of Electronics and Information Northwestern Polytechnical UniversityXi’an 710129China State Key Lab of Superhard Materials College of PhysicsJilin UniversityChangchun 130012China School of Computer Science Northwestern Polytechnical UniversityXi’an 710129China

“A Craftsman Must Sharpen His Tools to Do His Job,”said *** detection and readout techniques are the foundation of particle physics,nuclear physics,and particle astrophysics to reveal the nature of the ***,they are being increasingly used in other disciplines like nuclear power generation,life sciences,environmental sciences,medical sciences,*** article reviews the short history,recent development,and trend of nuclear detection and readout techniques,covering Semiconductor Detector,Gaseous Detector,Scintillation Detector,Cherenkov Detector,Transition Radiation Detector,and Readout *** explaining the principle and using examples,we hope to help the interested reader underst and this research field and bring exciting information to the community.

关键词： Silicon detector Wide bandgap detector Time projection chamber(TPC) Multigap resistive plate chamber detector(MRPC) Scintillation detector Calorimeters Cherenkov detector Transition radiation detector Artificial intelligence Trigger-less readout

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：