检索结果-内蒙古大学图书馆

作者： Li, Hongyu Yang, Meng Yang, Chao Kang, Jianglang Suo, Xiang Meng, Weiliang Li, Zhen Mao, Lijuan Sheng, Bin Qi, Jun School of Information science and Technology Beijing Forestry University Beijing China Engineering Research Center for Forestry-Oriented Intelligent Information Processing National Forestry and Grassland Administration Beijing China School of Athletic Performance Shanghai University of Sport Shanghai China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong Univerity Shanghai China Department of Computing Xi'an JiaoTong-Liverpool University Suzhou China

We propose a comprehensive soccer match video analysis pipeline tailored for broadcast footage, which encompasses three pivotal stages: soccer field localization, player tracking, and soccer ball detection. Firstly, we introduce sports camera calibration to seamlessly map soccer field images from match videos onto a standardized two-dimensional soccer field template. This addresses the challenge of consistent analysis across video frames amid continuous camera angle changes. Secondly, given challenges such as occlusions, high-speed movements, and dynamic camera perspectives, obtaining accurate position data for players and the soccer ball is non-trivial. To mitigate this, we curate a large-scale, high-precision soccer ball detection dataset and devise a robust detection model, which achieved the (Formula presented.) of 80.9%. Additionally, we develop a high-speed, efficient, and lightweight tracking model to ensure precise player tracking. Through the integration of these modules, our pipeline focuses on real-time analysis of the current camera lens content during matches, facilitating rapid and accurate computation and analysis while offering intuitive visualizations. © 2024 John Wiley & Sons Ltd.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Arbitrarily polarized bound states in the continuum with twisted photonic crystal slabs

引用

Light(science & Applications) 2023年第4期12卷 542-550页

作者： Haoye Qin Zengping Su Mengqi Liu Yixuan Zeng Man-Chung Tang Mengyao Li Yuzhi Shi Wei Huang Cheng-Wei Qiu Qinghua Song Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Institute of Precision Optical Engineering School of Physics Science and EngineeringTongji UniversityShanghai 200092China Key Laboratory of Multifunctional Nanomaterials and Smart Systems Suzhou institute of Nano-Tech and Nano-Bionics(SINANO)Chinese Academy of Sciences(CAS)Suzhou 215123China

Arbitrary polarized vortex beam induced by polarization singularity offers a new platform for both classical optics and quantum entanglement *** states in the continuum(BICs)have been demonstrated to be associated with topological charge and vortex polarization singularities in momentum *** conventional symmetric photonic crystal slabs(PhCSs),BIC is enclosed by linearly polarized far fields with winding angle of 2π,which is unfavorable for high-capacity and multi-functionality integration-optics ***,we show that by breakingσz-symmetry of the PhCS,asymmetry in upward and downward directions and arbitrarily polarized BIC can be realized with a bilayer-twisted *** exhibits elliptical polarization states with constant ellipticity angle at every point in momentum space within the vicinity of *** topological nature of BIC reflects on the orientation angle of polarization state,with a topological charge of 1 for any value of ellipticity *** coverage of Poincarésphere(i.e.,-π/4≤X≤4 and-π/2≤ψ≤π/2)and higher-order Poincarésphere can be realized by tailoring the twist *** findings may open up new avenues for applications in structured light,quantum optics,and twistronics for photons.

关键词： Poincaré polarized twisted

来源：评论

学校读者我要写书评

暂无评论

Service-Based Event Penetration from IoT Sensors to Businesses: a Case Study

Service-Based Event Penetration from IoT Sensors to Business...

引用

2022 CCF International Conference on Service science, CCF ICSS 2022

作者： Wang, Guiling Fang, Jun Wang, Jing Yu, Jian Zhang, Liang Han, Yanbo Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data Beijing China North China University of Technology School of Information Science and Technology Beijing China Auckland University of Technology Department of Computer Science Auckland New Zealand Shanghai Key Laboratory of Data Science Shanghai China Shanghai Institute of Intelligent Electronics & Systems Shanghai China

