检索结果-内蒙古大学图书馆

27th International Conference on MultiMedia Modeling, MMM 2021

作者： Long, Jia Lu, Hongtao Key Lab of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783030678319

In this paper, we focus on the task of generating realistic images given an input semantic layout, which is also called semantic image synthesis. Most of previous methods are based on conditional generative adversarial networks mechanism, which is stacks of convolution, normalization, and non-linearity layers. However, these methods easily generate blurred regions and distorted structures. There are two limits existing: their normalization layers are unable to make a good balance between keeping semantic layout information and geometric changes;and cannot effectively aggregated multi-level feature. To address the above problems, we propose a novel method which incorporates multi-level gate feature aggregation mechanism (GFA) and spatially adaptive batch-instance normalization (SPAda-BIN) for semantic image synthesis. Experiments on several challenging datasets demonstrate the advantage of the proposed method over existing approaches, in terms of both visual fidelity and quantitative metrics. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Leveraging Unstructured Statistical Knowledge in a Probabilistic Language of Thought 42

Leveraging Unstructured Statistical Knowledge in a Probabili...

引用

42nd Annual Meeting of the cognitive science Society: Developing a Mind: Learning in Humans, Animals, and Machines, CogSci 2020

作者： Lew, Alexander K. Tessler, Michael Henry Mansinghka, Vikash K. Tenenbaum, Joshua B. Department of Electrical Engineering and Computer Science MIT United States Department of Brain and Cognitive Sciences MIT United States

One hallmark of human reasoning is that we can bring to bear a diverse web of common-sense knowledge in any situation. The vastness of our knowledge poses a challenge for the practical implementation of reasoning systems as well as for our cognitive theories - how do people represent their commonsense knowledge? On the one hand, our best models of sophisticated reasoning are top-down, making use primarily of symbolically-encoded knowledge. On the other, much of our understanding of the statistical properties of our environment may arise in a bottom-up fashion, for example through associationist learning mechanisms. Indeed, recent advances in AI have enabled the development of billion-parameter language models that can scour for patterns in gigabytes of text from the web, picking up a surprising amount of common-sense knowledge along the way-but they fail to learn the structure of coherent reasoning. We propose combining these approaches, by em- bedding language-model-backed primitives into a state-of-the-art probabilistic programming language (PPL). On two open-ended reasoning tasks, we show that our PPL models with neural knowledge components characterize the distribution of human responses more accurately than the neural language models alone, raising interesting questions about how people might use language as an interface to common-sense knowledge, and suggesting that building probabilistic models with neural language-model components may be a promising approach for more human-like AI. © 2020 The Author(s)

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Development of Flexible Sendust Composite Sheets with Enhanced Magnetic Permeability for Microwave Absorbers and Antennas

引用

IEEE Transactions on Magnetics 2025年

作者： Whalen, Matthew P. Plouff, David T. Shevchenko, Nicholas B. Mirotznik, Mark Xiao, John Q. University of Delaware Quantum Science and Engineering Program NewarkDE19716 United States University of Delaware Department of Physics and Astronomy NewarkDE19716 United States University of Delaware Center for Composite Materials NewarkDE19716 United States University of Delaware Department of Electrical and Computer Engineering NewarkDE19716 United States

The demand for high-frequency soft magnetic composites with elevated permeability and flexibility is growing for applications in microwave absorbers and magnetodielectric antennas. However, balancing high permeability with mechanical flexibility remains challenging. This study presents flexible Sendust (FeSiAl) composite sheets, fabricated with a hot-pressing technique that aligns flakes within an acrylic rubber and epoxy resin matrix. The alignment significantly enhances relative permeability at high frequencies, achieving single-layer film properties of μr' = 14.8 and μr"= 20.4 at 1 GHz, alongside high saturation magnetization (118 eμg) and high hesitivity (44.7 kΩ m-1), outperforming commonly used materials such as NiZn ferrite. Our method supports customizable thickness without sacrificing permeability, establishing a versatile platform for advanced conformal microwave absorber and antenna applications. © 2025 IEEE.

关键词： Saturation magnetization

来源：评论

学校读者我要写书评

暂无评论

Proposal of Close Contact Confirmation Method in Cyberspace for Influencer Marketing

Proposal of Close Contact Confirmation Method in Cyberspace ...

