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

15,854 篇 会议
360 篇 期刊文献
193 册 图书

馆藏范围

16,407 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,314 篇 工学
- 5,413 篇 计算机科学与技术...
- 2,985 篇 软件工程
- 2,163 篇 电气工程
- 1,860 篇 信息与通信工程
- 1,123 篇 控制科学与工程
- 880 篇 光学工程
- 644 篇 机械工程
- 637 篇 电子科学与技术（可...
- 539 篇 生物医学工程（可授...
- 538 篇 仪器科学与技术
- 477 篇 生物工程
- 225 篇 测绘科学与技术
- 217 篇 交通运输工程
- 201 篇 材料科学与工程（可...
- 199 篇 航空宇航科学与技...
- 163 篇 化学工程与技术
- 159 篇 网络空间安全
- 140 篇 安全科学与工程
4,005 篇 理学
- 2,390 篇 物理学
- 1,355 篇 数学
- 527 篇 生物学
- 367 篇 统计学（可授理学、...
- 341 篇 系统科学
- 205 篇 化学
1,521 篇 医学
- 1,348 篇 临床医学
- 200 篇 特种医学
- 197 篇 基础医学(可授医学...
1,054 篇 管理学
- 612 篇 管理科学与工程(可...
- 481 篇 图书情报与档案管...
- 139 篇 工商管理
84 篇 法学
66 篇 农学
45 篇 经济学
43 篇 教育学
37 篇 军事学
32 篇 文学
26 篇 艺术学
1 篇 哲学

主题

2,779 篇 image processing
1,551 篇 image segmentati...
1,513 篇 signal processin...
867 篇 feature extracti...
656 篇 image edge detec...
634 篇 cameras
633 篇 signal processin...
609 篇 real-time system...
575 篇 image reconstruc...
517 篇 image coding
498 篇 algorithm design...
399 篇 clustering algor...
398 篇 deep learning
398 篇 image color anal...
381 篇 object detection
369 篇 image enhancemen...
354 篇 accuracy
334 篇 hardware
323 篇 image analysis
312 篇 computer vision

机构

39 篇 xi'an jiaotong u...
32 篇 northwestern pol...
31 篇 xi an jiao tong ...
31 篇 school of electr...
29 篇 school of electr...
26 篇 university of ch...
24 篇 xi an jiao tong ...
23 篇 national laborat...
22 篇 xi an jiao tong ...
21 篇 signal and image...
19 篇 samara national ...
18 篇 xidian universit...
16 篇 school of inform...
16 篇 institute of art...
15 篇 department of el...
15 篇 school of automa...
15 篇 national key lab...
15 篇 school of comput...
14 篇 tsinghua univers...
14 篇 school of electr...

作者

39 篇 chen xi
29 篇 xi chen
24 篇 nanning zheng
24 篇 licheng jiao
20 篇 li xi
20 篇 liu ying
18 篇 xuelong li
17 篇 anon
14 篇 xi ning
14 篇 wei li
14 篇 yuan yuan
14 篇 xi li
13 篇 de-shuang huang
13 篇 yanning zhang
12 篇 jie yang
12 篇 yang xi
12 篇 ying liu
11 篇 p. pirsch
11 篇 liu yang
11 篇 mingyi he

语言

16,103 篇 英文
159 篇 其他
132 篇 中文
20 篇 土耳其文
3 篇 葡萄牙文
2 篇 法文
2 篇 俄文
1 篇 西班牙文

检索条件"任意字段=Conference on Image Processing - Algorithms and Systems XI"

共 16407 条记录，以下是841-850 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：

Efficient Equivariant Transfer Learning from Pretrained Models 37

Efficient Equivariant Transfer Learning from Pretrained Mode...

引用

37th conference on Neural Information processing systems (NeurIPS)

作者： Basu, Sourya Katdare, Pulkit Sattigeri, Prasanna Chenthamarakshan, Vijil Driggs-Campbell, Katherine Das, Payel Varshney, Lav R. Univ Illinois Champaign IL 61820 USA IBM Res Yorktown Hts NY USA

