检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

4,699 篇 会议
650 篇 期刊文献
3 篇 学位论文

馆藏范围

5,352 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,496 篇 工学
- 834 篇 电气工程
- 773 篇 计算机科学与技术...
- 323 篇 信息与通信工程
- 238 篇 控制科学与工程
- 159 篇 软件工程
- 126 篇 机械工程
- 94 篇 仪器科学与技术
- 40 篇 电子科学与技术（可...
- 31 篇 交通运输工程
- 17 篇 航空宇航科学与技...
- 11 篇 测绘科学与技术
- 11 篇 生物医学工程（可授...
- 10 篇 土木工程
- 9 篇 网络空间安全
- 7 篇 材料科学与工程（可...
- 4 篇 动力工程及工程热...
- 4 篇 矿业工程
- 4 篇 石油与天然气工程
- 4 篇 核科学与技术
160 篇 理学
- 68 篇 系统科学
- 54 篇 数学
- 18 篇 生物学
- 17 篇 物理学
- 9 篇 统计学（可授理学、...
- 5 篇 地球物理学
- 4 篇 地理学
100 篇 管理学
- 98 篇 管理科学与工程(可...
49 篇 医学
- 45 篇 临床医学
38 篇 文学
- 37 篇 新闻传播学
7 篇 艺术学
- 7 篇 设计学（可授艺术学...
6 篇 农学
2 篇 教育学
1 篇 军事学

主题

5,352 篇 inference algori...
534 篇 computational mo...
410 篇 fuzzy systems
402 篇 algorithm design...
386 篇 fuzzy logic
384 篇 bayesian methods
371 篇 computer science
333 篇 neural networks
331 篇 training
304 篇 approximation al...
292 篇 bayes methods
226 篇 optimization
224 篇 clustering algor...
216 篇 signal processin...
214 篇 data mining
208 篇 fuzzy sets
204 篇 heuristic algori...
192 篇 prediction algor...
190 篇 accuracy
185 篇 feature extracti...

机构

15 篇 school of electr...
11 篇 university of ch...
10 篇 school of comput...
10 篇 zhejiang univ co...
9 篇 tsinghua univers...
9 篇 purple mt labs p...
9 篇 national univers...
8 篇 microsoft resear...
8 篇 university of mi...
7 篇 department of co...
7 篇 tianjin univ col...
7 篇 department of el...
7 篇 university of so...
7 篇 department of au...
7 篇 tsinghua univ de...
6 篇 ibm thomas j. wa...
6 篇 nanyang technol ...
6 篇 university of so...
6 篇 department of el...
6 篇 department of co...

作者

8 篇 pushmeet kohli
7 篇 li cheng
7 篇 edward r. doughe...
7 篇 wei li
7 篇 xiaodong wang
7 篇 t.s. huang
7 篇 erik b. sudderth
7 篇 a. taylan cemgil
7 篇 p. baranyi
7 篇 nizar bouguila
6 篇 simon godsill
6 篇 alan s. willsky
6 篇 hui wang
6 篇 ying wu
6 篇 wang wei
6 篇 s. suresh
6 篇 chen yongxin
6 篇 yang xu
6 篇 luca benini
6 篇 viktor k. prasan...

语言

5,281 篇 英文
59 篇 其他
11 篇 中文
1 篇 西班牙文

检索条件"主题词=inference algorithms"

共 5352 条记录，以下是111-120 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Enhancing Novel Object Detection via Cooperative Foundational Models

Enhancing Novel Object Detection via Cooperative Foundationa...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Rohit Bharadwaj Muzammal Naseer Salman Khan Fahad Shahbaz Khan MBZUAI Khalifa University Australian National University Linköping University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

In this work, we address the challenging and emergent problem of novel object detection (NOD), focusing on the accurate detection of both known and novel object categories during inference. Traditional object detection algorithms are inherently closed-set, limiting their capability to handle NOD. We present a novel approach to transform existing closed-set detectors into open-set detectors. This transformation is achieved by leveraging the complementary strengths of pre-trained foundational models, specifically CLIP and SAM, through our cooperative mechanism. Furthermore, by integrating this mechanism with state-of-the-art open-set detectors such as GDINO, we establish new benchmarks in object detection performance. Our method achieves 17.42 mAP in novel object detection and 42.08 mAP for known objects on the challenging LVIS dataset. Adapting our approach to the COCO OVD split, we obtain an impressive result of 49.6 Novel AP50, which outperforms existing SOTA methods with similar backbone. Our code is available at: https://***/coop-foundation-models/.

