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

11,414 篇 会议
9 篇 期刊文献

馆藏范围

11,423 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,979 篇 工学
- 7,533 篇 计算机科学与技术...
- 805 篇 机械工程
- 401 篇 电气工程
- 390 篇 软件工程
- 231 篇 控制科学与工程
- 58 篇 光学工程
- 42 篇 生物工程
- 37 篇 信息与通信工程
- 19 篇 生物医学工程（可授...
- 14 篇 电子科学与技术（可...
- 13 篇 化学工程与技术
- 9 篇 安全科学与工程
- 7 篇 交通运输工程
- 6 篇 仪器科学与技术
- 4 篇 土木工程
- 3 篇 轻工技术与工程
3,137 篇 医学
- 3,137 篇 临床医学
- 8 篇 基础医学(可授医学...
- 5 篇 药学(可授医学、理...
- 4 篇 公共卫生与预防医...
307 篇 理学
- 200 篇 系统科学
- 63 篇 物理学
- 43 篇 生物学
- 30 篇 数学
- 15 篇 统计学（可授理学、...
- 14 篇 化学
29 篇 管理学
- 17 篇 图书情报与档案管...
- 13 篇 管理科学与工程(可...
- 5 篇 工商管理
3 篇 法学
- 3 篇 社会学
2 篇 教育学
2 篇 农学
1 篇 经济学
1 篇 艺术学

主题

5,612 篇 computer vision
2,584 篇 training
2,092 篇 pattern recognit...
1,682 篇 computational mo...
1,496 篇 visualization
1,343 篇 three-dimensiona...
1,098 篇 semantics
1,007 篇 benchmark testin...
1,005 篇 codes
927 篇 computer archite...
898 篇 deep learning
790 篇 task analysis
708 篇 feature extracti...
571 篇 conferences
563 篇 face recognition
520 篇 transformers
517 篇 neural networks
493 篇 object detection
476 篇 image segmentati...
452 篇 cameras

机构

172 篇 univ sci & techn...
150 篇 univ chinese aca...
148 篇 tsinghua univ pe...
145 篇 carnegie mellon ...
136 篇 chinese univ hon...
116 篇 peng cheng lab p...
106 篇 zhejiang univ pe...
97 篇 swiss fed inst t...
96 篇 sensetime res pe...
95 篇 tsinghua univers...
91 篇 shanghai ai lab ...
85 篇 shanghai jiao to...
83 篇 alibaba grp peop...
81 篇 peng cheng labor...
80 篇 zhejiang univers...
80 篇 stanford univ st...
78 篇 univ hong kong p...
77 篇 university of ch...
75 篇 australian natl ...
75 篇 tech univ munich...

作者

64 篇 timofte radu
60 篇 van gool luc
50 篇 zhang lei
44 篇 yang yi
39 篇 tao dacheng
35 篇 loy chen change
32 篇 tian qi
31 篇 zhou jie
31 篇 sun jian
30 篇 liu yang
29 篇 vasconcelos nuno
29 篇 qi tian
29 篇 zha zheng-jun
28 篇 chen chen
27 篇 boxin shi
26 篇 li xin
26 篇 luc van gool
26 篇 pollefeys marc
25 篇 liu xiaoming
25 篇 ying shan

语言

11,420 篇 英文
3 篇 其他

检索条件"任意字段=2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021"

共 11423 条记录，以下是4941-4950 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：

Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models

Intrinsic Physical Concepts Discovery with Object-Centric Pr...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Tang, Qu Zhu, Xiangyu Lei, Zhen Zhang, Zhaoxiang Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Chinese Acad Sci Inst Automat MAIS Beijing Peoples R China Chinese Acad Sci Hong Kong Inst Sci & Innovat Ctr Artificial Intelligence & Robot Beijing Peoples R China

ISBN: (纸本)9798350301298

The ability to discover abstract physical concepts and understand how they work in the world through observing lies at the core of human intelligence. The acquisition of this ability is based on compositionally perceiving the environment in terms of objects and relations in an unsupervised manner. Recent approaches learn object-centric representations and capture visually observable concepts of objects, e.g., shape, size, and location. In this paper, we take a step forward and try to discover and represent intrinsic physical concepts such as mass and charge. We introduce the PHYsical Concepts Inference NEtwork (PHYCINE), a system that infers physical concepts in different abstract levels without supervision. The key insights underlining PHYCINE are two-fold, commonsense knowledge emerges with prediction, and physical concepts of different abstract levels should be reasoned in a bottom-up fashion. Empirical evaluation demonstrates that variables inferred by our system work in accordance with the properties of the corresponding physical concepts. We also show that object representations containing the discovered physical concepts variables could help achieve better performance in causal reasoning tasks, i.e., ComPhy.

