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

25,250 篇 会议
280 篇 期刊文献
21 册 图书
3 篇 学位论文

馆藏范围

25,554 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

15,801 篇 工学
- 9,866 篇 计算机科学与技术...
- 6,079 篇 电气工程
- 5,768 篇 信息与通信工程
- 5,611 篇 软件工程
- 2,017 篇 光学工程
- 1,448 篇 控制科学与工程
- 1,280 篇 机械工程
- 1,153 篇 电子科学与技术（可...
- 873 篇 生物医学工程（可授...
- 833 篇 生物工程
- 794 篇 仪器科学与技术
- 261 篇 网络空间安全
- 253 篇 化学工程与技术
- 244 篇 安全科学与工程
- 238 篇 交通运输工程
- 183 篇 材料科学与工程（可...
- 164 篇 土木工程
- 161 篇 建筑学
5,714 篇 理学
- 3,481 篇 物理学
- 2,204 篇 数学
- 886 篇 生物学
- 563 篇 统计学（可授理学、...
- 420 篇 系统科学
- 310 篇 化学
3,021 篇 医学
- 2,897 篇 临床医学
- 312 篇 基础医学(可授医学...
- 229 篇 药学(可授医学、理...
1,387 篇 管理学
- 849 篇 管理科学与工程(可...
- 610 篇 图书情报与档案管...
- 169 篇 工商管理
181 篇 法学
133 篇 农学
55 篇 教育学
52 篇 文学
51 篇 经济学
51 篇 军事学
22 篇 艺术学

主题

3,121 篇 image processing
2,084 篇 image coding
2,021 篇 visualization
1,752 篇 image segmentati...
1,488 篇 feature extracti...
1,082 篇 image reconstruc...
907 篇 cameras
885 篇 signal processin...
833 篇 image color anal...
756 篇 humans
714 篇 image edge detec...
688 篇 image enhancemen...
665 篇 computer vision
650 篇 training
582 篇 image analysis
568 篇 deep learning
536 篇 image quality
481 篇 conferences
473 篇 object detection
472 篇 robustness

机构

51 篇 school of electr...
50 篇 shanghai jiao to...
39 篇 ieee
38 篇 university of sc...
36 篇 shanghai jiao to...
36 篇 school of comput...
34 篇 shanghai jiao to...
33 篇 university of ch...
32 篇 microsoft resear...
26 篇 national institu...
25 篇 department of el...
24 篇 hendisli&#x011f
23 篇 institute for in...
23 篇 institute of ima...
23 篇 istanbul teknik ...
23 篇 institute of dig...
22 篇 peking univ inst...
21 篇 institute of inf...
21 篇 univ chinese aca...
21 篇 univ sci & techn...

作者

62 篇 guangtao zhai
46 篇 song li
45 篇 zhai guangtao
32 篇 jie yang
27 篇 li li
25 篇 m. vetterli
25 篇 bovik alan c.
25 篇 li sumei
25 篇 li song
25 篇 sarp ertürk
24 篇 jing zhang
24 篇 b. macq
23 篇 zhang lei
23 篇 li zhuo
23 篇 d.r. bull
22 篇 jürgen seiler
21 篇 shi guangming
20 篇 liu yang
20 篇 zhang wenjun
18 篇 mohamed-chaker l...

语言

24,744 篇 英文
489 篇 土耳其文
206 篇 其他
131 篇 中文
2 篇 西班牙文
2 篇 葡萄牙文

检索条件"任意字段=IEEE Visual Communications and Image Processing Conference"

共 25554 条记录，以下是281-290 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：

VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis

VoiceDiT: Dual-Condition Diffusion Transformer for Environme...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Jaemin Jung Junseok Ahn Chaeyoung Jung Tan Dat Nguyen Youngjoon Jang Joon Son Chung Korea Advanced Institute of Science and Technology South Korea

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We present VoiceDiT, a multi-modal generative model for producing environment-aware speech and audio from text and visual prompts. While aligning speech with text is crucial for intelligible speech, achieving this alignment in noisy conditions remains a significant and underexplored challenge in the field. To address this, we present a novel audio generation pipeline named VoiceDiT. This pipeline includes three key components: (1) the creation of a large-scale synthetic speech dataset for pre-training and a refined real-world speech dataset for fine-tuning, (2) the Dual-DiT, a model designed to efficiently preserve aligned speech information while accurately reflecting environmental conditions, and (3) a diffusion-based image-to-Audio Translator that allows the model to bridge the gap between audio and image, facilitating the generation of environmental sound that aligns with the multi-modal prompts. Extensive experimental results demonstrate that VoiceDiT outperforms previous models on real-world datasets, showcasing significant improvements in both audio quality and modality integration. Synthesized samples are available on our demo page: https://***/projects/voicedit/

