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

8,212 篇 会议
158 篇 期刊文献
36 册 图书

馆藏范围

8,405 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

5,774 篇 工学
- 5,035 篇 计算机科学与技术...
- 3,598 篇 软件工程
- 1,534 篇 光学工程
- 865 篇 信息与通信工程
- 662 篇 电气工程
- 641 篇 控制科学与工程
- 501 篇 机械工程
- 449 篇 生物医学工程（可授...
- 372 篇 电子科学与技术（可...
- 349 篇 生物工程
- 237 篇 仪器科学与技术
- 119 篇 化学工程与技术
- 101 篇 建筑学
- 92 篇 土木工程
- 71 篇 安全科学与工程
- 57 篇 材料科学与工程（可...
- 51 篇 交通运输工程
3,196 篇 理学
- 1,979 篇 物理学
- 1,901 篇 数学
- 578 篇 统计学（可授理学、...
- 408 篇 生物学
- 126 篇 化学
- 57 篇 系统科学
486 篇 管理学
- 327 篇 图书情报与档案管...
- 175 篇 管理科学与工程(可...
- 55 篇 工商管理
424 篇 医学
- 407 篇 临床医学
- 105 篇 基础医学(可授医学...
- 79 篇 药学(可授医学、理...
54 篇 艺术学
- 53 篇 设计学（可授艺术学...
53 篇 农学
45 篇 法学
27 篇 教育学
18 篇 经济学
11 篇 军事学
5 篇 文学

主题

1,328 篇 image processing
1,100 篇 computer vision
894 篇 image segmentati...
663 篇 pattern recognit...
538 篇 image reconstruc...
515 篇 image analysis
501 篇 cameras
452 篇 layout
375 篇 shape
366 篇 computer science
317 篇 feature extracti...
268 篇 face recognition
264 篇 image recognitio...
260 篇 robustness
243 篇 humans
202 篇 pixel
200 篇 image edge detec...
192 篇 object recogniti...
189 篇 object detection
188 篇 pattern recognit...

机构

23 篇 department of co...
20 篇 microsoft resear...
17 篇 center for autom...
16 篇 the robotics ins...
15 篇 national laborat...
15 篇 institute of ima...
15 篇 institute of ima...
15 篇 department of co...
15 篇 institute of com...
14 篇 department of co...
14 篇 tsinghua univers...
14 篇 school of comput...
14 篇 nec research ins...
14 篇 school of comput...
13 篇 robotics institu...
13 篇 institute for ro...
12 篇 computer science...
11 篇 carnegie mellon ...
11 篇 swiss fed inst t...
11 篇 inria sophia-ant...

作者

31 篇 anon
27 篇 huang thomas s.
25 篇 jain anil k.
24 篇 s.k. nayar
22 篇 nayar shree k.
22 篇 haralick robert ...
19 篇 timofte radu
18 篇 shum heung-yeung
18 篇 aggarwal j.k.
17 篇 zhang lei
17 篇 hancock edwin r.
16 篇 van gool luc
15 篇 g. healey
14 篇 davis larry s.
14 篇 rosenfeld azriel
14 篇 t. kanade
14 篇 r. szeliski
14 篇 ahuja narendra
13 篇 k. ikeuchi
13 篇 chellappa rama

语言

8,192 篇 英文
126 篇 其他
87 篇 中文
3 篇 土耳其文
1 篇 西班牙文
1 篇 葡萄牙文

检索条件"任意字段=Proceedings - IEEE Computer Society Conference on Pattern Recognition and Image Processing."

共 8406 条记录，以下是401-410 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 and Adversarial: Improve ASR with Speaker Labels 48

Enhancing and Adversarial: Improve ASR with Speaker Labels

引用

48th ieee International conference on Acoustics, Speech and Signal processing. ICASSP 2023

作者： Zhou, Wei Wu, Haotian Xu, Jingjing Zeineldeen, Mohammad Luscher, Christoph Schluter, Ralf Ney, Hermann Rwth Aachen University Human Language Technology and Pattern Recognition Computer Science Department Aachen52074 Germany AppTek GmbH Aachen52062 Germany

ISBN: (纸本)9781728163277

ASR can be improved by multi-task learning (MTL) with domain enhancing or domain adversarial training, which are two opposite objectives with the aim to increase/decrease domain variance towards domain-aware/agnostic ASR, respectively. In this work, we study how to best apply these two opposite objectives with speaker labels to improve conformer-based ASR. We also propose a novel adaptive gradient reversal layer for stable and effective adversarial training without tuning effort. Detailed analysis and experimental verification are conducted to show the optimal positions in the ASR neural network (NN) to apply speaker enhancing and adversarial training. We also explore their combination for further improvement, achieving the same performance as i-vectors plus adversarial training. Our best speaker-based MTL achieves 7% relative improvement on the Switchboard Hub5'00 set. We also investigate the effect of such speaker-based MTL w.r.t. cleaner dataset and weaker ASR NN. © 2023 ieee.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors

PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-...

