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

11,745 篇 会议
8 篇 期刊文献

馆藏范围

11,753 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,139 篇 工学
- 7,674 篇 计算机科学与技术...
- 804 篇 机械工程
- 580 篇 软件工程
- 376 篇 电气工程
- 252 篇 控制科学与工程
- 208 篇 光学工程
- 85 篇 生物工程
- 83 篇 信息与通信工程
- 29 篇 生物医学工程（可授...
- 23 篇 电子科学与技术（可...
- 21 篇 化学工程与技术
- 15 篇 交通运输工程
- 14 篇 安全科学与工程
- 10 篇 网络空间安全
- 8 篇 仪器科学与技术
- 6 篇 材料科学与工程（可...
- 6 篇 动力工程及工程热...
3,194 篇 医学
- 3,190 篇 临床医学
- 11 篇 基础医学(可授医学...
- 7 篇 公共卫生与预防医...
481 篇 理学
- 216 篇 物理学
- 203 篇 系统科学
- 88 篇 生物学
- 55 篇 数学
- 29 篇 统计学（可授理学、...
- 24 篇 化学
55 篇 管理学
- 29 篇 图书情报与档案管...
- 28 篇 管理科学与工程(可...
- 12 篇 工商管理
17 篇 法学
- 15 篇 社会学
6 篇 农学
4 篇 教育学
2 篇 经济学
1 篇 军事学
1 篇 艺术学

主题

5,434 篇 computer vision
2,516 篇 training
2,087 篇 pattern recognit...
1,621 篇 computational mo...
1,435 篇 visualization
1,306 篇 three-dimensiona...
1,060 篇 semantics
981 篇 codes
968 篇 benchmark testin...
898 篇 computer archite...
884 篇 deep learning
762 篇 task analysis
681 篇 feature extracti...
536 篇 face recognition
527 篇 conferences
515 篇 transformers
515 篇 neural networks
479 篇 object detection
466 篇 image segmentati...
454 篇 cameras

机构

168 篇 univ sci & techn...
144 篇 univ chinese aca...
144 篇 tsinghua univ pe...
143 篇 carnegie mellon ...
135 篇 chinese univ hon...
112 篇 peng cheng lab p...
108 篇 zhejiang univ pe...
97 篇 swiss fed inst t...
92 篇 tsinghua univers...
92 篇 sensetime res pe...
88 篇 shanghai ai lab ...
85 篇 zhejiang univers...
84 篇 shanghai jiao to...
78 篇 peng cheng labor...
77 篇 university of sc...
77 篇 alibaba grp peop...
76 篇 univ hong kong p...
76 篇 tech univ munich...
76 篇 stanford univ st...
73 篇 university of ch...

作者

76 篇 timofte radu
64 篇 van gool luc
50 篇 zhang lei
44 篇 yang yi
40 篇 loy chen change
34 篇 tao dacheng
32 篇 liu yang
32 篇 chen chen
30 篇 zhou jie
30 篇 tian qi
30 篇 sun jian
28 篇 zha zheng-jun
27 篇 qi tian
26 篇 li xin
26 篇 vasconcelos nuno
26 篇 ying shan
25 篇 liu xiaoming
25 篇 luc van gool
25 篇 boxin shi
24 篇 zheng wei-shi

语言

11,746 篇 英文
7 篇 其他

检索条件"任意字段=2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023"

共 11753 条记录，以下是4731-4740 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：

When to Prune? A Policy towards Early Structural Pruning

When to Prune? A Policy towards Early Structural Pruning

引用

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

作者： Shen, Maying Molchanov, Pavlo Yin, Hongxu Alvarez, Jose M. NVIDIA Santa Clara CA 95051 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Pruning enables appealing reductions in network memory footprint and time complexity. Conventional post-training pruning techniques lean towards efficient inference while overlooking the heavy computation for training. Recent exploration of pre-training pruning at initialization hints on training cost reduction via pruning, but suffers noticeable performance degradation. We attempt to combine the benefits of both directions and propose a policy that prunes as early as possible during training without hurting performance. Instead of pruning at initialization, our method exploits initial dense training for few epochs to quickly guide the architecture, while constantly evaluating dominant sub-networks via neuron importance ranking. This unveils dominant sub-networks whose structures turn stable, allowing conventional pruning to be pushed earlier into the training. To do this early, we further introduce an Early Pruning Indicator (EPI) that relies on sub-network architectural similarity and quickly triggers pruning when the sub-network's architecture stabilizes. Through extensive experiments on ImageNet, we show that EPI empowers a quick tracking of early training epochs suitable for pruning, offering same efficacy as an otherwise "oracle" grid-search that scans through epochs and requires orders of magnitude more compute. Our method yields 1.4% top-1 accuracy boost over state-of-the-art pruning counterparts, cuts down training cost on GPU by 2.4x, hence offers a new efficiency-accuracy boundary for network pruning during training.