关键词： Adaptation models visualization Translation Pipelines Production Speech enhancement Signal processing Transformers Acoustics Text to speech

来源：评论

学校读者我要写书评

暂无评论

Chitrarth: Bridging Vision and Language for a Billion People

Chitrarth: Bridging Vision and Language for a Billion People

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Shaharukh Khan Ayush Tarun Abhinav Ravi Ali Faraz Praveen Kumar Pokala Anagha Bhangare Raja Kolla Chandra Khatri Shubham Agarwal Krutrim AI Bangalore India

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recent multimodal foundation models are primarily trained on English or high resource European language data, which limits their applicability to other medium and low-resource languages, such as the Indian languages. To address this limitation, we introduce Chitrarth (Chitra: image; Artha: Meaning), an inclusive Vision-Language Model (VLM), specifically targeting the rich linguistic diversity and visual reasoning across 10 prominent Indian languages. Our model effectively integrates a state-of-the-art (SOTA) multilingual Large Language Model (LLM) with a vision module, primarily trained on multilingual image-text data. Furthermore, we also introduce BharatBench, a comprehensive framework for evaluating VLMs across various low resource languages, ultimately contributing to more diverse and effective AI systems. Our model presents SOTA results for benchmarks across Indian languages while retaining its efficiency in English. Through our research, we aim to set new benchmarks in multilingual-multimodal capabilities, offering substantial improvements over existing models and establishing a foundation for facilitating future advancements in this arena.

关键词： Training Representation learning visualization Pipelines Training data Benchmark testing Data models Multilingual Speech processing Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy image Reconstruction

Deep Unfolded Approximate Message Passing for Quantitative A...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Odysseas Pappas Jonathan Mamou Adrian Basarab Denis Kouamé Alin Achim Visual Information Laboratory University of Bristol Bristol UK Department of Radiology Weill Cornell Medicine New York USA CREATIS University of Lyon Lyon France IRIT University of Toulouse III Paul Sabatier Toulouse France

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Quantitative Acoustic Microscopy (QAM) is an imaging technology utilising high frequency ultrasound to produce quantitative two-dimensional (2D) maps of acoustical and mechanical properties of biological tissue at microscopy scale. Increased frequency QAM allows for finer resolution at the expense of increased acquisition times and data storage cost. Compressive sampling (CS) methods have been employed to produce QAM images from a reduced sample set, with recent state of the art utilising Approximate Message Passing (AMP) methods. In this paper we investigate the use of AMP-Net, a deep unfolded model for AMP, for the CS reconstruction of QAM parametric maps. Results indicate that AMP-Net can offer superior reconstruction performance even in its stock configuration trained on natural imagery (up to 63% in terms of PSNR), while avoiding the emergence of sampling pattern related artefacts.

关键词： Training Time-frequency analysis Ultrasonic imaging Quadrature amplitude modulation Microscopy Message passing Two-dimensional displays Acoustics Speech processing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Virtual Reality Technology in Digital Protection of Cultural Heritage Landscape

Research on the Application of Virtual Reality Technology in...

引用

Electronics, Energy Systems and Power Engineering (EESPE), ieee International conference on

作者： Yan Huang Yu Huang Nanning University Nanning China

ISBN: (数字)9798350389579

ISBN: (纸本)9798350389586

This paper puts forward a kind of digital protection system based on VR, which uses 3D modeling and dynamic rendering to provide high quality digital protection and exhibition platform. First, the cultural heritage landscape is modeled with high precision through laser scanning and drone photogrammetry technology to obtain three-dimensional point cloud data. Subsequently, an efficient dynamic rendering algorithm is designed, which can enhance the realism and immersion of the landscape by simulating physical properties such as lighting, shadows, reflection and refraction. To ensure that the system can still run smoothly under high load, image processing optimization technology is used to stabilize the rendering frame rate at more than 60 frames per second and perform well under multiple dynamic scenes switching. At last, the paper builds a virtual reality simulation environment based on Unity and Unreal Engine. The experiment shows that the system can reconstruct the cultural heritage scene exactly, the rendering effect is high, and the user experience rate reaches 92%.