引用

conference on computer Vision and pattern recognition (CVPR)

作者： Haley M. So Laurie Bose Piotr Dudek Gordon Wetzstein Stanford University The University of Manchester

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Conventional image sensors digitize high-resolution images at fast frame rates, producing a large amount of data that needs to be transmitted off the sensor for fur-ther processing. This is challenging for perception system operating on edge devices, because communication is power inefficient and induces latency. Fueled by innovations in stacked image sensor fabrication, emerging sensor-processors offer programmability and processing.capabilities directly on the sensor. We exploit these capabilities by developing an efficient recurrent neural network architecture, PixelRNN, that encodes spatio-temporal features on the sensor using purely binary operations. PixelRNN reduces the amount of data to be transmitted off the sensor by factors up to 256 compared to the raw sensor data while offering competitive accuracy for hand gesture recognition and lip reading tasks. We experimentally validate PixelRNN using a prototype implementation on the SCAMP-5 sensor-processor platform.

关键词： image sensors Fabrication Technological innovation Recurrent neural networks Lips image edge detection Prototypes

来源：评论

学校读者我要写书评

暂无评论

VISUAL REPRESENTATION LEARNING WITH SELF-SUPERVISED ATTENTION FOR LOW-LABEL HIGH-DATA REGIME 47

VISUAL REPRESENTATION LEARNING WITH SELF-SUPERVISED ATTENTIO...

引用

2022 ieee International conference on Acoustics, Speech and Signal processing. ICASSP 2022

作者： Bhattacharyya, Prarthana Li, Chenge Zhao, Xiaonan Fehérvári, István Sun, Jason University of Waterloo Amazon Inc Canada

ISBN: (纸本)9781665405409

Self-supervision has shown outstanding results for natural language processing. and more recently, for image recognition. Simultaneously, vision transformers and its variants have emerged as a promising and scalable alternative to convolutions on various computer vision tasks. In this paper, we are the first to question if self-supervised vision transformers (SSL-ViTs) can be adapted to two important computer vision tasks in the low-label, high-data regime: few-shot image classification and zero-shot image retrieval. The motivation is to reduce the number of manual annotations required to train a visual embedder, and to produce generalizable and semantically meaningful embeddings. For few-shot image classification we train SSL-ViTs without any supervision, on external data, and use this trained embedder to adapt quickly to novel classes with limited number of labels. For zero-shot image retrieval, we use SSL-ViTs pre-trained on a large dataset without any labels and fine-tune them with several metric learning objectives. Our self-supervised attention representations outperforms the state-of-the-art on several public benchmarks for both tasks, namely miniimageNet and CUB200 for few-shot image classification by up-to 6%-10%, and Stanford Online Products, Cars196 and CUB200 for zero-shot image retrieval by up-to 4%-11%. Code is available at https://***/AutoVision-cloud/SSL-ViT-lowlabel-highdata. © 2022 ieee

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Road Condition Detection and Crowdsourced Data Collection for Accident Prevention: A Deep Learning Approach 12

Road Condition Detection and Crowdsourced Data Collection fo...

引用

12th International conference on image processing.Theory, Tools and Applications, IPTA 2023

作者： Jahan, Md Saroar Islam, Mominul Hossain, Md Sanjid Kabir Mim, Jhuma Oussalah, Mourad Akter, Nasrin Oulu Finland Daffodil International University Dept. of Cse Dhaka Bangladesh Lut Univerity Computer Vision and Pattern Recognition Lappeenranta Finland University of Oulu Cmvs Faculty of Itee Oulu Finland