关键词： Training Measurement Costs Neurons computer architecture Object detection Power system stability

来源：评论

学校读者我要写书评

暂无评论

Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking

Transformer Meets Tracker: Exploiting Temporal Context for R...

引用

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

作者： Wang, Ning Zhou, Wengang Wang, Jie Li, Houqiang Univ Sci & Technol China USTC EEIS Dept CAS Key Lab GIPAS Hefei Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei Peoples R China

ISBN: (纸本)9781665445092

In video object tracking, there exist rich temporal contexts among successive frames, which have been largely overlooked in existing trackers. In this work, we bridge the individual video frames and explore the temporal contexts across them via a transformer architecture for robust object tracking. Different from classic usage of the transformer in natural language processing tasks, we separate its encoder and decoder into two parallel branches and carefully design them within the Siamese-like tracking pipelines. The transformer encoder promotes the target templates via attention-based feature reinforcement, which benefits the high-quality tracking model generation. The transformer decoder propagates the tracking cues from previous templates to the current frame, which facilitates the object searching process. Our transformer-assisted tracking framework is neat and trained in an end-to-end manner. With the proposed transformer, a simple Siamese matching approach is able to outperform the current top-performing trackers. By combining our transformer with the recent discriminative tracking pipeline, our method sets several new state-of-the-art records on prevalent tracking benchmarks.

关键词： Bridges Visualization Target tracking Pipelines computer architecture Transformers Search problems

来源：评论

学校读者我要写书评

暂无评论

Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization 31

Towards Faster Training of Global Covariance Pooling Network...

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Li, Peihua Xie, Jiangtao Wang, Qilong Gao, Zilin Dalian Univ Technol Dalian Peoples R China

ISBN: (纸本)9781538664209

Global covariance pooling in convolutional neural networks has achieved impressive improvement over the classical first-order pooling. Recent works have shown matrix square root normalization plays a central role in achieving state-of-the-art performance. However, existing methods depend heavily on eigendecomposition (EIG) or singular value decomposition (SVD), suffering from inefficient training due to limited support of EIG and SVD on GPU. Towards addressing this problem, we propose an iterative matrix square root normalization method for fast end-toend training of global covariance pooling networks. At the core of our method is a meta-layer designed with loop-embedded directed graph structure. The meta-layer consists of three consecutive nonlinear structured layers, which perform pre-normalization, coupled matrix iteration and post-compensation, respectively. Our method is much faster than EIG or SVD based ones, since it involves only matrix multiplications, suitable for parallel implementation on GPU. Moreover, the proposed network with ResNet architecture can converge in much less epochs, further accelerating network training. On large-scale ImageNet, we achieve competitive performance superior to existing counterparts. By finetuning our models pre-trained on ImageNet, we establish state-of-the-art results on three challenging finegrained benchmarks. The source code and network models will be available at http://***/iSQRT-COV.

关键词： Covariance matrices Graphics processing units Training Matrix decomposition Backpropagation Symmetric matrices computer architecture

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Visual recognition using Semantics-Preserving Adversarial Embedding Networks 31

Zero-Shot Visual Recognition using Semantics-Preserving Adve...

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Chen, Long Zhang, Hanwang Xiao, Jun Liu, Wei Chang, Shih-Fu Zhejiang Univ Hangzhou Zhejiang Peoples R China Nanyang Technol Univ Singapore Singapore Tencent AI Lab Bellevue WA USA Columbia Univ New York NY 10027 USA

ISBN: (纸本)9781538664209

We propose a novel framework called SemanticsPreserving Adversarial Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their classes are both unseen during training. SP-AEN aims to tackle the inherent problem - semantic loss in the prevailing family of embedding-based ZSL, where some semantics would be discarded during training if they are non-discriminative for training classes, but could become critical for recognizing test classes. Specifically, SPAEN prevents the semantic loss by introducing an independent visual-to-semantic space embedder which disentangles the semantic space into two subspaces for the two arguably conflicting objectives: classification and reconstruction. Through adversarial learning of the two subspaces, SP-AEN can transfer the semantics from the reconstructive subspace to the discriminative one, accomplishing the improved zero-shot recognition of unseen classes. Comparing with prior works, SP-AEN can not only improve classification but also generate photo-realistic images, demonstrating the effectiveness of semantic preservation. On four popular benchmarks: CUB, AWA, SUN and aPY, SP-AEN considerably outperforms other state-of-the-art methods by an absolute performance difference of 12.2%, 9.3%, 4.0%, and 3.6% in terms of harmonic mean values [62].

