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

8,227 篇 会议
158 篇 期刊文献
36 册 图书

馆藏范围

8,420 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

5,789 篇 工学
- 5,044 篇 计算机科学与技术...
- 3,605 篇 软件工程
- 1,541 篇 光学工程
- 867 篇 信息与通信工程
- 663 篇 电气工程
- 642 篇 控制科学与工程
- 501 篇 机械工程
- 449 篇 生物医学工程（可授...
- 374 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
- 72 篇 安全科学与工程
- 58 篇 材料科学与工程（可...
- 52 篇 交通运输工程
3,203 篇 理学
- 1,985 篇 物理学
- 1,904 篇 数学
- 579 篇 统计学（可授理学、...
- 408 篇 生物学
- 126 篇 化学
- 57 篇 系统科学
488 篇 管理学
- 329 篇 图书情报与档案管...
- 176 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
28 篇 教育学
18 篇 经济学
11 篇 军事学
5 篇 文学

主题

1,329 篇 image processing
1,100 篇 computer vision
895 篇 image segmentati...
663 篇 pattern recognit...
538 篇 image reconstruc...
515 篇 image analysis
501 篇 cameras
451 篇 layout
374 篇 shape
366 篇 computer science
318 篇 feature extracti...
268 篇 face recognition
263 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

8,151 篇 英文
182 篇 其他
88 篇 中文
3 篇 土耳其文
1 篇 西班牙文
1 篇 日文
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 8421 条记录，以下是541-550 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：

Building Vision-Language Models on Solid Foundations with Masked Distillation

Building Vision-Language Models on Solid Foundations with Ma...

引用

conference on computer Vision and pattern recognition (CVPR)

作者： Sepehr Sameni Kushal Kafle Hao Tan Simon Jenni University of Bern Adobe Research

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Recent advancements in Vision-Language Models (VLMs) have marked a significant leap in bridging the gap between computer vision and natural language processing. However, traditional VLMs, trained through contrastive learning on limited and noisy image-text pairs, often lack the spatial and linguistic understanding to generalize well to dense vision tasks or less common languages. Our approach, Solid Foun-dation CLIP (SF-CLIP), circumvents this issue by implicitly building on the solid visual and language understanding of foundational models trained on vast amounts of unimodal data. SF-CLIP integrates contrastive image-text pretraining with a masked knowledge distillation from large foundational text and vision models. This methodology guides our VLM in developing robust text and image representations. As a result, SF-CLIP shows exceptional zero-shot classification accuracy and enhanced image and text retrieval capabilities, setting a new state of the art for ViT-B/16 trained on YFCC15M and ***, the dense per-patch supervision enhances our zero-shot and linear probe performance in semantic segmentation tasks. A remarkable aspect of our model is its multilingual proficiency, evidenced by strong retrieval results in multiple languages despite being trained predominantly on English data. We achieve all of these improvements without sacrificing the training efficiency through our selective application of masked distillation and the inheritance of teacher word embeddings.

关键词： Training Solid modeling computer vision Visualization Computational modeling Semantic segmentation Buildings

来源：评论

学校读者我要写书评

暂无评论

Sensor Equivariance: A Framework for Semantic Segmentation with Diverse Camera Models

Sensor Equivariance: A Framework for Semantic Segmentation w...

引用

ieee computer society conference on computer Vision and pattern recognition Workshops (CVPRW)

作者： Hannes Reichert Manuel Hetzel Andreas Hubert Konrad Doll Bernhard Sick University of Applied Sciences Aschaffenburg Germany University of Kassel Germany

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Objects are represented differently in projection-based sensors such as cameras depending on sensor resolution, field of view, and distortion, leading to distorted physical and geometric properties. As a result, sensor data processing.depend on these properties. With the large variations of sensors on the market, an equivariant representation and suitable processing.are necessary to become independent of the sensor used. In this work, we propose an extension of conventional image data by an additional channel in which the associated projection properties are encoded. Furthermore, we introduce a SensorConv layer as an extension to the conventional convolution layer. SensorConv enable using projection properties in convolutional neural networks. To that end, we propose an architecture for using the SensorConv layer in the Detectron2 [21] framework. We collected a dataset of equirectangular images for our experiments with the CARLA [3] simulator. To analyze multiple sensor models (i.e., sensor intrinsic), we created an augmentation method to emulate a high variability of sensors from the collected equirectangular panoramas. In our experiment, we show that our method can generalize better across different camera sensors.