ISBN: (纸本)9798350325416

Bangladesh is one of the countries struggling to prevent road accidents, which is a global cause for concern. An early warning system that indicates road conditions can contribute to the prevention task. For this purpose, a deep-learning based approach using a Convolutional Neural Network (CNN) to learn from random road images the safety factor is developed. This results in a three-class categorization: (i) Severely risky roads, (ii) Mildly risky roads, and (iii) Normal roads. The application of deep learning techniques in this study yields an accuracy of 95.5% in detecting problematic road conditions. Furthermore, based on the study's findings, a mobile application has been developed. The app enables real-time crowdsourced data collection of road conditions and provides a platform for users to share this information in real-time with other drivers, thereby, contributing to prevent accidents and raise awareness among drivers and users by pinpointing the location of the risky road. Finally, crowdsourced data has been reused to update the trained model, which further improves the classifier accuracy. © 2023 ieee.

关键词： Safety factor

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Distortion Sensitivity Prediction for Full-Reference image Quality Assessment

Deep Learning-based Distortion Sensitivity Prediction for Fu...

引用

ieee/CVF conference on computer Vision and pattern recognition (CVPR)

作者： Ahn, Sewoong Choi, Yeji Yoon, Kwangjin SI Analyt 441 Expo Ro Daejeon South Korea

ISBN: (纸本)9781665448994

Previous full-reference image quality assessment methods aim to evaluate the quality of images impaired by traditional distortions such as JPEG, white noise, Gaussian blur, and so on. However, there is a lack of research measuring the quality of images generated by various image processing.algorithms, including super-resolution, denoising, restoration, etc. Motivated by the previous model that predicts the distortion sensitivity maps, we use the DeepQA as a baseline model on a challenge database that includes various distortions. We have further improved the baseline model by dividing it into three parts and modifying each: 1) distortion encoding network, 2) sensitivity generation network, and 3) score regression. Through rigorous experiments, the proposed model achieves better prediction accuracy on the challenge database than other methods. Also, the proposed method shows better visualization results compared to the baseline model. We submitted our model in NTIRE 2021 Perceptual image Quality Assessment Challenge and won 12th in the main score.

关键词： image quality Visualization Sensitivity Databases Superresolution Transform coding Predictive models

来源：评论

学校读者我要写书评

暂无评论

Weighted Multi-Kernel Prediction Network for Burst image Super-Resolution

Weighted Multi-Kernel Prediction Network for Burst Image Sup...

引用

ieee/CVF conference on computer Vision and pattern recognition (CVPR)

作者： Cho, Wooyeong Son, Sanghyeok Kim, Dae-Shik Korea Adv Inst Sci & Technol Daejeon South Korea

ISBN: (纸本)9781665448994

Burst image super-resolution is an ill-posed problem tha' aims to restore a high-resolution (HR) image from a sequence of low-resolution (LR) burst images. To restore a photo-realistic HR image using their abundant information, it is essential to align each burst of frames containing random hand-held motion. Some kernel prediction networks (KPNs) that are operated without external motion compensation such as optical flow estimation have been applied to burst image processing.as implicit image alignment modules. However, the existing methods do not consider the interdependencies among the kernels of different sizes that have a significant effect on each pixel. In this paper, we propose a novel weighted multi-kernel prediction network (WMKPN) that can learn the discriminative features on each pixel for burst image super-resolution. Our experimental results demonstrate that WMKPN improves the visual quality of super-resolved images. To the best of our knowledge, it outperforms the state-of-the-art within kernel prediction methods and multiple frame super-resolution (MFSR) on both the Zurich RAW to RGB and BurstSR datasets.

关键词： Visualization Computational modeling Superresolution Prediction methods Motion compensation image restoration pattern recognition

来源：评论

学校读者我要写书评

暂无评论

StGAN: A Novel Symbolic Signal Decomposition Base on GANs and Swin Transformer

StGAN: A Novel Symbolic Signal Decomposition Base on GANs an...