关键词： Solid modeling Three-dimensional displays Heuristic algorithms Virtual environments Rendering (computer graphics) visual effects User experience image restoration Cultural differences Protection

来源：评论

学校读者我要写书评

暂无评论

Online Optimization of Offloading Video Analytics Tasks to Multiple Edges for Accuracy Maximization

Online Optimization of Offloading Video Analytics Tasks to M...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yu Liang Sheng Zhang Jie Wu School of Computer and Electronic Information and the School of Artificial Intelligence Nanjing Normal University State Key Laboratory for Novel Software Technology Nanjing University Center for Networked Computing Temple University US

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Real-time video analytics (VA) presents challenges due to its computational intensity and latency sensitivity, especially when processed on mobile devices with limited local resources. We propose to offload VA tasks to edge servers with diverse computational capabilities. We present a "detect + track" approach with on-device object tracking and edge-assisted object detection. We formulate a long-term nonlinear integer programming to maximize the overall accuracy within detection frequency and latency constraints. We then design a queue-based online optimization algorithm to solve it: relax the original problem from the integer domain to the real domain, then employ a queue-based adaptation and randomized rounding strategy. Via rigorous proof, both dynamic regret regarding detection accuracy and the real-time requirement are ensured. Evaluation results also demonstrate the effectiveness of our approach.

关键词： Accuracy image edge detection visual analytics Signal processing algorithms Streaming media Signal processing Real-time systems Servers Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

Volatile MAB-based Configuration Selection for Offloading Video Analytics Tasks to Edges

Volatile MAB-based Configuration Selection for Offloading Vi...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The demand for video analytics is increasing rapidly. Due to the limited computational and network resources on edge servers, adjusting video configurations such as resolution and frame rate has become an effective strategy to reduce computational and transmission costs. However, this can also compromise detection accuracy, necessitating a balance between resource consumption and analytics accuracy. Also, the dynamic availability of edge servers and variability in their energy consumption further complicates making offloading decisions and configuration selection. In this paper, we first model the problem as a mixed planning program. Then we propose a volatile MAB-based configuration selection algorithm, VACS, which aims to maximize video analytics accuracy while reducing the overall energy consumption. Rigorous proof measures the gap between online decisions and the optimum. Extensive experiments validate the effectiveness of VACS.

关键词： Energy consumption Accuracy visual analytics image edge detection Heuristic algorithms Signal processing algorithms Signal processing Planning Servers Speech processing

来源：评论

学校读者我要写书评

暂无评论

Pre-training with Synthetic Patterns for Audio

Pre-training with Synthetic Patterns for Audio

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yuchi Ishikawa Tatsuya Komatsu Yoshimitsu Aoki LY Corporation Keio University Tokyo Japan LY Corporation Tokyo Japan Keio University Kanagawa Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we propose to pre-train audio encoders using synthetic patterns instead of real audio data. Our proposed framework consists of two key elements. The first one is Masked Autoencoder (MAE), a self-supervised learning framework that learns from reconstructing data from randomly masked counterparts. MAEs tend to focus on low-level information such as visual patterns and regularities within data. Therefore, it is unimportant what is portrayed in the input, whether it be images, audio mel-spectrograms, or even synthetic patterns. This leads to the second key element, which is synthetic data. Synthetic data, unlike real audio, is free from privacy and licensing infringement issues. By combining MAEs and synthetic patterns, our framework enables the model to learn generalized feature representations without real data, while addressing the issues related to real audio. To evaluate the efficacy of our framework, we conduct extensive experiments across a total of 13 audio tasks and 17 synthetic datasets. The experiments provide insights into which types of synthetic patterns are effective for audio. Our results demonstrate that our framework achieves performance comparable to models pre-trained on AudioSet-2M and partially outperforms image-based pre-training methods.

关键词： Data privacy visualization Autoencoders Self-supervised learning Signal processing Licenses Data models Speech processing image reconstruction Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Using Convolutional Neural Networks for image Recognition in IoT Applications

Using Convolutional Neural Networks for Image Recognition in...

引用

Pervasive Computational Technologies (ICPCT), International conference on

作者： Durgam Rajababu Sampenga Veerraju K. Suresh Kumar Sonali Gupta V B Thurai Raaj Rahul Joshi Department of EEE School of Engineering SR University Warangal Telangana India Department of Electronics and Communications Engineering Dadi Institute of Engineering and Technology Anakapalli Visakhapatnam Andhra Pradesh MBA Department Panimalar Engineering College Varadarajapuram Poonamallee Chennai J C Bose University of Science and Technology YMCA Faridabad Electrical and Electronics Engineering Madanapalle Institute of Technology & Science Madanapalle Andhra Pradesh Department of Journalism & Mass Communication SMeH Manav Rachna International Institute of Research and Studies Haryana India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Convolutional Neural Networks (CNNs) have grown into a powerful picture identification tool. They are an important part of making Internet of Things (IoT) apps. In this regard, CNNs make it possible to analyse visual data gathered from networked devices, like cameras and sensors, effectively and accurately. With an emphasis on its potential for real-time applications for example smart surveillance, healthcare monitoring, autonomous cars, and industrial automation, this study investigates the incorporation of CNN-based image identification into IoT contexts. We tackle important issues such as the requirement for low-latency processing, energy economy, and computing limitations on edge devices. In order to maximise CNN performance in the resource-constrained IoT ecosystem, strategies like model compression, edge computing, and distributed architectures are covered. The ability to interpret large volumes of visual data is improved by the integration of CNNs with IoT, providing creative solutions for automation and intelligent decision-making across numerous industries.

