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

52,961 篇 会议
1,121 篇 期刊文献
10 册 图书

馆藏范围

54,092 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

26,316 篇 工学
- 17,171 篇 计算机科学与技术...
- 9,476 篇 软件工程
- 8,117 篇 电气工程
- 3,820 篇 控制科学与工程
- 2,467 篇 信息与通信工程
- 2,393 篇 机械工程
- 1,898 篇 生物医学工程（可授...
- 1,311 篇 仪器科学与技术
- 1,051 篇 生物工程
- 778 篇 电子科学与技术（可...
- 696 篇 土木工程
- 672 篇 光学工程
- 657 篇 建筑学
- 527 篇 交通运输工程
- 453 篇 测绘科学与技术
- 385 篇 安全科学与工程
4,511 篇 理学
- 1,748 篇 数学
- 1,310 篇 物理学
- 981 篇 生物学
- 699 篇 系统科学
- 433 篇 统计学（可授理学、...
- 399 篇 化学
3,455 篇 管理学
- 2,111 篇 管理科学与工程(可...
- 1,604 篇 图书情报与档案管...
- 765 篇 工商管理
3,101 篇 医学
- 2,681 篇 临床医学
- 751 篇 基础医学(可授医学...
- 361 篇 药学(可授医学、理...
665 篇 教育学
- 651 篇 教育学
515 篇 农学
- 485 篇 作物学
340 篇 法学
189 篇 经济学
168 篇 艺术学
135 篇 文学
29 篇 军事学
4 篇 历史学
1 篇 哲学

主题

34,664 篇 visualization
7,346 篇 data visualizati...
4,834 篇 training
4,314 篇 feature extracti...
2,956 篇 computational mo...
2,941 篇 three-dimensiona...
2,914 篇 cameras
2,454 篇 computer vision
2,439 篇 semantics
2,073 篇 task analysis
1,936 篇 conferences
1,622 篇 accuracy
1,315 篇 image color anal...
1,299 篇 data mining
1,284 篇 image segmentati...
1,265 篇 navigation
1,202 篇 robustness
1,189 篇 data models
1,144 篇 real-time system...
1,101 篇 shape

机构

95 篇 university of sc...
94 篇 tsinghua univers...
72 篇 univ chinese aca...
71 篇 shanghai jiao to...
66 篇 zhejiang univers...
59 篇 georgia inst tec...
48 篇 univ konstanz co...
46 篇 georgia institut...
41 篇 facebook ai rese...
40 篇 hong kong univ s...
39 篇 microsoft resear...
37 篇 school of comput...
35 篇 tu wien austria
34 篇 inria
34 篇 univ michigan an...
33 篇 massachusetts in...
32 篇 university of ce...
32 篇 carnegie mellon ...
30 篇 national institu...
30 篇 univ toronto on

作者

53 篇 itoh takayuki
44 篇 zhang lei
31 篇 lei wang
27 篇 jing zhang
26 篇 jun wang
25 篇 yongdong zhang
25 篇 pfister hanspete...
24 篇 schreck tobias
24 篇 van gool luc
24 篇 yang yi
24 篇 li li
22 篇 guangtao zhai
22 篇 nassir navab
22 篇 takahiro ogawa
20 篇 bin wang
20 篇 li xin
19 篇 shuqiang jiang
19 篇 chang remco
19 篇 jie yang
19 篇 wei liu

语言

53,551 篇 英文
300 篇 其他
189 篇 中文
21 篇 西班牙文
14 篇 土耳其文
9 篇 俄文
8 篇 葡萄牙文
1 篇 法文

检索条件"任意字段=IEEE Information Visualization Conference/IEEE Visualization Conference"

共 54092 条记录，以下是381-390 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：

Improving Visual Reinforcement Learning via Spatial-Temporal Data Augmentation

Improving Visual Reinforcement Learning via Spatial-Temporal...

引用

Consumer Electronics and Computer Engineering (ICCECE), 2021 ieee International conference on

作者： Jiabao Li Qingwen Hou Jie Zhang Xianzhong Chen Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China

ISBN: (数字)9798331533113

ISBN: (纸本)9798331533120

Sample efficiency has been a challenging problem in visual reinforcement learning, where agents not only learn polices but also extract meaningful state representations for decision making from images. Reinforcement Learning methods that adopt data augmentation have significantly improved sample efficiency. However, prior studies have primarily focused on spatial augmentation, which enhances data diversity but insufficiently exploits temporal information, such as historical states which is critical for time-series-dependent reinforcement learning tasks. To address this gap, we introduce a Spatial-Temporal Data Augmentation (STDA) framework designed to enhance the agent's ability to learn task-relevant state representations by effectively leveraging historical state information. We evaluate our approach using the DeepMind Control Suite, and empirical results demonstrate that STDA significantly improves performance, surpassing state-of-the-art methods across a range of tasks.

