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

53,097 篇 会议
1,122 篇 期刊文献
10 册 图书

馆藏范围

54,229 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

26,347 篇 工学
- 17,155 篇 计算机科学与技术...
- 9,464 篇 软件工程
- 8,125 篇 电气工程
- 3,795 篇 控制科学与工程
- 2,427 篇 信息与通信工程
- 2,395 篇 机械工程
- 1,900 篇 生物医学工程（可授...
- 1,316 篇 仪器科学与技术
- 1,054 篇 生物工程
- 781 篇 电子科学与技术（可...
- 750 篇 土木工程
- 710 篇 建筑学
- 679 篇 光学工程
- 532 篇 交通运输工程
- 505 篇 测绘科学与技术
- 392 篇 安全科学与工程
4,527 篇 理学
- 1,750 篇 数学
- 1,316 篇 物理学
- 984 篇 生物学
- 699 篇 系统科学
- 434 篇 统计学（可授理学、...
- 404 篇 化学
3,471 篇 管理学
- 2,121 篇 管理科学与工程(可...
- 1,611 篇 图书情报与档案管...
- 770 篇 工商管理
3,104 篇 医学
- 2,684 篇 临床医学
- 754 篇 基础医学(可授医学...
- 361 篇 药学(可授医学、理...
676 篇 教育学
- 662 篇 教育学
515 篇 农学
- 485 篇 作物学
345 篇 法学
190 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

34,753 篇 visualization
7,388 篇 data visualizati...
4,846 篇 training
4,318 篇 feature extracti...
2,961 篇 computational mo...
2,949 篇 three-dimensiona...
2,917 篇 cameras
2,455 篇 computer vision
2,445 篇 semantics
2,073 篇 task analysis
1,940 篇 conferences
1,628 篇 accuracy
1,315 篇 image color anal...
1,302 篇 data mining
1,283 篇 image segmentati...
1,271 篇 navigation
1,203 篇 robustness
1,201 篇 data models
1,158 篇 real-time system...
1,106 篇 measurement

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 ...
31 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
18 篇 yiming li

语言

53,428 篇 英文
560 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 54229 条记录，以下是4391-4400 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：

Multi-Domain Incremental Learning for Semantic Segmentation 22

Multi-Domain Incremental Learning for Semantic Segmentation

引用

22nd ieee/CVF Winter conference on Applications of Computer Vision (WACV)

作者： Garg, Prachi Saluja, Rohit Balasubramanian, Vineeth N. Arora, Chetan Subramanian, Anbumani Jawahar, C., V CVIT IIIT Hyderabad Hyderabad India IIT Hyderabad Hyderabad India IIT Delhi New Delhi India

ISBN: (纸本)9781665409155

Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experiment performed sequentially on three popular road scene segmentation datasets demonstrates that existing segmentation frameworks fail at incrementally learning on a series of visually disparate geographical domains. When learning a new domain, the model catastrophically forgets previously learned knowledge. In this work, we pose the problem of multi-domain incremental learning for semantic segmentation. Given a model trained on a particular geographical domain, the goal is to (i) incrementally learn a new geographical domain, (ii) while retaining performance on the old domain, (iii) given that the previous domain's dataset is not accessible. We propose a dynamic architecture that assigns universally shared, domain-invariant parameters to capture homogeneous semantic features present in all domains, while dedicated domain-specific parameters learn the statistics of each domain. Our novel optimization strategy helps achieve a good balance between retention of old knowledge (stability) and acquiring new knowledge (plasticity). We demonstrate the effectiveness of our proposed solution on domain incremental settings pertaining to realworld driving scenes from roads of Germany (Cityscapes), the United States (BDD100k), and India (IDD).(1)

关键词： visualization Computer vision Roads Semantics Computer architecture Interference Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions

Advancing High-Resolution Video-Language Representation with...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xue, Hongwei Hang, Tiankai Zeng, Yanhong Sun, Yuchong Liu, Bei Yang, Huan Fu, Jianlong Guo, Baining Microsoft Res Asia Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that high-resolution videos and diversified semantics can significantly improve cross-modality learning. In this paper, we propose a novel High-resolution and Diversified VIdeo-LAnguage pre-training model (HDVILA) for many visual tasks. In particular, we collect a large dataset with two distinct properties: 1) the first high-resolution dataset including 371.5k hours of 720p videos, and 2) the most diversified dataset covering 15 popular YouTube categories. To enable VL pre-training, we jointly optimize the HD-VILA model by a hybrid Transformer that learns rich spatiotemporal features, and a multimodal Transformer that enforces interactions of the learned video features with diversified texts. Our pre-training model achieves new state-of-the-art results in 10 VL understanding tasks and 2 more novel text-to-visual generation tasks. For example, we outperform SOTA models with relative increases of 40.4% R@1 in zero-shot MSR-VTT text-tovideo retrieval task, and 55.4% in high-resolution dataset LSMDC. The learned VL embedding is also effective in generating visually pleasing and semantically relevant results in text-to-visual editing and super-resolution tasks.

关键词： visualization Video on demand Computational modeling Superresolution Semantics Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Visual Servo Control of COVID-19 Nasopharyngeal Swab Sampling Robot

Visual Servo Control of COVID-19 Nasopharyngeal Swab Samplin...

引用

ieee/RSJ International conference on Intelligent Robots and Systems (IROS)

作者： Hwang, Guebin Lee, Jongwon Yang, Sungwook Korea Inst Sci & Technol Ctr Intelligent & Interact Robot Seoul 02792 South Korea

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

In this study, we present a visual servo control framework for fully automated nasopharyngeal swab robots. The proposed framework incorporates a deep learning-based nostril detection with a cascade approach to reliably identify the nostrils with high accuracy in real time. In addition, a partitioned visual servoing scheme that combines image-based visual servoing with axial control is formulated for accurately positioning the sampling swabs at the nostril with a multi-DOF robot arm. As the visual servoing is designed to minimize an error between the detected nostril and the swab, it can compensate for potential errors in real operation, such as positioning error by inaccurate camera-robot calibration and kinematic error by unavoidable swab deflection. The performance of the visual servo control was tested on a head phantom model for 30 unused swabs, and then compared with a method referring to only the 3D nostril target for control. Consequently, the swabs reached the nostril target with less than an average error of 1.2 +/- 0.5 mm and a maximum error of 2.0 mm via the visual servo control, while the operation without visual feedback yielded an average error of 10.6 +/- 2.3 mm and a maximum error of 16.2 mm. The partitioned visual servoing allows the swab to rapidly converge to the nostril target within 1.0 s without control instability. Finally, the swab placement at the nostril among the entire procedure of fully automated NP swab was successfully demonstrated on a human subject via the visual servo control.

关键词： visualization Solid modeling Three-dimensional displays Phantoms Kinematics Manipulators Visual servoing

来源：评论

学校读者我要写书评

暂无评论

Network Distribution for Damage Warning System with Cloud-Edge Collaborative Architecture 4

Network Distribution for Damage Warning System with Cloud-Ed...

引用

4th International conference on Digital Data Processing, DDP 2024

作者： Huang, Yiwei Chen, Jingteng Wang, Huan Xie, Zhibin Li, Yunliang Xie, Weiping Zheng, Xianghan State Grid Fujian Electric Power Co. Ltd. Putian Power Supply Company Fujian China Fuzhou University Fujian Fuzhou China Fuzhou Boyun Information Fujian Fuzhou China University of Sanya The Innovation Platform for Academicians of Hainan Province Hainan China

ISBN: (纸本)9798331515706

This paper designs a distribution network external force damage early warning system based on audio classification technology, focusing on the potential damage that large construction machinery might cause to cables. By utilizing audio data, the system can accurately monitor and analyze the real-time status of construction sites to identify potential cable damage activities. Leveraging a cloud-edge collaboration architecture, the system employs cloud-based model training and edge computing technology to achieve real-time monitoring and data processing, thereby enhancing the accuracy and timeliness of warnings. Integrating machine learning algorithms and pattern recognition technology, the system can automatically analyze and predict the impact of construction machinery on cables. Through a visualization system, it provides real-time warnings and response measures, effectively reducing losses caused by external damage and ensuring the safe operation and reliability of the distribution network and power supply. © 2024 ieee.