引用

IEEE Global Conference on Life sciences and Technologies (LifeTech)

作者： Atsushi Isozaki Naoki Suyama Tetsuo Imai Kenichi Arai Toru Kobayashi Computer and Information Science Program Graduate School of Engineering Nagasaki University Nagasaki Japan Computer and Information Science Program School of Engineering Nagasaki University Nagasaki Japan Division of Electrical Engineering and Computer Science Graduate School of Engineering Nagasaki University Nagasaki Japan

ISBN: (数字)9781665418751

ISBN: (纸本)9781665448086

We have developed the system to measure the effectiveness of influencer marketing by a general-purpose method using web browsers and web servers. This system uses the “COVID-19 Contact-Confirming Application” (COCOA) as a reference model. COCOA was developed by the Ministry of Health, Labor and Welfare in response to the epidemic of COVID-19, to detect suspicions of close contact while maintaining anonymity. The same model was applied to the cyberspace, and the “close contact confirmation method in the cyberspace” was considered in this study. We implemented a prototype and confirmed its functional validity while solving implementation problems using the Cross-Storage library.

关键词： COVID-19 Cyberspace Prototypes Web servers Libraries Browsers Proposals

来源：评论

学校读者我要写书评

暂无评论

StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and Commands

arXiv

引用

arXiv 2021年

作者： Cho, Won Ik Moon, Sangwhan Kim, Jong In Kim, Seok Min Kim, Nam Soo Department of Electrical and Computer Engineering INMC Seoul National University Korea Republic of Department of Computer Science Tokyo Institute of Technology Japan Google LLC Interdisciplinary Program in Cognitive Science Seoul National University Korea Republic of

Paraphrasing is often performed with less concern for controlled style conversion. Especially for questions and commands, style-variant paraphrasing can be crucial in tone and manner, which also matters with industrial applications such as dialog systems. In this paper, we attack this issue with a corpus construction scheme that simultaneously considers the core content and style of directives, namely intent and formality, for the Korean language. Utilizing manually generated natural language queries on six daily topics, we expand the corpus to formal and informal sentences by human rewriting and transferring. We verify the validity and industrial applicability of our approach by checking the adequate classification and inference performance that fit with conventional fine-tuning approaches, at the same time proposing a supervised formality transfer task. © 2021, CC BY-SA.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Collaborative Positional-Motion Excitation Module for Efficient Action Recognition 18th

Collaborative Positional-Motion Excitation Module for Effici...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Alsarhan, Tamam Lu, Hongtao Key Lab of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China MOE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783030893699

Massive progress for vision-based action recognition has been made in the last few years, owing to the advancement of deep convolutional neural networks (CNNs). In contrast with 2D CNN-based approaches, 3D CNN-based approaches can effectively capture spatial and temporal features. However, they are computationally intensive. To boost 2D-CNN performance, most of the existing methods leverage channel attention (e.g. squeeze and excitation), which despite its strong impact on the model performance, operates only on the channel space and ignores the spatial space. In this work, we design a generic and collaborative excitation module, namely the Collaborative Positional-Motion Excitation Module (CPME) for action recognition. CPME is a dual-pathway excitation module designed to embed the crucial types of information, mainly the positional information and the motion information, for efficient action recognition. Positional Enhancement Pathway (PEP), the first pathway of CPME, considers encoding direction-aware and position-sensitive information. Motion Enhancement Pathway (MEP), the second pathway, encodes the motion information by emphasizing the informative features in each frame and excite motion-sensitive channels. We integrate the proposed CPME into 2D CNNs to form a simple yet effective CPME-Net with limited extra computational cost. Finally, a discriminative and diverse video-level representation for action recognition is generated by end-to-end training. Experiments on two popular action recognition datasets demonstrate that CPME blocks bring performance improvements on 2D CNN baseline, and our method achieves competitive results against the state-of-the-art methods. © 2021, Springer Nature Switzerland AG.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

A CONFORMER BASED ACOUSTIC MODEL FOR ROBUST AUTOMATIC SPEECH RECOGNITION

arXiv

引用

arXiv 2022年

作者： Yang, Yufeng Wang, Peidong Wang, DeLiang Department of Computer Science and Engineering The Ohio State University United States Microsoft Corporation United States Center for Cognitive and Brain Sciences The Ohio State University United States