关键词： visualization Q-learning Law enforcement Decision making Training data Reinforcement learning Benchmark testing Data augmentation Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Relation Distillation for Efficient 3D Visual Grounding

Hierarchical Relation Distillation for Efficient 3D Visual G...

引用

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

作者： Jun Liu School of Information Renmin University of China BeiJing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

3D Vision-Language (3D-VL) Grounding seeks to localize 3D objects in point clouds using natural language descriptions. While existing methods focus on improving performance through intricate spatial understanding modules, the efficiency of 3D grounding models has been overlooked, despite its importance for real-time applications. To address this issue, we propose a novel hierarchical relation distillation framework that creates a small yet high-performing model through a two-stage distillation process. The first stage focuses on semantic feature distillation, eliminating noise and retaining valuable information for second stage training. The second stage utilizes half-layers of the teacher model for 3D relation feature distillation, enhancing computational efficiency without sacrificing accuracy. Experimental results on the challenging Nr3D and Sr3D datasets demonstrate that our distilled model achieves state-of-the-art performance while reducing computational costs by over 40%.

关键词： Training visualization Solid modeling Three-dimensional displays Accuracy Grounding Computational modeling Semantics Computational efficiency Speech processing

来源：评论

学校读者我要写书评

暂无评论

Structure-Preserving Video Hashing via Self-Supervised Transformer for Retrieval

Structure-Preserving Video Hashing via Self-Supervised Trans...

引用

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

作者： Lixia Du Xiaoping Liang Likai Yang Zhenjun Tang Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of MultiSource Information Mining & Security Guangxi Normal University Guilin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Self-supervised video hashing aims at generating hash codes and performing fast video content retrieval by leveraging the visual content information inherent in the videos themselves. Most existing methods often overlook the structure-preserving information within the visual content of the videos and thus cannot learn an effective discriminative video representation. In this paper, a Structure-Preserving Video Hashing (SPVH) via a self-supervised Transformer for retrieval is proposed by exploring the global relationships, local relationships, and inter-video relationships in the visual content of videos. In the proposed SPVH, a Transformer-based autoencoder model is used to extract the deep features of the videos. Moreover, a new structure-preserving loss function with the clustering loss, constraint loss, contrastive loss, and reconstruction loss is designed to capture the structural information of the videos. Extensive experiments are conducted on two large-scale video datasets. The results demonstrate the superior performance of our SPVH compared to some state-of-the-art methods.

关键词： visualization Codes Accuracy Semantics Autoencoders Signal processing Transformers Feature extraction Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Multi-level Feature Adaptation and Embeddings Alignment for Zero-shot Anomaly Detection

Multi-level Feature Adaptation and Embeddings Alignment for ...

引用

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

作者： Yiqing Liu Huilin Deng Gang Zhao School of Information Science and Technology University of Science and Technology of China HeFei China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Anomaly Detection (AD) is an important and challenging task in computer vision. Recently, Contrastive Language-Image Pre-training (CLIP) has shown impressive generalization capability in zero-shot AD tasks. However, the inherent global semantic consistency of CLIP fails to accurately identify subtle anomalies, and the lack of fine-grained alignment leads to inaccurate defect localization. In this study, we propose a hierarchical semantic feature adaptation framework designed to better leverage intermediate layer information from the visual encoder, enabling the effective capture of subtle and diverse anomaly-aware semantic features, thus improving CLIP’s adaptation to AD task. We further introduce an alignment and mask refinement co-optimization decoder to locate key anomalous regions from coarse to fine, thereby alleviating the misalignment between visual and textual embeddings. The experimental results demonstrate the effectiveness of our method.

关键词： Location awareness visualization Computer vision Adaptation models Semantics Signal processing Feature extraction Decoding Speech processing Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

SCENEDERELLA: Text-Driven 3D Scene Generation for Realistic Artboard

SCENEDERELLA: Text-Driven 3D Scene Generation for Realistic ...