关键词： Cloud computing architecture

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Image Synthesis with Latent Diffusion Models

High-Resolution Image Synthesis with Latent Diffusion Models

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Rombach, Robin Blattmann, Andreas Lorenz, Dominik Esser, Patrick Ommer, Bjoern Ludwig Maximilian Univ Munich Munich Germany Heidelberg Univ IWR Heidelberg Germany Runway ML New York NY USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization of powerful DMs often consumes hundreds of GPU days and inference is expensive due to sequential evaluations. To enable DM training on limited computational resources while retaining their quality and flexibility, we apply them in the latent space of powerful pretrained autoencoders. In contrast to previous work, training diffusion models on such a representation allows for the first time to reach a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity. By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. Our latent diffusion models (LDMs) achieve new state of the art scores for image inpainting and class-conditional image synthesis and highly competitive performance on various tasks, including unconditional image generation, text-to-image synthesis, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.

关键词： Training visualization Image synthesis Computational modeling Noise reduction Superresolution Process control

来源：评论

学校读者我要写书评

暂无评论

Unified Contrastive Learning in Image-Text-Label Space

Unified Contrastive Learning in Image-Text-Label Space

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yang, Jianwei Li, Chunyuan Zhang, Pengchuan Xiao, Bin Liu, Ce Yuan, Lu Gao, Jianfeng Microsoft Res Redmond Redmond WA 98052 USA Microsoft Cloud AI Redmond WA USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more discriminative representation, language-image pretraining shows unprecedented zero-shot recognition capability, largely due to the different properties of data sources and learning objectives. In this work, we introduce a new formulation by combining the two data sources into a common image-text-label space. In this space, we propose a new learning paradigm, called Unified Contrastive Learning (UniCL) with a single learning objective to seamlessly prompt the synergy of two data types. Extensive experiments show that our UniCL is an effective way of learning semantically rich yet discriminative representations, universally for image recognition in zero-shot, linear-probing, fully finetuning and transfer learning scenarios. Particularly, it attains gains up to 9.2% and 14.5% in average on zero-shot recognition benchmarks over the language-image contrastive learning and supervised learning methods, respectively. In linear probe setting, it also boosts the performance over the two methods by 7.3% and 3.4%, respectively. Our study also indicates that UniCL stand-alone is a good learner on pure image-label data, rivaling the supervised learning methods across three image classification datasets and two types of vision backbones, ResNet and Swin Transformer. Code is available at: https://***/microsoft/UniCL.

关键词： Representation learning visualization Image recognition Soft sensors Supervised learning Transfer learning Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Video Reconstruction for Rolling Shutter Cameras

Context-Aware Video Reconstruction for Rolling Shutter Camer...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Fan, Bin Dai, Yuchao Zhang, Zhiyuan Liu, Qi He, Mingyi Northwestern Polytech Univ Sch Elect & Informat Xian Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

With the ubiquity of rolling shutter (RS) cameras, it is becoming increasingly attractive to recover the latent global shutter (GS) video from two consecutive RS frames, which also places a higher demand on realism. Existing solutions, using deep neural networks or optimization, achieve promising performance. However;these methods generate intermediate GS frames through image warping based on the RS model, which inevitably result in black holes and noticeable motion artifacts. In this paper, we alleviate these issues by proposing a context-aware GS video reconstruction architecture. It facilitates the advantages such as occlusion reasoning, motion compensation, and temporal abstraction. Specifically, we first estimate the bilateral motion field so that the pixels of the two RS frames are warped to a common GS frame accordingly. Then, a refinement scheme is proposed to guide the GS frame synthesis along with bilateral occlusion masks to produce high-fidelity GS video frames at arbitrary times. Furthermore, we derive an approximated bilateral motion field model, which can serve as an alternative to provide a simple but effective GS frame initialization for related tasks. Experiments on synthetic and real data show that our approach achieves superior performance over state-of-the-art methods in terms of objective metrics and subjective visual quality. Code is available at https://***/GitCVfb/CVR.