This study addresses robust automatic speech recognition (ASR) by introducing a Conformer-based acoustic model. The proposed model builds on the wide residual bi-directional long short-term memory network (WRBN) with utterance-wise dropout and iterative speaker adaptation, but employs a Conformer encoder instead of the recurrent network. The Conformer encoder uses a convolution-augmented attention mechanism for acoustic modeling. The proposed system is evaluated on the monaural ASR task of the CHiME-4 corpus. Coupled with utterance-wise normalization and speaker adaptation, our model achieves 6.25% word error rate, which outperforms WRBN by 8.4% relatively. In addition, the proposed Conformer-based model is 18.3% smaller in model size and reduces total training time by 79.6%. Copyright © 2022, The Authors. All rights reserved.

关键词： Acoustic Modeling

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Networks for Handwritten Bangla Character Recognition

引用

IAENG International Journal of Applied Mathematics 2023年第4期53卷

作者： Begum, H. Islam, M.M. Eva, H.S. Emon, N.H. Siddique, F.A. Department of Electrical and Electronic Engineering East West University A/2 Aftabnagar Dhaka Bangladesh Department of Electrical Engineering and Computer Science South Dakota State University United States Engineering and Design Department Reverie Power and Automation Engineering Limited Bangladesh Program in Smart System Integrated Solutions Aalto University Finland

In recent years, deep convolutional networks (DCNN) have gained popularity for different classification (or recognition) tasks. In this paper, three well known DCNN structures were used, i.e., AlexNet, SqueezeNet and GoogLeNet, and their classification performances in recognizing handwritten Bangla isolated characters were compared. These networks have simpler structures compared to the recent DCNNs. Experiments on a standard Bangla database revealed that the overall performance of GoogLeNet is slightly better than the other two networks. Further analysis using saliency maps of the test samples revealed the important features that are learned by the networks for classifying characters. This information led us to understand why classification of some samples fail and how to rectify these. © (2023), (International Association of Engineers). All Rights Reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Gallium Oxide as Photonic Integrated Platforms in the UV-Visible Spectra

Gallium Oxide as Photonic Integrated Platforms in the UV-Vis...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Zhou, Jingan Zhao, Xuan Xu, Rui Zhang, Xiang Fu, Kai Li, Tao Xu, Mingfei Luo, Shisong He, Ziyi Robinson, Jacob T. Zhu, Hanyu Ajayan, Pulickel M. Zhang, Xiaodong Zhao, Yuji Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Materials Science and NanoEngineering Rice University HoustonTX77005 United States School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States Nanofabrication facility Suzhou Institute of Nano-Tech and Nano-Bionics Chinese Academy of Sciences Jiangsu Suzhou215123 China

We report the Ga2O3 as photonic integrated platforms and its nonlinear optical effects in the UV-visible spectra. A low propagation loss of 3.7 dB/cm and second-order susceptibility of x(2)=4.89xl03pm/V were obtained.... 详细信息

ISBN: (纸本)9781957171258

关键词： Gallium compounds

来源：评论

学校读者我要写书评

暂无评论

The Wilhelm Tell Dataset of Affordance Demonstrations 20

The Wilhelm Tell Dataset of Affordance Demonstrations

引用

20th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2025

作者： Ringe, Rachel Pomarlan, Mihai Tsiogkas, Nikolaos De Giorgis, Stefano Hedblom, Maria Malaka, Rainer University of Bremen Digital Media Lab Bremen Germany University of Bremen Bremen Germany Ku Leuven Department of Computer Science Leuven Belgium Institute of Cognitive Sciences and Technologies National Research Council Catania Italy Jönköping School of Engineering Department of Computing Jönköping Sweden

ISBN: (纸本)9798350378931

Affordances - i.e. possibilities for action that an environment or objects in it provide - are important for robots operating in human environments to perceive. Existing approaches train such capabilities on annotated static images or shapes. This work presents a novel dataset for affordance learning of common household tasks. Unlike previous approaches, our dataset consists of video sequences demonstrating the tasks from first- and third-person perspectives, along with metadata about the affordances that are manifested in the task, and is aimed towards training perception systems to recognize affordance manifestations. The demonstrations were collected from several participants and in total record about seven hours of human activity. The variety of task performances also allows studying preparatory maneuvers that people may perform for a task, such as how they arrange their task space, which is also relevant for collaborative service robots. © 2025 IEEE.

关键词： Industrial robots

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：