引用

ieee International conference on Consumer Electronics (ICCE)

作者： Jungmin Lee Haeun Noh Jaeyoon Lee Jongwon Choi Dept. of Advanced Imaging GSAIM Chung-Ang University Seoul Republic of Korea Dept. of Artificial Intelligence Chung-Ang University Seoul Republic of Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

As global media and Video-on-Demand (VOD) markets expand, efficiently producing high-quality 3D scenes has become a key challenge. Our study named SCENEDERELLA generates 3D scenes useful for the film industry using simple text prompts. Since traditional diffusion models create fantastic images, they have limitations in generating scenes truly desired by real-world users. However, fine-tuning the clip encoder of the diffusion model enables the production of realistic 2D scenes for users. Once the initial 2D scenes align with the user's conceptual expectations, we construct 3D scenes using a depth estimator and 3D Gaussian Splatting. The study successfully demonstrates the generation of 3D movie scenes based on various movie scripts. Our method overcomes the limitations of traditional physical set production and offers a new approach that enables the rapid creation of diverse scenes. Additionally, it can be used as a pre-visualization video to attract investment in movies and dramas. Our approach is expected to introduce a new paradigm in content production, with film, gaming, and advertising. Additional results and interactive demos are available at our project website.

关键词： visualization Technological innovation Three-dimensional displays Costs Entertainment industry Production Motion pictures Diffusion models Advertising Investment

来源：评论

学校读者我要写书评

暂无评论

DETECLAP: Enhancing Audio-Visual Representation Learning with Object information

DETECLAP: Enhancing Audio-Visual Representation Learning wit...

引用

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

作者： Shota Nakada Taichi Nishimura Hokuto Munakata Masayoshi Kondo Tatsuya Komatsu LY Corporation Tokyo Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current audio-visual representation learning can capture rough object categories (e.g., "animals" and "instruments"), but it lacks the ability to recognize fine-grained details, such as specific categories like "dogs" and "flutes" within animals and instruments. To address this issue, we introduce DETECLAP, a method to enhance audio-visual representation learning with object information. Our key idea is to introduce an audio-visual label prediction loss to the existing Contrastive Audio-Visual Masked AutoEncoder to enhance its object awareness. To avoid costly manual annotations, we prepare object labels from both audio and visual inputs using state-of-the-art language-audio models and object detectors. We evaluate the method of audio-visual retrieval and classification using the VGGSound and AudioSet20K datasets. Our method achieves improvements in recall@10 of +1.5% and +1.2% for audio-to-visual and visual-to-audio retrieval, respectively, and an improvement in accuracy of +0.6% for audio-visual classification.

关键词： Representation learning visualization Annotations Instruments Autoencoders Manuals Dogs Detectors Signal processing Speech processing

来源：评论

学校读者我要写书评

暂无评论

Uncovering the Visual Contribution in Audio-Visual Speech Recognition

Uncovering the Visual Contribution in Audio-Visual Speech Re...

引用

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

作者： Zhaofeng Lin Naomi Harte Sigmedia Group School of Engineering Trinity College Dublin Ireland

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Audio-Visual Speech Recognition (AVSR) combines auditory and visual speech cues to enhance the accuracy and robustness of speech recognition systems. Recent advancements in AVSR have improved performance in noisy environments compared to audio-only counterparts. However, the true extent of the visual contribution, and whether AVSR systems fully exploit the available cues in the visual domain, remains unclear. This paper assesses AVSR systems from a different perspective, by considering human speech perception. We use three systems: Auto-AVSR, AVEC and AV-RelScore. We first quantify the visual contribution using effective SNR gains at 0 dB and then investigate the use of visual information in terms of its temporal distribution and word-level informativeness. We show that low WER does not guarantee high SNR gains. Our results suggest that current methods do not fully exploit visual information, and we recommend future research to report effective SNR gains alongside WERs.

关键词： visualization Accuracy Speech recognition Speech enhancement Signal processing Robustness Acoustics Noise measurement Gain Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

InstaSight: Leveraging AI to See Beyond Sight for Blind Users on Social Media

InstaSight: Leveraging AI to See Beyond Sight for Blind User...