关键词： visualization Pipelines Neural networks Cameras Motion compensation Pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Open-Set Domain Adaptation Under Few Source-Domain Labeled Samples

Open-Set Domain Adaptation Under Few Source-Domain Labeled S...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Rakshit, Sayan Balasubramanian, S. Bandyopadhyay, Hmrishav Bharambe, Piyush Desetti, Sai Nandan Banerjee, Biplab Chaudhuri, Subhasis Indian Inst Technol Mumbai Maharashtra India Sri SSIHL Puttaparthi Andhra Pradesh India Jadavpur Univ Kolkata W Bengal India

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Recently, the notion of closed-set few-shot domain adaptation (FSDA) has been introduced where limited supervision is present in the source domain. However, FSDA overlooks the fact that the unlabeled target domain may contain new classes unseen in the source domain. To this end, we introduce the novel problem definition of few-shot open-set DA (FosDA) where the source domain contains few labeled samples together with a large pool of unlabeled data, and the target domain consists of test samples from the known as well as new categories. We propose an end-to-end model called FosDANet to tackle such a scenario which operates on two principles: to generate confident pseudo-labels for the unlabeled source samples and to classwise align the source and target domains for the known classes while rejecting the unknown-class data. A combination of a self-supervised loss and a novel triplet-based relation learning module is devised to aid in confident pseudo-labeling, and a dual adversarial learning scheme is proposed for domain alignment. Extensive experiments were performed on five datasets: Office-31, Office-Home, Adoptiape, and two new datasets we designed: Mini-domainNet and a remote sensing benchmark called NPU-RSDA. FosDANet is found to consistently outperform the relevant literature.

关键词： Measurement visualization Satellites Benchmark testing Optical imaging Adversarial machine learning Data models

来源：评论

学校读者我要写书评

暂无评论

Structured Sparse R-CNN for Direct Scene Graph Generation

Structured Sparse R-CNN for Direct Scene Graph Generation

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Teng, Yao Wang, Limin Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Scene graph generation (SGG) is to detect object pairs with their relations in an image. Existing SGG approaches often use multi-stage pipelines to decompose this task into object detection, relation graph construction, and dense or dense-to-sparse relation prediction. Instead, from a perspective on SGG as a direct set prediction, this paper presents a simple, sparse, and unified framework, termed as Structured Sparse R-CNN. The key to our method is a set of learnable triplet queries and a structured triplet detector which could be jointly optimized from the training set in an end-to-end manner. Specifically, the triplet queries encode the general prior for object pairs with their relations, and provide an initial guess of scene graphs for subsequent refinement. The triplet detector presents a cascaded architecture to progressively refine the detected scene graphs with the customized dynamic heads. In addition, to relieve the training difficulty of our method, we propose a relaxed and enhanced training strategy based on knowledge distillation from a Siamese Sparse R-CNN. We perform experiments on several datasets: Visual Genome and Open Images V4/V6, and the results demonstrate that our method achieves the state-of-the-art performance. In addition, we also perform in-depth ablation studies to provide insights on our structured modeling in triplet detector design and training strategies. The code and models are made available at https : // github com/MCG-NJU/Structured-Sparse-RCNN.

关键词： Training visualization Head Pipelines Genomics Detectors Object detection

来源：评论

学校读者我要写书评

暂无评论

ProgressLabeller: Visual Data Stream Annotation for Training Object-Centric 3D Perception

ProgressLabeller: Visual Data Stream Annotation for Training...

引用

ieee/RSJ International conference on Intelligent Robots and Systems (IROS)

作者： Chen, Xiaotong Zhang, Huijie Yu, Zeren Lewis, Stanley Jenkins, Odest Chadwicke Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA Univ Michigan Robot Inst Ann Arbor MI 48109 USA

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

Visual perception tasks often require vast amounts of labelled data, including 3D poses and image space segmentation masks. The process of creating such training data sets can prove difficult or time-intensive to scale up to efficacy for general use. Consider the task of pose estimation for rigid objects. Deep neural network based approaches have shown good performance when trained on large, public datasets. However, adapting these networks for other novel objects, or fine-tuning existing models for different environments, requires significant time investment to generate newly labelled instances. Towards this end, we propose ProgressLabeller as a method for more efficiently generating large amounts of 6D pose training data from color images sequences for custom scenes in a scalable manner. ProgressLabeller is intended to also support transparent or translucent objects, for which the previous methods based on depth dense reconstruction will fail. We demonstrate the effectiveness of ProgressLabeller by rapidly create a dataset of over 1M samples with which we fine-tune a state-of-the-art pose estimation network in order to markedly improve the downstream robotic grasp success rates. Progresslabeller is open-source at https://***/huijieZH/ProgressLabeller

关键词： Deep learning Training visualization Three-dimensional displays Annotations Pose estimation Neural networks

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 << < 436 437 438 439 440 441 442 443 444 445 > >>

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：