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4581-4590 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：

PointNetLK Revisited

PointNetLK Revisited

引用

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

作者： Li, Xueqian Pontes, Jhony Kaesemodel Lucey, Simon Argo AI Pittsburgh PA 15222 USA Univ Adelaide Adelaide SA Australia Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781665445092

We address the generalization ability of recent learning-based point cloud registration methods. Despite their success, these approaches tend to have poor performance when applied to mismatched conditions that are not well-represented in the training set, such as unseen object categories, different complex scenes, or unknown depth sensors. In these circumstances, it has often been better to rely on classical non-learning methods (e.g., Iterative Closest Point), which have better generalization ability. Hybrid learning methods, that use learning for predicting point correspondences and then a deterministic step for alignment, have offered some respite, but are still limited in their generalization abilities. We revisit a recent innovation-PointNetLK [1]-and show that the inclusion of an analytical Jacobian can exhibit remarkable generalization properties while reaping the inherent fidelity benefits of a learning framework. Our approach not only outperforms the state-of-the-art in mismatched conditions but also produces results competitive with current learning methods when operating on real-world test data close to the training set.

关键词： Training Jacobian matrices Solid modeling Three-dimensional displays Robustness Sensors pattern recognition

来源：评论

学校读者我要写书评

暂无评论

引用

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

作者： Collier, Mark Mustafa, Basil Kokiopoulou, Efi Jenatton, Rodolphe Berent, Jesse Google AI Mountain View CA 94043 USA

ISBN: (纸本)9781665445092

Large scale image classification datasets often contain noisy labels. We take a principled probabilistic approach to modelling input-dependent, also known as heteroscedastic, label noise in these datasets. We place a multivariate Nor-mal distributed latent variable on the final hidden layer of a neural network classifier. The covariance matrix of this latent variable, models the aleatoric uncertainty due to label noise. We demonstrate that the learned covariance structure captures known sources of label noise between semantically similar and co-occurring classes. Compared to standard neural network training and other baselines, we show significantly improved accuracy on Imagenet ILSVRC 2012 79.3% (+ 2.6%), Imagenet-21k 47.0% (+ 1.1%) and JFT 64.7% (+ 1.6%). We set a new state-of-the-art result on Webvision 1.0 with 76.6% top-1 accuracy. These datasets range from over 1M to over 300M training examples and from 1k classes to more than 21k classes. Our method is simple to use, and we provide an implementation that is a drop-in replacement for the final fully-connected layer in a deep classifier.

关键词： Training Correlation Uncertainty Neural networks Estimation Probabilistic logic pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Spatially-Adaptive Pixelwise Networks for Fast Image Translation

Spatially-Adaptive Pixelwise Networks for Fast Image Transla...

引用

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

作者： Shaham, Tamar Rott Gharbi, Michael Zhang, Richard Shechtman, Eli Michaeli, Tomer Technion Haifa Israel Adobe Res San Jose CA USA

ISBN: (纸本)9781665445092

We introduce a new generator architecture, aimed at fast and efficient high-resolution image-to-image translation. We design the generator to be an extremely lightweight function of the full-resolution image. In fact, we use pixel-wise networks;that is, each pixel is processed independently of others, through a composition of simple affine transformations and nonlinearities. We take three important steps to equip such a seemingly simple function with adequate expressivity. First, the parameters of the pixel-wise networks are spatially varying, so they can represent a broader function class than simple 1 x 1 convolutions. Second, these parameters are predicted by a fast convolutional network that processes an aggressively low-resolution representation of the input. Third, we augment the input image by concatenating a sinusoidal encoding of spatial coordinates, which provides an effective inductive bias for generating realistic novel high-frequency image content. As a result, our model is up to 18x faster than state-of-the-art baselines. We achieve this speedup while generating comparable visual quality across different image resolutions and translation domains.

关键词： Visualization computer vision Image coding Image synthesis Computational modeling computer architecture Generators

来源：评论

学校读者我要写书评

暂无评论

DynamicDet: A Unified Dynamic Architecture for Object Detection

DynamicDet: A Unified Dynamic Architecture for Object Detect...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Zhihao Lin Yongtao Wang Jinhe Zhang Xiaojie Chu Wangxuan Institute of Computer Technology Peking University