关键词： Semantics Image reconstruction Visualization Training Image color analysis Generative adversarial networks Birds

来源：评论

学校读者我要写书评

暂无评论

Edge Guided Progressively Generative Image Outpainting

Edge Guided Progressively Generative Image Outpainting

引用

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

作者： Lin, Han Pagnucco, Maurice Song, Yang Univ New South Wales Sch Comp Sci & Engn Sydney NSW Australia

ISBN: (纸本)9781665448994

Deep-learning based generative models are proven to be capable for achieving excellent results in numerous image processing tasks with a wide range of applications. One significant improvement of deep-learning approaches compared to traditional approaches is their ability to regenerate semantically coherent images by only relying on an input with limited information. This advantage becomes even more crucial when the input size is only a very minor proportion of the output size. Such image expansion tasks can be more challenging as the missing area may originally contain many semantic features that are critical in judging the quality of an image. In this paper we propose an edge-guided generative network model for producing semantically consistent output from a small image input. Our experiments show the proposed network is able to regenerate high quality images even when some structural features are missing in the input.

关键词： Measurement computer vision Image edge detection Computational modeling Image processing conferences Semantics

来源：评论

学校读者我要写书评

暂无评论

Neural Image Recolorization for Creative Domains

Neural Image Recolorization for Creative Domains

引用

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

作者： Li, Boyi Belongie, Serge Lim, Ser-nam Davis, Abe Cornell Univ Ithaca NY 14853 USA Univ Copenhagen Copenhagen Denmark Meta AI New York NY USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We present a self-supervised approach to recolorization of images from design-oriented domains. Our approach can recolor images based on image exemplars or target color palettes provided by a user. In contrast with previous approaches, our method can reproduce color palettes with luminance distributions that differ significantly from input, and our method is the first palette-based approach to distinguish between recolorings that match reflectance and those that match illumination, making it particularly well-suited to visualizing different aesthetic decisions in design applications. The key to our approach is first to learn latent representations for texture and color in a setting where self-supervision is especially straightforward, and then to learn a mapping to our color representation from input color palettes and scene illumination, which offers a more intuitive space for controlling and exploring recolorization.

关键词： Reflectivity Deep learning Visualization computer vision Image color analysis conferences Lighting

来源：评论

学校读者我要写书评

暂无评论

Depth-supervised NeRF: Fewer Views and Faster Training for Free

Depth-supervised NeRF: Fewer Views and Faster Training for F...

引用

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

作者： Deng, Kangle Liu, Andrew Zhu, Jun-Yan Ramanan, Deva Carnegie Mellon Univ Pittsburgh PA 15213 USA Google Mountain View CA 94043 USA Argo AI Pittsburgh PA USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

A commonly observed failure mode of Neural Radiance Field (NeRF) is fitting incorrect geometries when given an insufficient number of input views. One potential reason is that standard volumetric rendering does not enforce the constraint that most of a scene's geometry consist of empty space and opaque surfaces. We formalize the above assumption through DS-NeRF (Depth-supervised Neural Radiance Fields), a loss for learning radiance fields that takes advantage of readily-available depth supervision. We leverage the fact that current NeRF pipelines require images with known camera poses that are typically estimated by running structure-from-motion (SFM). Crucially, SFM also produces sparse 3D points that can be used as "free" depth supervision during training: we add a loss to encourage the distribution of a ray's terminating depth matches a given 3D keypoint, incorporating depth uncertainty. DS-NeRF can render better images given fewer training views while training 3x faster. Further, we show that our loss is compatible with other recently proposed NeRF methods, demonstrating that depth is a cheap and easily digestible supervisory signal. And finally, we find that DS-NeRF can support other types of depth supervision such as scanned depth sensors and RGB-D reconstruction outputs.