ISBN: (数字)9781665498616

ISBN: (纸本)9781665498616

By leveraging IoT Big Data, BPM can gain real-time physical world information to make faster and more accurate decisions, but there is a technical gap between IoT sensors and businesses. To bridge the gap, an event penetration mechanism from IoT sensors to business processes is proposed along a practical case study. This paper presents a concrete IoT-BPM application case dealing with seaborne safety ensurance in transporting liquefied natural gas (LNG), analyzes its technical challenges, and examines the feasibility and supposed effects of the BRIBOT approach. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Eye Movements Using Multi-way Autoregressive Model

Emotion Recognition from Eye Movements Using Multi-way Autor...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tian-Fang Ma Xuan-Hao Liu Wei-Long Zheng Bao-Liang Lu Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The application of physiological signals in emotion recognition is a popular research topic in human-computer interactions. Eye movement, as an important physiological signal, plays an essential role in medicine, psychology, cognitive science, and other scientific research fields. Previous studies have successfully identified human emotions by combining various eye-related measurements, selecting features, and utilizing machine learning techniques. However, the exploration of eye movement signals in emotion recognition remains insufficient. In this study, we utilize eye tracking heatmap and eye movement trajectory data for emotion recognition for the first time. Based on the two types of eye movement data, we develop a multi-way autoregressive model capable of processing multi-view eye movement data. Compared to traditional deep learning baseline models, our model better adapts to the structure of eye movement data and significantly improves the classification performance. Furthermore, we integrate heatmap and trajectory data with commonly used eye-related measurement features, which further enhance the performance of emotion recognition beyond previous methods.

关键词： Heating systems Emotion recognition Adaptation models Accuracy Psychology Gaze tracking Biomedical measurement Data models Physiology Trajectory

来源：评论

学校读者我要写书评

暂无评论

How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing 41

How Universal Polynomial Bases Enhance Spectral Graph Neural...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Huang, Keke Wang, Yu Guang Li, Ming Liò, Pietro School of Computing National University of Singapore Singapore Institute of Natural Sciences School of Mathematical Sciences Zhangjiang Institute for Advanced Study Shanghai Jiao Tong University Shanghai China Shanghai AI Laboratory Shanghai China School of Mathematics and Statistics University of New South Wales Sydney Australia Zhejiang Institute of Optoelectronics Jinhua China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua China Department of Computer Science and Technology Cambridge University Cambridge United Kingdom

Spectral Graph Neural Networks (GNNs), alternatively known as graph filters, have gained increasing prevalence for heterophily graphs. Optimal graph filters rely on Laplacian eigendecomposition for Fourier transform. In an attempt to avert prohibitive computations, numerous polynomial filters have been proposed. However, polynomials in the majority of these filters are predefined and remain fixed across different graphs, failing to accommodate the varying degrees of heterophily. Addressing this gap, we demystify the intrinsic correlation between the spectral property of desired polynomial bases and the heterophily degrees via thorough theoretical analyses. Subsequently, we develop a novel adaptive heterophily basis wherein the basis vectors mutually form angles reflecting the heterophily degree of the graph. We integrate this heterophily basis with the homophily basis to construct a universal polynomial basis UniBasis, which devises a polynomial filter-based graph neural network - UniFilter. It optimizes the convolution and propagation in GNN, thus effectively limiting over-smoothing and alleviating over-squashing. Our extensive experiments, conducted on datasets with a diverse range of heterophily, support the superiority of UniBasis in the universality but also its proficiency in graph explanation. Copyright 2024 by the author(s)

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

On-chip metamaterial-enabled high-order mode-division multiplexing

引用

Advanced Photonics 2023年第5期5卷 106-113页

作者： Yu He Xingfeng Li Yong Zhang Shaohua An Hongwei Wang Zhen Wang Haoshuo Chen Yetian Huang Hanzi Huang Nicolas KFontaine Roland Ryf Yuhan Du Lu Sun Xingchen Ji Xuhan Guo Yingxiong Song Qianwu Zhang Yikai Su Shanghai Jiao Tong University Department of Electronic EngineeringState Key Laboratory of Advanced Optical Communication Systems and NetworksShanghaiChina Nokia Bell Labs Murray HillNew JerseyUnited States Shanghai University Key Laboratory of Specialty Fiber Optics and Optical Access NetworksJoint International Research Laboratory of Specialty Fiber Optics and Advanced CommunicationShanghaiChina Shanghai Jiao Tong University School of Electronic Information and Electrical EngineeringJohn Hopcroft Center for Computer ScienceShanghaiChina