关键词： computer vision Convolution Semantic segmentation conferences Cameras Distortion Data processing

来源：评论

学校读者我要写书评

暂无评论

MobileDeRainGAN: An Efficient Semi-Supervised Approach to Single image Rain Removal for Task-Driven Applications

MobileDeRainGAN: An Efficient Semi-Supervised Approach to Si...

引用

ieee computer society conference on computer Vision and pattern recognition Workshops (CVPRW)

作者： Ruphan Swaminathan Pradyot Korupolu Columbia University Ottonomy Inc

Rain removal is an essential task in computer vision, particularly for applications such as autonomous navigation to function seamlessly during rain. However, most existing single-image deraining algorithms are limited by their inability to generalize on diverse real-world rainy images, the need for real-time processing. and the lack of task-driven metric enhancement. This paper proposes MobileDeRainGAN, an efficient semi-supervised algorithm that addresses these challenges. The proposed approach includes a novel latent bridge network and multi-scale discriminator that effectively removes rain-related artifacts at different scales. Our cross-domain experiments on Rain1400 and RainCityscapes datasets demonstrate substantial improvements over state-of-the-art methods in terms of generalization and object detection scores in a semi-supervised setting. Furthermore, our approach is significantly faster and can run in real-time even on edge devices. Overall, our proposed MobileDeRainGAN algorithm offers a significant improvement in rain removal performance on real-world images while being efficient, scalable, and suitable for real-world applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review on Deep Learning Models for Optic Disc Segmentation and Glaucoma Classification

A Review on Deep Learning Models for Optic Disc Segmentation...

引用

2022 ieee World conference on Applied Intelligence and Computing, AIC 2022

作者： Irfana Parveen, C.A. Sunder, R. Satheesh Kumar, R. Sahrdaya College of Engineering and Technology Department of Computer Science and Engineering Kerala India

ISBN: (数字)9781665479882

ISBN: (纸本)9781509050017

Due to the recent existence of large datasets and advancements in processing.capabilities, deep learning has risen to the forefront of artificial intelligence on a variety of tasks, particularly those related to image classification and pattern recognition. Ophthalmology offers a chance to see how deep learning classifiers are used in medicine. Globally, glaucoma is the prime factor of chronic blindness and disability. Despite this, most patients are unsure whether they have glaucoma, and detecting glaucoma progression with present technology is challenging in clinical practice. We can detect glaucoma early with the help of deep learning technology. The segmentation of the optic disc and classification of glaucoma using retinal data will be examined using several deep structured learning approaches in this research. Also presented a basic understanding of deep learning. Finally, the difficulties that deep learning models face are highlighted. © 2022 ieee.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Seven-segment Display Automatic Detection and Interpretation System using CNN-GO 6

Seven-segment Display Automatic Detection and Interpretation...

引用

6th International conference on Green Technology and Sustainable Development, GTSD 2022

作者： Wannachai, Autanan Boonyung, Wanarut Yawootti, Artit Nuangpirom, Pinit Munsin, Ronnachart Rajamangala University of Technology Lanna Chiang Mai Faculty of Engineering Chiang Mai Thailand Chiang Mai University Computer Engineering Chiang Mai Thailand Department of Mechanical Engineering Faculty of Engineering Rajamangala University of Technology Lanna Chiang Mai Chiang Mai Thailand