关键词： Instance segmentation Training Location awareness Adaptation models Limiting Focusing Object detection Detectors Transforms inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Real-Time Performance Analysis of Multi-Armed Bandit Solution for OBSS and Dynamic Channel Bonding in WLAN

Real-Time Performance Analysis of Multi-Armed Bandit Solutio...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Remya P. R J. Govindarajan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (数字)9798331507022

ISBN: (纸本)9798331507039

Rapid expansion of dense Wi-Fi network deploy-ments creates challenges in optimizing performance. Existing multi-armed bandit (MAB) solutions for dynamic channel bonding (DCB) and overlapping basic service set (OBSS) issues are tested using simulations. This research aims to identify the gaps in current solutions through real-time performance analysis. Along-side this primary objective, we proposed a modified exploration-first algorithm to minimize convergence time. This secondary objective helped us achieve the primary objective. The results demonstrate that our algorithm can adapt to dynamic Wi-Fi environments and improve the user experience. We also present a summary of the inferences from the primary objective study.

关键词： Heuristic algorithms IEEE 802.11ax Standard Real-time systems inference algorithms User experience Performance analysis Bonding Wireless fidelity Standards Convergence

来源：评论

学校读者我要写书评

暂无评论

Comparative Knowledge Distillation

Comparative Knowledge Distillation

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Alex Tianyi Xu Alex Wilf Paul Pu Liang Alexander Obolenskiv Daniel Fried Louis-Philippe Morency Carnegie Mellon University Pittsburgh PA USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

In the era of large-scale pretrained models, Knowledge Distillation (KD) serves an important role in transferring the wisdom of computationally-heavy teacher models to lightweight, efficient student models while preserving performance. Yet KD settings often assume readily available access to teacher models capable of performing many in-ferences-a notion increasingly at odds with the realities of costly large-scale models. Addressing this gap, we study an important question: how KD algorithms fare as the number of teacher inferences decreases, a setting we term Reduced-Teacher-inference Knowledge Distillation (RTI-KD). We observe that the performance of prevalent KD techniques and state-of-the-art data augmentation strategies suffers considerably as the number of teacher inferences is reduced. One class of approaches, termed “relational” knowledge distillation underperforms the rest, yet we hypothesize that they hold promise for reduced dependency on teacher models because they can augment the effective dataset size without additional teacher calls. We find that a simple change - performing high-dimensional comparisons instead of low-dimensional relations, which we term Comparative Knowledge Distillation - vaults performance well over existing KD approaches. We perform empirical evaluation across varied experimental settings and rigorous analysis to understand the learning outcomes of our method. All code is made publicly available.

关键词： Training Computer vision Correlation Computational modeling Large language models Data augmentation Chronic kidney disease inference algorithms Computational efficiency Glass box

来源：评论

学校读者我要写书评

暂无评论

An Algorithm for Identifying Altimeter Setting Errors from ADS-B Data

An Algorithm for Identifying Altimeter Setting Errors from A...

引用

Integrated Communications, Navigation and Surveillance Conference, ICNS

作者： Nikolaos Mourousias Emilien Robert David De Smedt EUROCONTROL Brussels Belgium

ISBN: (数字)9798331534738

ISBN: (纸本)9798331534745

This study introduces an algorithm designed to detect barometric pressure setting (BPS) errors in large-scale flight data. The algorithm leverages Automatic Dependent Surveillance-Broadcast (ADS-B) data to detect deviations from the expected BPS values. A statistical model incorporating pilot-selected QNH values is developed to estimate local QNH variations, enabling precise error identification. Unlike previous studies that rely on Meteorological Aerodrome Reports (METAR) data, which may be limited or unavailable, particularly at smaller airports, this approach uses ADS-B data for both inferring local QNH and identifying outliers, enabling large-scale analysis. The QNH inference principle is based on a moving median over a subset of flights near a given location and time. Although a fixed time window presented promising results, a performance enhancement has been achieved by dynamically selecting the optimal moving median window size for each dataset. To validate the accuracy of the inferred QNH values, the results were first compared against METAR data. This comparison demonstrated strong agreement between the inferred and observed QNH values, establishing the reliability of the proposed method. Further validation was conducted using two well-known case studies from recent safety investigation reports. ADS-B data for the same day and area were processed, and the algorithm accurately identified the same BPS error, confirming its capability to detect and locate such errors. Following the validation of the algorithm, an analysis was conducted using ADS-B data from multiple airports of EURO-CONTROL member states over a 31-day period. The analysis identified multiple cases that require further investigation and gathered statistics on these errors. With further analysis of error patterns, the study provides insights into the potential underlying causes of these errors. This is achieved by creating new error categorization, examining the error frequencies, using string m