关键词： Training visualization Automation Computational modeling Surveillance Training data Feature extraction Convolutional neural networks Internet of Things image classification

来源：评论

学校读者我要写书评

暂无评论

Low-Power Approximate Computing-based VLSI Architecture for Biomedical Signal processing

Low-Power Approximate Computing-based VLSI Architecture for ...

引用

2025 International conference on visual Analytics and Data visualization, ICVADV 2025

作者： Sathiya, A. Prabhavathy, B. Balasupramani, A. Amutha, A. Kavitha, L. Saravanakumar, R. Department of Electronics and Communication Engineering Karur Thalavapalayam639113 India E.G.S. Pillay Engineering College Department of Electronics and Communication Engineering Tamil Nadu Nagapattinam611002 India Rajalakshmi Institute of Technology Department of Electronics and Communication Engineering Chennai600124 India Dhanalakshmi Srinivasan College of Engineering Department of Electrical and Electronics Engineering Coimbatore641105 India Thalavapalayam639113 India Velalar College of Engineering and Technology Department of Biomedical Engineering Erode638012 India

ISBN: (纸本)9798331521394

The analysis of ECG, EEG and EMG signals requires biomedical signal processing which needs low-power high-performance VLSI architectures to achieve real-time processing. This paper introduces an optimized VLSI architecture which enables biomedical signal processing through energy-efficient digital filtering along with feature extraction as well as pipeline-based clock gating. The proposed architecture combines a distributed arithmetic FIR filter without multipliers to reduce complexity and it integrates a low-power feature extraction system that detects ECG R-peaks and EEG spectral energy and EMG muscle activity effectively. The system uses dynamic clock gating together with power gating to cut down both dynamic power usage and leakage power. The experimental findings show that the developed VLSI architecture both reduces power usage through low hardware complexity while keeping high accuracy levels for biomedical signal processing. The system delivers its performance measurement through power dissipation and area efficiency along with processing speed which enables its use in wearable and implantable medical devices. © 2025 ieee.

关键词： Medical image processing

来源：评论

学校读者我要写书评

暂无评论

Improving Open-vocabulary Video visual Relation Detection with Decomposed Prompt Learning and Relation Adjustment

Improving Open-vocabulary Video Visual Relation Detection wi...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Ming Pei Yi Tan Yanbin Hao Hao Zhang Jinmeng Wu Basura Fernando Xun Yang School of Information Science and Technology University of Science and Technology of China Hefei China Centre for Frontier AI Research Agency for Science Technology and Research(A*STAR) Singapore Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Open-vocabulary video visual relation detection (VidVRD) expands the scope of detecting object relations in videos to include unseen categories. It marks considerable advancement in recognizing novel relations solely by training on a base set, thus extending the frontiers of automated video understanding. However, the performance of current methods on novel predicates remains significantly inferior to that on base categories. We attribute this discrepancy to two primary factors: (1) A significant task misalignment between the visual Relation Detection (VRD) task and the pre-trained models’ visual feature extractors, which are often designed for tasks like video-text retrieval and image-text retrieval, resulting in poor generalization to the novel set. (2) The relatively small size and limited vocabulary of open-vocabulary datasets, which create a substantial gap between base and novel predicates. Consequently, text prompts trained on the base set fail to generalize effectively to the novel set. To address these issues, we propose two improvement measures: (1) We decompose base and novel relations into actional and spatial patterns and introduce an innovative text prompt learning method that leverages the shared patterns between base and novel relations. (2) We develop a relation probability adjustment mechanism that utilizes reliable base relation predictions to adjust the probabilities of relations in novel classes by considering their overlaps in either actional or spatial contents. Experimental results on the benchmark dataset demonstrate significant performance improvements.

关键词： Training Learning systems visualization Vocabulary Signal processing Benchmark testing Feature extraction Acoustics Reliability Speech processing

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 << < 25 26 27 28 29 30 31 32 33 34 > >>

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：