引用

ieee International conference on Consumer Electronics (ICCE)

作者： Chun-Nan Chi Jia-Lien Hsu Chi-Huang Hung Chia-Hsun Hsu To Nguyen Tan Phuong Wei-Chih Juan Graduate Institute of Applied Science and Engineering Fu Jen Catholic University New Taipei City Taiwan R.O.C. Department of Computer Science and Information Engineering Fu Jen Catholic University New Taipei City Taiwan R.O.C. Dept. of Information Technology Graduate Institute of Applied Science and Engineering Fu Jen Catholic University Lee-Ming Institute of Technology New Taipei City Taiwan R.O.C. Dept. of International High School Kang Chiao International School New Taipei City Taiwan R.O.C. Dept. Electronical Engineering Lee-Ming Institute of Technology New Taipei City Taiwan R.O.C. Department of Information Management Hwa Hsia University Of Technology New Taipei City Taiwan R.O.C.

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

This study introduces “InstaSight,” a system enabling visually impaired individuals to engage with social media focused on visual content. InstaSight integrates a Single Board Computer, head-mounted webcam, and Bluetooth headset for seamless voice interactions. By utilizing the APIs of social media, speech recognition, and Large Language Models (LLMs), users can post photos and videos with voice-to-text captions and listen to comments converted from text or images. This system fosters social engagement, helping blind users connect and share experiences, improving their psychological well-being.

关键词： Headphones visualization Electric potential Social networking (online) Webcams Large language models Psychology Speech recognition Consumer electronics Videos

来源：评论

学校读者我要写书评

暂无评论

Application of Data Hiding Method Based on Triplet Difference in QR Code Images

Application of Data Hiding Method Based on Triplet Differenc...

引用

Consumer Electronics and Computer Engineering (ICCECE), 2021 ieee International conference on

作者： Dan He School of Artificial Intelligence Dongguan City University Dongguan Guangdong China

ISBN: (数字)9798331533113

ISBN: (纸本)9798331533120

Ensuring the privacy and security of sensitive information is paramount in the digital age. Quick response (QR) codes, known for their high data density and robust error correction capabilities, have become widely used, making them an ideal medium for secure data transmission. This paper introduces a novel data hiding method based on triplet differences, designed to embed secret information within QR code images. The proposed method manipulates the differences between pixel triplets in the QR code matrix, achieving high payload capacity while maintaining the structural integrity and readability of the QR code. By leveraging the inherent redundancy of the QR code matrix, this technique imperceptibly encodes hidden data and resists various forms of image processing attacks. Performance is evaluated based on data capacity, imperceptibility, and robustness to errors. Experimental results demonstrate that the triplet difference method significantly outperforms traditional data hiding techniques in terms of efficiency and security. This study highlights the potential applications of the triplet difference method in secure information sharing, digital watermarking, and authentication, paving the way for advanced data hiding techniques that enhance the security and practicality of QR code technology.

关键词： visualization Privacy Redundancy information sharing Authentication QR codes Watermarking Resists Robustness Payloads

来源：评论

学校读者我要写书评

暂无评论

Development of a Collaborative Design Platform Based on Bim (Building information Modeling) and Cloud Computing

Development of a Collaborative Design Platform Based on Bim ...

引用

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

作者： Zekun Chang Shandong Vocational College of Industry Zibo China

ISBN: (数字)9798350389579

ISBN: (纸本)9798350389586

This study proposes a collaborative design platform based on BIM and cloud computing, combined with an innovative real-time synchronization algorithm, to solve the problems of delay, data consistency and synchronization conflict in cloud collaborative design. The proposed real-time synchronization algorithm is based on a distributed computing model. By introducing a distributed lock and timestamp mechanism, it effectively guarantees the data consistency and real-time performance in large-scale collaborative design, and can reduce data conflicts and improve collaborative efficiency when multiple design teams operate in parallel. In order to verify the effectiveness of the platform, this study conducted experiments in multiple architectural design projects, and the platform runs in mainstream cloud computing environments (such as AWS and Azure). The experimental results show that the collaborative design platform based on the innovative algorithm has significant advantages over traditional collaborative design tools in terms of synchronization delay, data transmission speed and number of concurrent users. When multiple design teams collaborate, the design cycle of the platform is shortened by 15 %, the overall work efficiency is improved by more than 20 %, and it can maintain stability and low response time in a high concurrent user environment. In addition, the platform's real-time rendering and version control mechanism also significantly improve the design quality and accuracy.

关键词： Cloud computing visualization Computational modeling Buildings Collaboration Distributed databases Real-time systems Delays Synchronization Security

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 << < 35 36 37 38 39 40 41 42 43 44 > >>

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：