Mode-division multiplexing(MDM)technology enables high-bandwidth data transmission using orthogonal waveguide modes to construct parallel data ***,few demonstrations have been realized for generating and supporting high-order modes,mainly due to the intrinsic large material groupvelocity dispersion(GVD),which make it challenging to selectively couple different-order spatial *** show the feasibility of on-chip GVD engineering by introducing a gradient-index metamaterial structure,which enables a robust and fully scalable MDM *** demonstrate a record-high-order MDM device that supports TE_(0)–TE_(15)modes simultaneously.40-GBaud 16-ary quadrature amplitude modulation signals encoded on 16 mode channels contribute to a 2.162 Tbit∕s net data rate,which is the highest data rate ever reported for an on-chip single-wavelength *** method can effectively expand the number of channels provided by MDM technology and promote the emerging research fields with great demand for parallelism,such as high-capacity optical interconnects,high-dimensional quantum communications,and large-scale neural networks.

关键词： integrated photonics metamaterial mode-division multiplexing subwavelength grating

来源：评论

学校读者我要写书评

暂无评论

BMP-SD: Marrying Binary and Mixed-Precision Quantization for Efficient Stable Diffusion Inference

BMP-SD: Marrying Binary and Mixed-Precision Quantization for...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Cheng Gu Gang Li Xiaolong Lin Jiayao Ling Jian Cheng Xiaoyao Liang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China The Key Laboratory of Cognition and Decision Intelligence for Complex Systems CASIA Beijing China AiRiA Nanjing China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Stable Diffusion (SD) is an emerging deep neural network (DNN) model that has demonstrated impressive capabilities in generative tasks such as text-to-image generation. However, the iterative denoising stage of the SD model is extremely expensive in both computations and memory accesses, making it challenging for fast and energy-efficient edge deployment. To alleviate the overhead of denoising, in this paper we propose BMP-SD, a post-training quantization framework for hardware-efficient SD inference. BMP-SD employs binary weight quantization to significantly reduce the computational complexity and memory footprint of iterative denoising, along with dynamic step-aware mixed-precision activation quantization, based on the observation that not all denoising steps are equally important for a specific input prompt. Experiments on the text-to-image generation task show that BMP-SD achieves mixed-precision (W1.73A4.87) with minimal accuracy loss on MS-COCO 2014 dataset. We also evaluate the BMP-SD quantized model on three state-of-the-art bit-flexible DNN accelerators, results reveal that our method can deliver up to 5.14× performance and 3.85×energy efficiency improvements compared to W8A8 quantization.

关键词： Quantization (signal) Accuracy Computational modeling Noise reduction Text to image Europe Artificial neural networks Energy efficiency Iterative methods Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Pruning Networks With Cross-Layer Ranking & k-Reciprocal Nearest Filters

引用

IEEE Transactions on Neural Networks and Learning systems 2023年第11期34卷 9139-9148页

作者： Lin, Mingbao Cao, Liujuan Zhang, Yuxin Shao, Ling Lin, Chia-Wen Ji, Rongrong School of Informatics Xiamen University Media Analytics and Computing Laboratory Department of Artificial Intelligence Xiamen361005 China Tencent Youtu Laboratory Shanghai200233 China School of Informatics Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City Computer Science Department Xiamen361005 China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates National Tsing Hua University Department of Electrical Engineering and the Institute of Communications Engineering Hsinchu30013 Taiwan Institute of Artificial Intelligence Xiamen University Xiamen361005 China