ISBN: (纸本)9781713899921

Efficient transfer learning algorithms are key to the success of foundation models on diverse downstream tasks even with limited data. Recent works of Basu et al. (2023) and Kaba et al. (2022) propose group averaging (equitune) and optimization-based methods, respectively, over features from group-transformed inputs to obtain equivariant outputs from non-equivariant neural networks. While Kaba et al. (2022) are only concerned with training from scratch, we find that equitune performs poorly on equivariant zero-shot tasks despite good finetuning results. We hypothesize that this is because pretrained models provide better quality features for certain transformations than others and simply averaging them is deleterious. Hence, we propose lambda-equitune that averages the features using importance weights, lambda s. These weights are learned directly from the data using a small neural network, leading to excellent zero-shot and finetuned results that outperform equitune. Further, we prove that lambda-equitune is equivariant and a universal approximator of equivariant functions. Additionally, we show that the method of Kaba et al. (2022) used with appropriate loss functions, which we call equizero, also gives excellent zero-shot and finetuned performance. Both equitune and equizero are special cases of lambda-equitune. To show the simplicity and generality of our method, we validate on a wide range of diverse applications and models such as 1) image classification using CLIP, 2) deep Q-learning, 3) fairness in natural language generation (NLG), 4) compositional generalization in languages, and 5) image classification using pretrained CNNs such as Resnet and Alexnet.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Multi-stage image Deraining based on Pre-trained Diffusion Model 6

Multi-stage Image Deraining based on Pre-trained Diffusion M...

引用

6th ACM International conference on Multimedia in Asia, MMAsia 2024

作者： Zeng, xiong Jiang, Min Huang, RongHua School of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan China

ISBN: (纸本)9798400712739

image deraining typically involves synthesizing low-quality degraded data for training using a predefined degraded model of a single weather condition. While in real world scenarios, varying rain intensities result in different sizes and densities of raindrops and rain streaks, increasing the complexity of image degradation. In this paper, we proposed a multi-stage deraining framework based on pre-trained diffusion model, it can efficiently perform the rain removal task under a variety of weather situations. We diffuse degraded images into a noisy state where various types of degradation are transformed into Gaussian noise. Then, during the denoising process, the low-frequency information of the image is replaced through iterative refinement, guiding the pre-trained diffusion model for image reconstruction. Our method effectively utilizes the generative priors in diffusion models and avoid the computational burden of retraining conditional diffusion models. Experimental results on four rainy degradation image datasets show its robustness to different types and severities of degradation (such as raindrops and rain streaks). Compared to recent deraining algorithms, our method achieves a maximum improvement of 0.96 dB (3.5%) in PSNR and 0.021 dB (2.7%) in SSIM for the restored images. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

A PROPER ORTHOGONAL DECOMPOSITION APPROACH FOR PARAMETERS REDUCTION OF SINGLE SHOT DETECTOR NETWORKS 29

A PROPER ORTHOGONAL DECOMPOSITION APPROACH FOR PARAMETERS RE...

引用

IEEE International conference on image processing (ICIP)

作者： Meneghetti, Laura Demo, Nicola Rozza, Gianluigi SISSA Math Area MathLab Via Bonomea 265 I-34136 Trieste Italy

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

As a major breakthrough in artificial intelligence and deep learning, Convolutional Neural Networks have achieved an impressive success in solving many problems in several fields including computer vision and image processing. Real-time performance, robustness of algorithms and fast training processes remain open problems in these contexts. In addition object recognition and detection are challenging tasks for resource-constrained embedded systems, commonly used in the industrial sector. To overcome these issues, we propose a dimensionality reduction framework based on Proper Orthogonal Decomposition, a classical model order reduction technique, in order to gain a reduction in the number of hyperparameters of the net. We have applied such framework to SSD300 architecture using PASCAL VOC dataset, demonstrating a reduction of the network dimension and a remarkable speedup in the fine-tuning of the network in a transfer learning context.

关键词： image processing Object Detection Dimensionality Reduction Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

Design of Cloud Platform for Efficient Remote Sensing Big Data processing Based on Open Stack

Design of Cloud Platform for Efficient Remote Sensing Big Da...

引用

Integrated Intelligence and Communication systems (ICIICS), International conference on

作者： Yan Huang Weimeng Zhang Xi’an Traffic Engineering Institute Xi’an Shaanxi China Xi’an Technical School Xi’an Shaanxi China

The rapid preparation of computing resources is an important step to realize efficient remote sensing image processing. It takes a lot of time for researchers to prepare hardware resources and deploy computing framework. It often mistakes in the preparation and careless deployment of the framework which can lead to high research costs. To solve this problem, this paper uses Open Stack to virtualize hardware resources and uses Linux Shell scripting language to quickly prepare and deploy the Spark parallel computing environment. In this paper, based on the remote sensing image change detection method of connection condition, for example, the data processing algorithm in advance import platform algorithms library, component library, used to support the remote sensing image change detection of business flow of creation and recognition, resources rapid preparation, execution and presentation of the results of the algorithm and implement of massive remote sensing image change detection and efficient. It effectively improves the efficiency of remote sensing data management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI Mediated Surface Waste Auto-Detection on Water Bodies Using Cutting Edge Technology

AI Mediated Surface Waste Auto-Detection on Water Bodies Usi...