ISBN: (数字)9781665466288

ISBN: (纸本)9781665466288

In industrial plants, machines and measuring instruments are displayed through a seven-segment display. The machine is operating for more than 20 hours/day. The operator cannot check measurement data or status all the time. In addition, human error affects overall performance and time. This research aims to develop an embedded system for interpreting data from seven segment displays through online image processing. CNN (Convolution Neural Network) is applied in the detection and interpretation process. This paper proposes seven-segment display automatic detection and interpretation system using CNN-GO. An IoT device takes the photo of the measuring instrument's seven-segment display and sends the image to the server. The server interprets an image to numerical data using CNN-GO. Grayscale and Overlapping scanning are applied to increase the accuracy of detection and interpretation of numerical data. © 2022 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Generalized Single-image-Based Morphing Attack Detection Using Deep Representations from Vision Transformer

Generalized Single-Image-Based Morphing Attack Detection Usi...

引用

ieee computer society conference on computer Vision and pattern recognition Workshops (CVPRW)

作者： Haoyu Zhang Raghavendra Ramachandra Kiran Raja Christoph Busch Norwegian University of Science and Technology Norway Darmstadt University of Applied Sciences Germany

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Face morphing attacks have posed severe threats to Face recognition Systems (FRS), which are operated in border control and passport issuance use cases. Correspondingly, morphing attack detection algorithms (MAD) are needed to defend against such attacks. MAD approaches must be robust enough to handle unknown attacks in an open-set scenario where attacks can originate from various morphing generation algorithms, post-processing.and the diversity of printers/scanners. The problem of generalization is further pronounced when the detection has to be made on a single suspected image. In this paper, we propose a generalized single-image-based MAD (S-MAD) algorithm by learning the encoding from Vision Transformer (ViT) architecture. Compared to CNN-based architectures, ViT model has the advantage on integrating local and global information and hence can be suitable to detect the morphing traces widely distributed among the face region. Extensive experiments are carried out on face morphing datasets generated using publicly available FRGC face datasets. Several state-of-the-art (SOTA) MAD algorithms, including representative ones that have been publicly evaluated, have been selected and benchmarked with our ViT-based approach. Obtained results demonstrate the improved detection performance of the proposed S-MAD method on inter-dataset testing (when different data is used for training and testing) and comparable performance on intra-dataset testing (when the same data is used for training and testing) experimental protocol.

关键词： Training computer vision image coding Protocols Statistical analysis Face recognition Digital images

来源：评论

学校读者我要写书评

暂无评论

MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation

MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Corr...

引用

conference on computer Vision and pattern recognition (CVPR)

作者： Yuelong Li Yafei Mao Raja Bala Sunil Hadap Amazon Inc.

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

We propose a single-shot approach to determining 6-DoF pose of an object with available 3D computer-aided design (CAD) model from a single RGB image. Our method, dubbed MRC-Net, comprises two stages. The first performs pose classification and renders the 3D object in the classified pose. The second stage performs regression to predict fine-grained residual pose within class. Connecting the two stages is a novel multi-scale residual correlation (MRC) layer that captures high-and-low level correspondences between the input image and rendering from first stage. MRC-Net employs a Siamese network with shared weights between both stages to learn embeddings for input and rendered images. To mitigate ambiguity when predicting discrete pose class labels on symmetric objects, we use soft probabilistic labels to define pose class in the first stage. We demonstrate state-of-the-art accuracy, outperforming all competing RGB-based methods on four challenging BOP benchmark datasets: T-LESS, LM-O, YCB-V, and ITODD. Our method is non-iterative and requires no complex post-processing. Our code and pretrained models are available at https://***/amzn/mrc-net-6d-pose.

关键词： Solid modeling Three-dimensional displays Design automation Correlation Computational modeling Pose estimation Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Probability-based Global Cross-modal Upsampling for Pansharpening

Probability-based Global Cross-modal Upsampling for Pansharp...