关键词： Training Geometry Three-dimensional displays Uncertainty Pipelines Rendering (computer graphics) Surface fitting

来源：评论

学校读者我要写书评

暂无评论

Reformulating HOI Detection as Adaptive Set Prediction

Reformulating HOI Detection as Adaptive Set Prediction

引用

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

作者： Chen, Mingfei Liao, Yue Liu, Si Chen, Zhiyuan Wang, Fei Qian, Chen Huazhong Univ Sci & Technol Wuhan Peoples R China Beihang Univ Inst Artificial Intelligence Beijing Peoples R China SenseTime Res Hong Kong Peoples R China

ISBN: (纸本)9781665445092

Determining which image regions to concentrate is critical for Human-Object Interaction (HOI) detection. Conventional HOI detectors focus on either detected human and object pairs or pre-defined interaction locations, which limits learning of the effective features. In this paper, we reformulate HOI detection as an adaptive set prediction problem, with this novel formulation, we propose an Adaptive Set-based one-stage framework (AS-Net) with parallel instance and interaction branches. To attain this, we map a trainable interaction query set to an interaction prediction set with transformer. Each query adaptively aggregates the interaction-relevant features from global contexts through multi-head co-attention. Besides, the training process is supervised adaptively by matching each ground-truth with the interaction prediction. Furthermore, we design an effective instance-aware attention module to introduce instructive features from the instance branch into the interaction branch. Our method outperforms previous state-of-the-art methods without any extra human pose and language features on three challenging HOI detection datasets. Especially, we achieve over 31% relative improvement on a large scale HICO-DET dataset. Code is available at https://***/yoyomimi/AS-Net.

关键词： Training computer vision Codes Aggregates Detectors Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration

From a Bird's Eye View to See: Joint Camera and Subject Regi...

引用

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

作者： Qian, Zekun Han, Ruize Feng, Wei Wang, Song Tianjin Univ Coll Intelligence & Comp Tianjin Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China City Univ Hong Kong Hong Kong Peoples R China Univ South Carolina Columbia SC 29208 USA

ISBN: (纸本)9798350353013;9798350353006

We tackle a new problem of multi-view camera and subject registration in the bird's eye view (BEV) without pre-given camera calibration, which promotes the multi-view subject registration problem to a new calibration-free stage. This greatly alleviates the limitation in many practical applications. However, this is a very challenging problem since its only input is several RGB images from different first-person views (FPVs), without the BEV image and the calibration of the FPVs, while the output is a unified plane aggregated from all views with the positions and orientations of both the subjects and cameras in a BEV. For this purpose, we propose an end-to-end framework solving camera and subject registration together by taking advantage of their mutual dependence, whose main idea is as below: i) creating a subject view-transform module (VTM) to project each pedestrian from FPV to a virtual BEV, ii) deriving a multi-view geometry-based spatial alignment module (SAM) to estimate the relative camera pose in a unified BEV, iii) selecting and refining the subject and camera registration results within the unified BEV. We collect a new large-scale synthetic dataset with rich annotations for training and evaluation. Additionally, we also collect a real dataset for cross-domain evaluation. The experimental results show the remarkable effectiveness of our method. The code and proposed datasets are available at BEVSee.

关键词： Camera Registration computer vision Multiview Detection Subject Registration

来源：评论

学校读者我要写书评

暂无评论

Self-Aligned Video Deraining with Transmission-Depth Consistency

Self-Aligned Video Deraining with Transmission-Depth Consist...

引用

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

作者： Yan, Wending Tan, Robby T. Yang, Wenhan Dai, Dengxin Natl Univ Singapore Singapore Singapore Yale NUS Coll Singapore Singapore City Univ Hong Kong Hong Kong Peoples R China Swiss Fed Inst Technol Zurich Switzerland

ISBN: (纸本)9781665445092

In this paper, we address the problem of rain streaks and rain accumulation removal in video, by developing a self-alignment network with transmission-depth consistency. Existing video based deraining methods focus only on rain streak removal, and commonly use optical flow to align the rain video frames. However, besides rain streaks, rain accummulation can considerably degrade visibility;and, optical flow estimation in a rain video is still erroneous, making the deraining performance tend to be inaccurate. Our method employs deformable convolution layers in our encoder to achieve feature-level frame alignment, and hence avoids using optical flow. For rain streaks, our method predicts the current frame from its adjacent frames, such that rain streaks that appear randomly in the temporal domain can be removed. For rain accumulation, our method employs a transmission-depth consistency loss to resolve the ambiguity between the depth and water-droplet density. Our network estimates the depth from consecutive rain-accumulation-removal outputs, and calculates the transmission map using a commonly used physics model. To ensure photometric-temporal and depth-temporal consistencies, our method estimates the camera poses, so that it can warp one frame to its adjacent frames. Experimental results show that our method is effective in removing both rain streaks and rain accumulation, outperforming those of state-of-the-art methods quantitatively and qualitatively.

关键词： Optical losses Visualization computer vision Rain Convolution Estimation Propagation losses

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 << < 470 471 472 473 474 475 476 477 478 479 > >>

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：