引用

2024 IEEE International conference on Cognitive Computing and Complex Data

作者： Choudhary, Vijaya Guha, Paramita Archana Dey, Sharmistha IILM Univ Sch Comp Sci & Engn Plot 16-18Knowledge Pk 2 Greater Noida Uttar Pradesh India Acad Sci & Innovat Res AcSIR CSIR Natl Phys Lab Dr KS Kushnan Marg New Delhi India OP Jindal Global Univ Sonipat India Galgotias Univ Sch Comp Sci & Applicat Greater Noida India

ISBN: (纸本)9798350352900;9798350352894

The proliferation of surface waste in water bodies poses significant environmental and ecological challenges. Traditional methods of waste detection are often labor-intensive and limited in scope. This paper presents a novel approach to surface waste detection using artificial intelligence (AI) and advanced imaging technologies. Leveraging cutting-edge techniques such as deep learning algorithms, high-resolution satellite imagery, and real-time data processing, our system offers an automated solution for identifying and monitoring waste in water bodies. We developed a robust AI model trained on diverse datasets, including satellite and drone-captured images, to detect various types of surface waste with high accuracy. The system integrates real-time processing capabilities to provide timely alerts and actionable insights for environmental management. Evaluation results demonstrate that our approach significantly improves detection accuracy and operational efficiency compared to conventional methods. This research contributes to the advancement of smart environmental monitoring systems and offers a scalable solution for mitigating the impact of surface waste on aquatic ecosystems.

关键词： Artificial Intelligence Garbage detections Convolutional neural network river research image processing computer vision

来源：评论

学校读者我要写书评

暂无评论

Optimizing FPGA Hardware Design for Temporal Filtering of High-Definition Video

Optimizing FPGA Hardware Design for Temporal Filtering of Hi...

引用

International conference on Computers, Communications, and systems (ICCCS)

作者： xingjian Fu College of Electrical and Electronic Engineering University of Nottingham Nottingham United Kingdom

ISBN: (数字)9798350350210

ISBN: (纸本)9798350350227

In daily life, noise reduction is an inevitable aspect of video or image processing because noise can affect the subjective quality of viewing. Therefore, video denoising filtering is a crucial operation in video image processing. Among various denoising methods, motion-compensated temporal filtering is a typical and effective filtering technique. However, there is still room for further research in the hardware implementation of this method. Hence, this paper investigates the Multi-hypothesis Motion-Compensated Filter algorithm and proposes an efficient hardware structure for the filtering algorithm. By parallelizing or pipelining various modules, hardware efficiency is effectively improved. By FPGA evaluation, the final experiments demonstrate that the hardware structure for motion-compensated temporal weighted filtering presented in this paper can meet the requirements of video denoising filtering with a resolution of 1920xl080@60fps.

关键词： Filtering Communication systems image processing Noise reduction Noise Filtering algorithms Hardware

来源：评论

学校读者我要写书评

暂无评论

Color Texture image Recognition based on Deep Learning 2

Color Texture Image Recognition based on Deep Learning

引用

2nd IEEE International conference on Electronic Technology, Communication and Information, ICETCI 2022

作者： xiao, Shuping College of Engineering Technology Xi'an Fanyi University Shaanxi Xi'an710105 China

ISBN: (数字)9781728181158

ISBN: (纸本)9781728181158

Traditional image recognition mainly preprocesses the image based on the basic characteristics of the image, and then classifies the image after processing, but the whole process is complicated and requires a lot of resources to be invested, and the recognition effect may not meet people's expectations. The introduction of deep learning (DL) algorithms has further improved the efficiency of texture image recognition, and can also improve the time-consuming and labor-intensive shortcomings of traditional image recognition (IR). Deep learning imitates the hierarchical structure of the human brain neural network, removing invalid information layer by layer from the input information, and extracting effective information. Applying DL to the field of IR can achieve better target feature extraction and higher classification accuracy, and further improve the accuracy of image recognition. © 2022 IEEE.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Improving image Clarity with Artificial Intelligence-Powered Super-Resolution Methods 1

引用

3rd International conference on Mechanical and Energy Technologies, ICMET 2023

作者： Malathy, V. Poornima, M. Varun, V.L. Venugopal, Padmaja Acharjee, Purnendu Bikash Krishnaveni, S. School of Engineering SR University Telangana Warangal India Department of Mathematics SJB Institute of Technology Bengaluru India Computer Science CHRIST University Pune Lavasa Campus Lavasa India Department of Management Studies Adithya Institute of Technology Coimbatore Kovilpalayam India