关键词： Measurement Navigation Surveillance Atmospheric modeling Airports Market research inference algorithms Safety Reliability Aircraft

来源：评论

学校读者我要写书评

暂无评论

Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching for Speaker Diarization

Flow-TSVAD: Target-Speaker Voice Activity Detection via Late...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhengyang Chen Bing Han Shuai Wang Yidi Jiang Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China National University of Singapore Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speaker diarization is typically considered as a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore for the first time the use of neural network-based generative methods for speaker diarization. We implement a Flow-Matching (FM) based generative algorithm within the sequenceto-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, we propose mapping the binary label sequence into a dense latent space before applying the generative algorithm, and our proposed Flow-TSVAD method can significantly outperform the traditional Seq2Seq-TSVAD system. Additionally, we observe that the FM algorithm converges rapidly during the inference stage, only requiring two inference steps to achieve promising results. Moreover, as a generative model, Flow-TSVAD allows for sampling different diarization results by running the model multiple times, so the ensemble system combining the results from various sampling instances can further boost the diarization performance.

关键词： Voice activity detection Frequency modulation Computational modeling Signal processing algorithms Signal processing inference algorithms Acoustics Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Basis Function Learning for Variable-Length and Continuous-Indexed Signals

Basis Function Learning for Variable-Length and Continuous-I...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Siyuan Li Lei Cheng Feng Yin Jianlong Li Peter Gerstoft College of ISEE Zhejiang University Hangzhou China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Scripps Institution of Oceanography University of California San Diego CA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Representing variable-length and continuous-indexed signals through a linear combination of basis functions poses a fundamental challenge in science and engineering. Current approaches resort to preprocessing steps, such as interpolation and extrapolation, to handle irregular and off-grid measurements, which compromise the physical nature of signals and degrade the representation performance. To address this challenge, rather than utilizing discrete vectors, we introduce a Bayesian functional representation model that capitalizes on the continuous nature and rich expressiveness of Gaussian processes to facilitate interpretable and effective basis function learning. Moreover, an analytical and efficient algorithm based on the variational inference framework is developed. Experimental results using real-life datasets demonstrate the superior performance of our proposed method.

关键词： Interpolation Extrapolation Current measurement Data preprocessing Signal processing algorithms Gaussian processes Vectors inference algorithms Speech processing Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Neural Adaptive Contextual Video Streaming

Neural Adaptive Contextual Video Streaming

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jianchao Yang Mufan Liu Puyue Hou Yiling Xu Jun Sun Department of Electronic Engineering Shanghai Jiao Tong University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Video streaming services typically employ traditional codecs, such as H.264, to encode videos into multiple bitrate representations. These codecs are tightly limited by discrete quantization parameters (QPs), resulting in encoded rates that do not align with the target bitrate. Additionally, the subpar video quality produced by conventional codecs does not meet the demands of high-resolution communication. Considering the limitations of traditional codecs, we take a fresh new approach to video streaming by leveraging advanced deep learning-based video codecs. Specifically, we develop a neural adaptive contextual video streaming framework that incorporates: 1) an ensemble deep reinforcement learning based adaptive bitrate algorithm named TSAC that enables continuous bitrate adjustment to varying network conditions 2) a two-stage proportional-integral-derivative-based rate control module that dynamically fine-tunes QPs to ensure the encoded bitrate aligning with the target bitrate. Furthermore, we implement intra-GoP and inter-GoP techniques to accelerate the inference process of the contextual video codec for real-time processing needs. Our experiments demonstrate that the average relative error in bitrate remains below 2%, the quality of experience provided by our TSAC agents surpasses that of existing discrete algorithms by 13%-20%. Our optimization techniques enable real-time decoding at approximately 24 frames per second for quad high definition videos.