关键词： vision applications and systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging per Image-Token Consistency for vision-Language Pre-training

Leveraging per Image-Token Consistency for Vision-Language P...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Gou, Yunhao Ko, Tom Yang, Hansi Kwok, James Zhang, Yu Wang, Mingxuan Southern Univ Sci & Technol Shenzhen Peoples R China Hong Kong Univ Sci & Technol Hong Kong Peoples R China ByteDance Ai Lab Beijing Peoples R China Peng Cheng Lab Shenzhen Peoples R China

ISBN: (纸本)9798350301298

Most existing vision-language pre-training (VLP) approaches adopt cross-modal masked language modeling (CMLM) to learn vision-language associations. However, we find that CMLM is insufficient for this purpose according to our observations: (1) Modality bias: a considerable amount of masked tokens in CMLM can be recovered with only the language information, ignoring the visual inputs. (2) Under-utilization of the unmasked tokens: CMLM primarily focuses on the masked token but it cannot simultaneously leverage other tokens to learn vision-language associations. To handle those limitations, we propose EPIC (lEveraging Per Image-Token Consistency for vision-language pre-training). In EPIC, for each image-sentence pair, we mask tokens that are salient to the image (i.e., Saliency-based Masking Strategy) and replace them with alternatives sampled from a language model (i.e., Inconsistent Token Generation Procedure), and then the model is required to determine for each token in the sentence whether it is consistent with the image (i.e., Image-Token Consistency Task). The proposed EPIC method is easily combined with pre-training methods. Extensive experiments show that the combination of the EPIC method and state-of-the-art pre-training approaches, including ViLT, ALBEF, METER, and X-VLM, leads to significant improvements on downstream tasks. Our coude is released at https://***/gyhdog99/epic

关键词： Multi-modal learning

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Transfer Learning for Image Rain Removal 32

Semi-supervised Transfer Learning for Image Rain Removal

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Wei, Wei Meng, Deyu Zhao, Qian Xu, Zongben Wu, Ying Xi An Jiao Tong Univ Sch Math & Stat Xian Peoples R China Northwestern Univ Dept Elect & Comp Engn Evanston IL 60208 USA

ISBN: (纸本)9781728132938

Single image rain removal is a typical inverse problem in computer vision. The deep learning technique has been verified to be effective for this task and achieved state-of-the-art performance. However, previous deep learning methods need to pre-collect a large set of image pairs with/without synthesized rain for training, which tends to make the neural network be biased toward learning the specific patterns of the synthesized rain, while be less able to generalize to real test samples whose rain types differ from those in the training data. To this issue, this paper firstly proposes a semi-supervised learning paradigm toward this task. Different from traditional deep learning methods which only use supervised image pairs with/without synthesized rain, we further put real rainy images, without need of their clean ones, into the network training process. This is realized by elaborately formulating the residual between an input rainy image and its expected network output (clear image without rain) as a specific parametrized rain streaks distribution. The network is therefore trained to adapt real unsupervised diverse rain types through transferring from the supervised synthesized rain, and thus both the short-of-training-sample and bias-to-supervised-sample issues can be evidently alleviated. Experiments on synthetic and real data verify the superiority of our model compared to the state-of-the-arts.

关键词： Low-level vision Statistical Learning vision + Graphics

来源：评论

学校读者我要写书评

暂无评论

UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image recognition

UniRepLKNet: A Universal Perception Large-Kernel ConvNet for...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Ding, Xiaohan Zhang, Yiyuan Ge, Yixiao Zhao, Sijie Song, Lin Yue, Xiangyu Shan, Ying Tencent AI Lab Shenzhen Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9798350353013;9798350353006

Large-kernel convolutional neural networks (ConvNets) have recently received extensive research attention, but two unresolved and critical issues demand further investigation. 1) The architectures of existing large-kernel ConvNets largely follow the design principles of conventional ConvNets or transformers, while the architectural design for large-kernel ConvNets remains under-addressed. 2) As transformers have dominated multiple modalities, it remains to be investigated whether ConvNets also have a strong universal perception ability in domains beyond vision. In this paper, we contribute from two aspects. 1) We propose four architectural guidelines for designing large-kernel ConvNets, the core of which is to exploit the essential characteristics of large kernels that distinguish them from small kernels - they can see wide without going deep. Following such guidelines, our proposed large-kernel ConvNet shows leading performance in image recognition (ImageNet accuracy of 88.0%, ADE20K mIoU of 55.6%, and COCO box AP of 56.4%), demonstrating better performance and higher speed than the recent powerful competitors. 2) We discover large kernels are the key to unlocking the exceptional performance of ConvNets in domains where they were originally not proficient. With certain modality-related pre-processing approaches, the proposed model achieves state-of-the-art performance on time-series forecasting and audio recognition tasks even without modality-specific customization to the architecture. All the code and models are publicly available on GitHub and Huggingface.