This article focuses on filter-level network pruning. A novel pruning method, termed CLR-RNF, is proposed. We first reveal a 'long-tail' pruning problem in magnitude-based weight pruning methods and then propose a computation-aware measurement for individual weight importance, followed by a cross-layer ranking (CLR) of weights to identify and remove the bottom-ranked weights. Consequently, the per-layer sparsity makes up the pruned network structure in our filter pruning. Then, we introduce a recommendation-based filter selection scheme where each filter recommends a group of its closest filters. To pick the preserved filters from these recommended groups, we further devise a ${k}$ -reciprocal nearest filter (RNF) selection scheme where the selected filters fall into the intersection of these recommended groups. Both our pruned network structure and the filter selection are nonlearning processes, which, thus, significantly reduces the pruning complexity and differentiates our method from existing works. We conduct image classification on CIFAR-10 and ImageNet to demonstrate the superiority of our CLR-RNF over the state-of-the-arts. For example, on CIFAR-10, CLR-RNF removes 74.1% FLOPs and 95.0% parameters from VGGNet-16 with even 0.3% accuracy improvements. On ImageNet, it removes 70.2% FLOPs and 64.8% parameters from ResNet-50 with only 1.7% top-five accuracy drops. Our project is available at https://***/lmbxμCLR-RNF. © 2012 IEEE.

关键词： computer architecture

来源：评论

学校读者我要写书评

暂无评论

SBQ: Exploiting Significant Bits for Efficient and Accurate Post-Training DNN Quantization

SBQ: Exploiting Significant Bits for Efficient and Accurate ...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Jiayao Ling Gang Li Qinghao Hu Xiaolong Lin Cheng Gu Jian Cheng Xiaoyao Liang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China The Key Laboratory of Cognition and Decision Intelligence for Complex Systems CASIA Beijing China AiRiA Nanjing China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Post-Training Quantization is an effective technique for deep neural network acceleration. However, as the bit-width decreases to 4 bits and below, PTQ faces significant challenges in preserving accuracy, especially for attention-based models like LLMs. The main issue lies in considerable clipping and rounding errors induced by the limited number of quantization levels and narrow data range in conventional low-precision quantization. In this paper, we present an efficient and accurate PTQ method that targets 4 bits and below through algorithm and architecture co-design. Our key idea is to dynamically extract a small portion of significant bit terms from high-precision operands to perform low-precision multiplications under the given computational budget. Specifically, we propose Significant-Bit Quantization (SBQ). It exploits a product-aware method to dynamically identify significant terms and an error-compensated computation scheme to minimize compute errors. We present a dedicated inference engine to unleash the power of SBQ. Experiments on CNNs, ViTs, and LLMs reveal that SBQ consistently outperforms prior PTQ methods under 2~4-bit quantization. We also compare the proposed inference engine with state-of-the-art bit-operation-based quantization architectures TQ and Sibia. Results show that SBQ can achieve the highest area and energy efficiency.

关键词： Quantization (signal) Accuracy Heuristic algorithms Europe computer architecture Artificial neural networks Energy efficiency Inference algorithms Engines Faces

来源：评论

学校读者我要写书评

暂无评论

SBQ: Exploiting Significant Bits for Efficient and Accurate Post-Training DNN Quantization

SBQ: Exploiting Significant Bits for Efficient and Accurate ...

引用

2025 Design, Automation and Test in Europe Conference, DATE 2025

作者： Ling, Jiayao Li, Gang Hu, Qinghao Lin, Xiaolong Gu, Cheng Cheng, Jian Liang, Xiaoyao Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China Casia The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Beijing China AiRiA Nanjing China

ISBN: (纸本)9783982674100

Post-Training Quantization is an effective technique for deep neural network acceleration. However, as the bit-width decreases to 4 bits and below, PTQ faces significant challenges in preserving accuracy, especially for attention-based models like LLMs. The main issue lies in considerable clipping and rounding errors induced by the limited number of quantization levels and narrow data range in conventional low-precision quantization. In this paper, we present an efficient and accurate PTQ method that targets 4 bits and below through algorithm and architecture co-design. Our key idea is to dynamically extract a small portion of significant bit terms from high-precision operands to perform low-precision multiplications under the given computational budget. Specifically, we propose Significant-Bit Quantization (SBQ). It exploits a product-aware method to dynamically identify significant terms and an error-compensated computation scheme to minimize compute errors. We present a dedicated inference engine to unleash the power of SBQ. Experiments on CNNs, ViTs, and LLMs reveal that SBQ consistently outperforms prior PTQ methods under 24-bit quantization. We also compare the proposed inference engine with state-of-the-art bit-operation-based quantization architectures TQ and Sibia. Results show that SBQ can achieve the highest area and energy efficiency. © 2025 EDAA.

关键词： Deep neural networks

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：