关键词： Adaptive systems Bit rate Signal processing algorithms Streaming media Approximation algorithms Real-time systems inference algorithms Decoding Video codecs Speech processing

来源：评论

学校读者我要写书评

暂无评论

DOC: Detection of On-Line Failures in CNNs

DOC: Detection of On-Line Failures in CNNs

引用

Latin American Test Workshop, LATW

作者： V. Turco N. Bellarmino A. Ruospo R. Cantoro E. Sanchez Politecnico di Torino DAUIN Torino Italy

ISBN: (数字)9781665477635

ISBN: (纸本)9781665477642

The integration of Artificial Intelligence (AI) in safety-critical systems raises concerns about reliability, particularly due to the inherent uncertainty of AI algorithms and the complexity of modern hardware, compromising billion of transistors. Existing solutions, such as Algorithm-Based Fault Tolerance often focus on running detection algorithms after every inference, introducing a not negligible overhead in the detection phase. This paper introduces a two-phase fault detection technique for Convolutional Neural Networks (CNNs) with floating-point precision. The first phase identifies easily detectable faults (such as those stemming from a bit-flip on the 30th of a floating-point representation), while the second one targets hard-to-detect critical faults—those producing a wrong prediction but having no visible effect during faults' propagation. Although these faults constitute only 1.4% of all critical faults, their detection is crucial for ensuring system reliability. Validated on the CIFAR-10 dataset with a ResNet-20 model, the proposed method achieves up to 99.67% coverage of critical inferences while maintaining moderate computational overhead. This lightweight, real-time solution enhances the robustness of CNNs in safety-critical applications.

关键词： Uncertainty Fault tolerant systems inference algorithms Robustness Real-time systems Hardware Convolutional neural networks Transistors Artificial intelligence Integrated circuit reliability

来源：评论

学校读者我要写书评

暂无评论

DFTIMP: Distributed Fake Traffic Injection from Multiple Points for Obfuscation of IoT Traffic

DFTIMP: Distributed Fake Traffic Injection from Multiple Poi...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Ken Sasaki Ryo Yamamoto Satoshi Ohzahata The University of Electro-Communications Tokyo Japan

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The rapid proliferation of Internet of Things (IoT) devices in smart homes has raised user privacy concerns through various attacks by analyzing wireless communication traffic. Such attacks often use machine learning algorithms to identify device categories and working states to map them to user behavior. Traffic obfuscation such as packet padding, packet shaping, and fake traffic injection can address these kinds of user privacy inference attacks. However, such traffic obfuscation methods generally rely on a single injection device and cannot scale effectively as network size increases. To overcome this issue, we propose DFTIMP (Distributed Fake Traffic Injection from Multiple Points) for obfuscation of IoT traffic. We conducted experiments to evaluate the effectiveness of traffic obfuscation reducing the overhead of each device. Experimental results show that the proposed method reduces the overhead of individual injection devices without degrading their obfuscation effectiveness, making it suitable for application to large networks.

关键词： Wireless communication Privacy Machine learning algorithms Smart homes inference algorithms Internet of Things Object recognition Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Computing First Network Multi-dimensional Resource Collaborative Allocation Based on Federated Segmentation Learning

Dynamic Computing First Network Multi-dimensional Resource C...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Yi Liu Junping Du Zhe Xue Zeli Guan Department of Computer Science Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

Driven by the challenges associated with training large models in heterogeneous networks, where a one-size-fits-all training strategy can result in inefficiencies, we propose a versatile Federated Split Learning (FSL) algorithm designed for dynamic resource allocation. Conventional methods often encounter resource limitations, particularly in settings with varying computational abilities. Our algorithm overcomes this issue by intelligently distributing model components among nodes according to their specific computational capabilities, thereby enhancing resource utilization.A key feature of our approach is the inclusion of an auxiliary classifier layer that enables each client to calculate losses and locally update parameters, while only sending activation values to the central server. This mechanism not only reduces communication overhead but also speeds up the overall training process. Additionally, we implement an earlyexit inference strategy that adapts based on task complexity and available resources, further enhancing inference efficiency.

关键词： Training Federated learning Heuristic algorithms Computational modeling Dynamic scheduling inference algorithms Heterogeneous networks Complexity theory Resource management Servers

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 8 9 10 11 12 13 14 15 16 17 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：