关键词： Large-Kernel ConvNets Multimodal Learning Network Architecture

来源：评论

学校读者我要写书评

暂无评论

OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data

OccAM's Laser: Occlusion-based Attribution Maps for 3D Objec...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Schinagl, David Krispel, Georg Possegger, Horst Roth, Peter M. Bischof, Horst Graz Univ Technol Graz Austria Christian Doppler Lab Embedded Machine Learning Graz Austria Tech Univ Munich Munich Germany Univ Vet Med Vienna Austria

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

While 3D object detection in LiDAR point clouds is well-established in academia and industry, the explainability of these models is a largely unexplored field. In this paper, we propose a method to generate attribution maps for the detected objects in order to better understand the behavior of such models. These maps indicate the importance of each 3D point in predicting the specific objects. Our method works with black-box models: We do not require any prior knowledge of the architecture nor access to the model's internals, like parameters, activations or gradients. Our efficient perturbation-based approach empirically estimates the importance of each point by testing the model with randomly generated subsets of the input point cloud. Our sub-sampling strategy takes into account the special characteristics of LiDAR data, such as the depth-dependent point density. We show a detailed evaluation of the attribution maps and demonstrate that they are interpretable and highly informative. Furthermore, we compare the attribution maps of recent 3D object detection architectures to provide insights into their decision-making processes.

关键词： Point cloud compression computer vision Three-dimensional displays Laser radar Detectors computer architecture Object detection

来源：评论

学校读者我要写书评

暂无评论

On the Importance of Accurate Geometry Data for Dense 3D vision Tasks

On the Importance of Accurate Geometry Data for Dense 3D Vis...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Jung, HyunJun Ruhkamp, Patrick Zhai, Guangyao Brasch, Nikolas Li, Yitong Verdie, Yannick Song, Jifei Zhou, Yiren Armagan, Anil Ilic, Slobodan Leonardis, Ales Navab, Nassir Busam, Benjamin Tech Univ Munich Munich Germany Dwe Ai Munich Germany Huawei Noahs Ark Lab Montreal PQ Canada Siemens AG Munich Germany

ISBN: (纸本)9798350301298

Learning-based methods to solve dense 3D vision problems typically train on 3D sensor data. The respectively used principle of measuring distances provides advantages and drawbacks. These are typically not compared nor discussed in the literature due to a lack of multi-modal datasets. Texture-less regions are problematic for structure from motion and stereo, reflective material poses issues for active sensing, and distances for translucent objects are intricate to measure with existing hardware. Training on inaccurate or corrupt data induces model bias and hampers generalisation capabilities. These effects remain unnoticed if the sensor measurement is considered as ground truth during the evaluation. This paper investigates the effect of sensor errors for the dense 3D vision tasks of depth estimation and reconstruction. We rigorously show the significant impact of sensor characteristics on the learned predictions and notice generalisation issues arising from various technologies in everyday household environments. For evaluation, we introduce a carefully designed dataset1 comprising measurements from commodity sensors, namely D-ToF, I-ToF, passive/active stereo, and monocular RGB+P. Our study quantifies the considerable sensor noise impact and paves the way to improved dense vision estimates and targeted data fusion.

关键词： 3D from single images

来源：评论

学校读者我要写书评

暂无评论

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud 32

PointRCNN: 3D Object Proposal Generation and Detection from ...

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Shi, Shaoshuai Wang, Xiaogang Li, Hongsheng Chinese Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781728132938

In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical coordinates to obtain the final detection results. Instead of generating proposals from RGB image or projecting point cloud to bird's view or voxels as previous methods do, our stage-1 sub-network directly generates a small number of high-quality 3D proposals from point cloud in a bottom-up manner via segmenting the point cloud of the whole scene into foreground points and background. The stage-2 sub-network transforms the pooled points of each proposal to canonical coordinates to learn better local spatial features, which is combined with global semantic features of each point learned in stage-1 for accurate box refinement and confidence prediction. Extensive experiments on the 3D detection benchmark of KITTI dataset show that our proposed architecture outperforms state-of-the-art methods with remarkable margins by using only point cloud as input.