引用

2023 ieee International conference on Systems, Man, and Cybernetics, SMC 2023

作者： Sun, Ming Guo, Li Chen, Long The College of Computer Science & Technology Qingdao University Qingdao China University of Macau Faculty of Science and Technology Macau China

ISBN: (纸本)9798350337020

The symbolic imagery signal decomposition is a common problem in digital signal processing. Its main purpose is to divide the symbolic imagery signal into different parts. However, in real-world applications, symbolic imagery signal captured by the camera is usually influenced by complex negative lighting environments such as highlights, reflections, drop shadows, or information loss. To overcome those problems, a generative adversarial network with Swin Transformer (StGAN) is proposed and applied to symbolic imagery signal decomposition and semantic segmentation tasks. In addition, a realistic image dataset taken in complex lighting conditions is proposed for symbolic imagery signal decomposition, which have complex lighting environments and edge information loss, we name it the MLT dataset. We demonstrate StGAN brings significant improvements in performance than some existing methods in the accuracy of symbolic imagery signal decomposition on MLT datasets. Further experiments on Sky and Facades datasets prove that StGAN works well in other tasks, especially when fewer data is involved in training, but it can still ensure good accuracy. © 2023 ieee.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review on Deep Learning based Medical image processing

Review on Deep Learning based Medical Image Processing

引用

2022 ieee International conference on Current Development in Engineering and Technology, CCET 2022

作者： Agarwal, Aman Kumar, Rakesh Gupta, Meenu Computer Science and Engineering Chandigarh University Karnataka India

ISBN: (纸本)9781665454155

Deep learning (DL) has made extensive progress in many exploration regions. computer vision is one of the most trending fields advancing due to extensive research in developing DL models, mainly focusing on image pattern recognition. These days, numerous specialists attempt to track down answers for issues in different fields under the illumination of DL techniques. In this review, important information is added about DL models and testing points specialists can use in DL. This study explored DL and concentrates on what advancements are made in the most famous fields, for example, Medical image segmentation, automated disease classification, 4D Motion Estimation, etc. Moreover, this study discusses the leftover difficulties of these examination regions that DL can tackle and talks about future subjects to help scientists, especially in handling Medical images. © 2022 ieee.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Single image haze removal using sharpness evaluation index

Single image haze removal using sharpness evaluation index

引用

2022 International conference on image, Signal processing. and pattern recognition, ISPP 2022

作者： YiGuo, Huang HuaRong, Xu WenLong, Zhu LiFen, Weng Xiamen University of Technology Computer and Information Engineering Xiamen361024 China Xiamen University of Technology School of Design Art 361024 China Engineering Research Center for ICH Digitalization and Multi-source Information Fusion [Fujian Polytechnic Normal University Fujian Province University 350300 China

ISBN: (纸本)9781510654846

In order to reproduce clear scenes of visible light images in hazy weather, and effectively suppress the image contrast and clarity degradation caused by haze degradation. General defogging methods do not take into account the uneven distribution of fog concentration and defog the whole image directly. Outdoor scenes of defogging is required to take into account the distribution of fog concentration. In this paper, a natural image defogging method for clarity evaluation indicators is proposed. We select representative indicators for fog concentration classification based on depth information and also obtain global transmittance maps. Compared with traditional method and the deep learning defogging method, The results outperform the other algorithms in different metrics. Experiments show that our results outperform other algorithms in various metrics and are robust to inhomogeneous fog. © 2022 SPIE.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

An Improved image Dehazing method Based on Dark Channel Compensation and Guided Filtering

An Improved Image Dehazing method Based on Dark Channel Comp...

引用

2022 International conference on image, Signal processing. and pattern recognition, ISPP 2022

作者： Liu, Yueyuan Zhai, Yishu School of Science Tianjin University of Technology and Education Tianjin300222 China

ISBN: (纸本)9781510654846

image dehazing is an important topic in the field of computer vision. The traditional single image dehazing algorithm is susceptible to the serious halo phenomenon and color distortion. For this problem, an improved method for single image dehazing based on dark channel prior and guided filtering is proposed in this paper. Aiming at the problems of halo phenomenon by traditional dark channel prior, a compensation model was proposed firstly. This model identified halo regions by the differential operation on the two minimal filtered images and adjusted the filtering window scale to a more suitable value. Secondly, rough transmittance correction combined with sky area judgement was applied aiming at color degradation caused by serious cover influence of fog and haze. Finally, the guided filter algorithm was improved for optimal transmittance by locating edge points with Canny operator and modifying the smoothing factor in loss function with the ratio of the gradient operator to window gradient mean as edge weight. The experimental results demonstrate that the proposed algorithm can efficiently remove halo effects and keep more details whatever in near or far regions, as well as improving visual effects and color saturation of images. Objective experiment evaluations also verify the effectiveness of proposed algorithm. © 2022 SPIE.

关键词： Demulsification

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 << < 37 38 39 40 41 42 43 44 45 46 > >>

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：