ISBN: (数字)9789819727162

ISBN: (纸本)9789819727155

Super-resolution has advanced significantly in the last 20 years, particularly with the application of deep learning methods. One of the most important image processing methods for boosting an image's resolution in computer vision is image super-resolution besides providing an extensive overview of the most recent developments in artificial intelligence and deep learning for single-image super-resolution. This study delves into the subject of image enhancement by investigating sophisticated AI-based super-resolution techniques. High-quality photographs have become more and more in demand in a variety of industries recently, including medical imaging, satellite imaging, entertainment, and surveillance. Pixilation reduction and detail preservation are two areas where traditional image enhancing techniques fall short. Artificial intelligence has demonstrated amazing promise in addressing these issues, especially with regard to Deep Learning models. The applications, benefits, and difficulties of modern super-resolution techniques are thoroughly examined in this work. We also suggest new approaches and push the limits of image enhancement by experimenting with state-of-the-art artificial intelligence algorithms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

ETSS-Net: A one-stage detection model for infrared small target images based on efficient transformer and scale sequence attention mechanism

ETSS-Net: A one-stage detection model for infrared small tar...

引用

2024 conference on Spectral Technology and Applications, CSTA 2024

作者： Shi, Jingcheng Li, Jiaxing Jiang, Zhiwei Zhang, Shu Song, Ningning Chen, Shiguo Wei, Liping School of Chemical Engineering Northwest University Shaanxi Xi'an China People's Liberation Army Unit 93213 Beijing China School of Physics Xidian University Shaanxi Xi'an China

ISBN: (纸本)9781510683082

Infrared small target detection is crucial in various applications, such as nighttime vessel inspection, disaster warning systems, and others. Compared with traditional object detection tasks, infrared scenes present distinctive challenges. First of all, due to the target's distance or shape, the proportion of the target is exceedingly small and the information of the background is complex. Generally, the target comprises a few pixels in extreme cases. Second, the targets in infrared detection tasks are typically sparsely distributed and low contrast contains only a few instances, each of object occupies a minuscule portion of the entire infrared image. Meanwhile, the processing system has high requirements for real-time and multi-frame performance is difficult to achieve. In order to solve the above problems, we proposed a novel Detection Transformer network (DETR) for infrared images, which integrates the efficient transformer and a novel scale sequence attention mechanism (ETSS-Net). The contributions of this work can be summarized as follows: (1) with the success of Transformers in computer vision tasks, recent studies try to optimize the complexity of Transformers in the detection tasks. However, the variants of the Transformers still have higher considerably parameters than some lightweight convolutional neural networks. According to this idea, we designed a self-attention Transformer block, which we called Frequency-based Intra-scale Feature Interaction (FIFI). It is inspired by the interaction and expression of frequency information between image pixels. (2) Second, we propose a plug-and-play dimension scale selection module (DSSM) to maintain the balance between detection speed, effect, and the number of parameters and to make the proposed SLAM improve the performance of detection model, and it can simultaneously incorporate both spatial and channel information in the training processing, as well as local and global information. (3) The proposed ETSS-Net im

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

ColJailBreak: Collaborative Generation and Editing for Jailbreaking Text-to-image Deep Generation 38

ColJailBreak: Collaborative Generation and Editing for Jailb...

引用

38th conference on Neural Information processing systems, NeurIPS 2024

作者： Ma, Yizhuo Pang, Shanmin Guo, Qi Wei, Tianyu Guo, Qing School of Software Engineering Xi'an Jiaotong University China IHPC CFAR Agency for Science Technology and Research Singapore

The commercial text-to-image deep generation models (e.g. DALL·E) can produce high-quality images based on input language descriptions. These models incorporate a black-box safety filter to prevent the generation of unsafe or unethical content, such as violent, criminal, or hateful imagery. Recent jailbreaking methods generate adversarial prompts capable of bypassing safety filters and producing unsafe content, exposing vulnerabilities in influential commercial models. However, once these adversarial prompts are identified, the safety filter can be updated to prevent the generation of unsafe images. In this work, we propose an effective, simple, and difficult-to-detect jailbreaking solution: generating safe content initially with normal text prompts and then editing the generations to embed unsafe content. The intuition behind this idea is that the deep generation model cannot reject safe generation with normal text prompts, while the editing models focus on modifying the local regions of images and do not involve a safety strategy. However, implementing such a solution is non-trivial, and we need to overcome several challenges: how to automatically confirm the normal prompt to replace the unsafe prompts, and how to effectively perform editable replacement and naturally generate unsafe content. In this work, we propose the collaborative generation and editing for jailbreaking text-to-image deep generation (ColJailBreak), which comprises three key components: adaptive normal safe substitution, inpainting-driven injection of unsafe content, and contrastive language-image-guided collaborative optimization. We validate our method on three datasets and compare it to two baseline methods. Our method could generate unsafe content through two commercial deep generation models including GPT-4 and DALL·E 2. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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 << < 81 82 83 84 85 86 87 88 89 90 > >>

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：