关键词： 3D from Multiview and Sensors Categorization recognition: Detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

Graphical Contrastive Losses for Scene Graph Parsing 32

Graphical Contrastive Losses for Scene Graph Parsing

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Zhang, Ji Shih, Kevin J. Elgammal, Ahmed Tao, Andrew Catanzaro, Bryan Rutgers State Univ Dept Comp Sci New Brunswick NJ 08901 USA Nvidia Corp Santa Clara CA 95051 USA

ISBN: (纸本)9781728132938

Most scene graph parsers use a two-stage pipeline to detect visual relationships: the first stage detects entities, and the second predicts the predicate for each entity pair using a softmax distribution. We find that such pipelines, trained with only a cross entropy loss over predicate classes, suffer from two common errors. The first, Entity Instance Confusion, occurs when the model confuses multiple instances of the same type of entity (e.g. multiple cups). The second, Proximal Relationship Ambiguity, arises when multiple subject-predicate-object triplets appear in close proximity with the same predicate, and the model struggles to infer the correct subject-object pairings (e.g. mis-pairing musicians and their instruments). We propose a set of contrastive loss formulations that specifically target these types of errors within the scene graph parsing problem, collectively termed the Graphical Contrastive Losses. These losses explicitly force the model to disambiguate related and unrelated instances through margin constraints specific to each type of confusion. We further construct a relationship detector, called RelDN, using the aforementioned pipeline to demonstrate the efficacy of our proposed losses. Our model outperforms the winning method of the Open Images Relationship Detection Challenge by 4.7% (16.5% relatively) on the test set. We also show improved results over the best previous methods on the Visual Genome and Visual Relationship Detection datasets.

关键词： Categorization recognition: Detection Retrieval Scene Analysis and Understanding

来源：评论

学校读者我要写书评

暂无评论

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels 32

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kerne...

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Zhang, Kai Zuo, Wangmeng Zhang, Lei Harbin Inst Technol Sch Comp Sci & Technol Harbin Heilongjiang Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China Peng Cheng Lab Shenzhen Guangdong Peoples R China Alibaba Grp DAMO Acad Shenzhen Guangdong Peoples R China

ISBN: (纸本)9781728132938

While deep neural networks (DNN) based single image super-resolution (SISR) methods are rapidly gaining popularity, they are mainly designed for the widely-used bicubic degradation, and there still remains the fundamental challenge for them to super-resolve low-resolution (LR) image with arbitrary blur kernels. In the meanwhile, plug-and-play image restoration has been recognized with high flexibility due to its modular structure for easy plug-in of denoiser priors. In this paper, we propose a principled formulation and framework by extending bicubic degradation based deep SISR with the help of plug-and-play framework to handle LR images with arbitrary blur kernels. Specifically, we design a new SISR degradation model so as to take advantage of existing blind deblurring methods for blur kernel estimation. To optimize the new degradation induced energy function, we then derive a plug-and-play algorithm via variable splitting technique, which allows us to plug any super-resolver prior rather than the denoiser prior as a modular part. Quantitative and qualitative evaluations on synthetic and real LR images demonstrate that the proposed deep plug-and-play super-resolution framework is flexible and effective to deal with blurry LR images.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

Sign Language Transformers: Joint End-to-end Sign Language recognition and Translation

Sign Language Transformers: Joint End-to-end Sign Language R...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Camgoz, Necati Cihan Koller, Oscar Hadfield, Simon Bowden, Richard Univ Surrey CVSSP Guildford England Microsoft Munich Germany

ISBN: (纸本)9781728171685

Prior work on Sign Language Translation has shown that having a mid-level sign gloss representation (effectively recognizing the individual signs) improves the translation performance drastically. In fact, the current state-of-the- art in translation requires gloss level tokenization in order to work. We introduce a novel transformer based architecture that jointly learns Continuous Sign Language recognition and Translation while being trainable in an end-to-end manner. This is achieved by using a Connectionist Temporal Classification (CTC) loss to bind the recognition and translation problems into a single unified architecture. This joint approach does not require any ground-truth timing information, simultaneously solving two co-dependant sequence-to-sequence learning problems and leads to significant performance gains. We evaluate the recognition and translation performances of our approaches on the challenging RWTHPHOENIX-Weather-2014T (PHOENIX14T) dataset. We report state-of-the-art sign language recognition and translation results achieved by our Sign Language Transformers. Our translation networks outperform both sign video to spoken language and gloss to spoken language translation models, in some cases more than doubling the performance (9.58 vs. 21.80 BLEU-4 Score). We also share new baseline translation results using transformer networks for several other text-to-text sign language translation tasks.

关键词： Network architecture

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：