引用

conference on computer Vision and pattern recognition (CVPR)

作者： Zeyu Zhu Xiangyong Cao Man Zhou Junhao Huang Deyu Meng Xi'an Jiaotong University School of Computer Science and Technology Xi'an Jiaotong University Ministry of Education Key Lab For Intelligent Networks and Network Security Xi'an Jiaotong University Nanyang Technological University Macau University of Science and Technology

Pansharpening is an essential preprocessing.step for remote sensing image processing. Although deep learning (DL) approaches performed well on this task, current upsampling methods used in these approaches only utilize the local information of each pixel in the low-resolution multispectral (LRMS) image while neglecting to exploit its global information as well as the cross-modal information of the guiding panchromatic (PAN) image, which limits their performance improvement. To address this issue, this paper develops a novel probability-based global cross-modal upsampling (PGCU) method for pan-sharpening. Precisely, we first formulate the PGCU method from a probabilistic perspective and then design an efficient network module to implement it by fully utilizing the information mentioned above while simultaneously considering the channel specificity. The PGCU module consists of three blocks, i.e., information extraction (IE), distribution and expectation estimation (DEE), and fine adjustment (FA). Extensive experiments verify the superiority of the PGCU method compared with other popular upsampling methods. Additionally, experiments also show that the PGCU module can help improve the performance of existing SOTA deep learning pansharpening methods. The codes are available at https://***/Zeyu-Zhu/PGCU.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Snapshot Spectral Imaging for Face Anti-Spoofing: Addressing Data Challenges with Advanced processing.and Training

Snapshot Spectral Imaging for Face Anti-Spoofing: Addressing...

引用

ieee computer society conference on computer Vision and pattern recognition Workshops (CVPRW)

作者： Hui Li Yaowen Xu Zhaofan Zou Zhixiang He China Telecom Artificial Intelligence Technology Co. Ltd Beijing China

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Although considerable research progress has been made in the field of face anti-spoofing(FAS), it still faces continuous threats from ultra-realistic face mask attacks. Facing the challenge of highly realistic flexible masks, spectral sensors show great potential in enhancing the safety of FAS systems. However, the application of snapshot spectral imaging (SSI) in FAS is still in its infancy and faces two major challenges: data scarcity and data content differences. To this end, we introduce a data processing.and model training method for SSI images. In terms of data processing. we use RandomBorderMask technology and RandomDropChannels strategy to avoid misjudgment of material information, reduce interference from redundant information, and learn from RGB image preprocessing.methods to enhance data diversity. Regarding model training, we propose a model integration strategy and semi-supervised learning technology, which combines the prediction results of multiple models and uses pseudo labels to expand the training data to solve the over-fitting problem caused by data scarcity. These innovative methods achieved first-class results in the 5th Face Anti-Spoofing Challenge @CVPR2024, verifying their effectiveness in improving the accuracy and robustness of the FAS system.

关键词： Training Accuracy Face recognition Imaging Interference Predictive models Semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

Revisiting the Benefits of Knowledge Distillation against Adversarial Examples 6

Revisiting the Benefits of Knowledge Distillation against Ad...

引用

6th International conference on Data Science and Information Technology, DSIT 2023

作者： Li, Jiawen Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350304442

Deep neural networks (DNNs) have always been a popular base model in many image classification tasks. However, some recent works suggest that there are some man made images will easily lead DNNs give wrong predictions. These images are generated by adding some invisible perturbations into clean images, which are the so-called adversarial examples. Since they are almost similar to original data but can fool DNNs, adversarial examples can bring the insecurity to many life-critical applications. Adversarial knowledge distillation is a positive defense method to attach improved robustness to the target DNNs against adversarial examples. In distillation, student models are trained by soft labels coming from robust pre-trained teacher networks. However, it is hard for researchers to ensure that supervised information comes from a better teacher model. In this paper, We focus on four potential factors of the teacher that may have an effect to the distillation performance of student model, and investigate whether and when they can boost the model robustness against adversarial attacks. Multiple quantitative experiment illustrate that these factors have impact on the distillation process and these results can be considered to choose a better teacher model. Further studies can focus on the combination of adversarial knowledge distillation and other defense schemes. Empirical results in this paper may also help select proper teacher in new complex distillation tasks. © 2023 ieee.

关键词： Distillation

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 << < 51 52 53 54 55 56 57 58 59 60 > >>

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：