Dynamic neural network is an emerging research topic in deep learning. With adaptive inference, dynamic models can achieve remarkable accuracy and computational efficiency. However, it is challenging to design a powerful dynamic detector, because of no suitable dynamic architecture and exiting criterion for object detection. To tackle these difficulties, we propose a dynamic framework for object detection, named DynamicDet. Firstly, we carefully design a dynamic architecture based on the nature of the object detection task. Then, we propose an adaptive router to analyze the multi-scale information and to decide the inference route automatically. We also present a novel optimization strategy with an exiting criterion based on the detection losses for our dynamic detectors. Last, we present a variable-speed inference strategy, which helps to realize a wide range of accuracy-speed trade-offs with only one dynamic detector. Extensive experiments conducted on the COCO benchmark demonstrate that the proposed DynamicDet achieves new state-of-the-art accuracy-speed trade-offs. For instance, with comparable accuracy, the inference speed of our dynamic detector Dy-YOLOv7-W6 surpasses YOLOv7-E6 by 12%, YOLOv7-D6 by 17%, and YOLOv7-E6E by 39%. The code is available at https://***/VDIGPKU/DynamicDet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

End-to-End Object Detection with Fully Convolutional Network

End-to-End Object Detection with Fully Convolutional Network

引用

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

作者： Wang, Jianfeng Song, Lin Li, Zeming Sun, Hongbin Sun, Jian Zheng, Nanning Megvii Technol Beijing Peoples R China Xi An Jiao Tong Univ Coll Artificial Intelligence Xian Peoples R China

ISBN: (纸本)9781665445092

Mainstream object detectors based on the fully convolutional network has achieved impressive performance. While most of them still need a hand-designed non-maximum suppression (NMS) post-processing, which impedes fully endto-end training. In this paper, we give the analysis of discarding NMS, where the results reveal that a proper label assignment plays a crucial role. To this end, for fully convolutional detectors, we introduce a Prediction-aware One-To-One (POTO) label assignment for classification to enable end-to-end detection, which obtains comparable performance with NMS. Besides, a simple 3D Max Filtering (3DMF) is proposed to utilize the multi-scale features and improve the discriminability of convolutions in the local region. With these techniques, our end-to-end framework achieves competitive performance against many state-of-the-art detectors with NMS on COCO and CrowdHuman datasets.

关键词： Convolutional codes Training computer vision Three-dimensional displays Filtering Detectors Object detection

来源：评论

学校读者我要写书评

暂无评论

LPSNet: A lightweight solution for fast panoptic segmentation

LPSNet: A lightweight solution for fast panoptic segmentatio...

引用

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

作者： Hong, Weixiang Guo, Qingpei Zhang, Wei Chen, Jingdong Chu, Wei Ant Financial Serv Grp Hangzhou Peoples R China

ISBN: (纸本)9781665445092

Panoptic segmentation is a challenging task aiming to simultaneously segment objects (things) at instance level and background contents (stuff) at semantic level. Existing methods mostly utilize a two-stage detection network to attain instance segmentation results, and a fully convolutional network to produce a semantic segmentation prediction. Post-processing or additional modules are required to handle the conflicts between the outputs from these two nets, which makes such methods suffer from low efficiency, heavy memory consumption and complicated implementation. To simplify the pipeline and decrease computation/memory cost, we propose an one-stage approach called Lightweight Panoptic Segmentation Network (LPSNet), which does not involve a proposal, anchor or mask head. Instead, we predict a bounding box and semantic category at each pixel upon the feature map produced by an augmented feature pyramid, and design a parameter-free head to merge the per-pixel bounding box and semantic prediction into panoptic segmentation output. Our LPSNet is not only efficient in computation and memory, but also accurate in panoptic segmentation. Comprehensive experiments on COCO, Cityscapes and Mapillary Vistas datasets demonstrate the promising effectiveness and efficiency of the proposed LP-SNet.

关键词： computer vision Costs Semantics Memory management Pipelines Object detection Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Radar-Camera Pixel Depth Association for Depth Completion

Radar-Camera Pixel Depth Association for Depth Completion

引用

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

作者： Long, Yunfei Morris, Daniel Liu, Xiaoming Castro, Marcos Chakravarty, Punarjay Narayanan, Praveen Michigan State Univ E Lansing MI 48824 USA Ford Motor Co Dearborn MI 48121 USA

ISBN: (纸本)9781665445092

While radar and video data can be readily fused at the detection level, fusing them at the pixel level is potentially more beneficial. This is also more challenging in part due to the sparsity of radar, but also because automotive radar beams are much wider than a typical pixel combined with a large baseline between camera and radar, which results in poor association between radar pixels and color pixel. A consequence is that depth completion methods designed for LiDAR and video fare poorly for radar and video. Here we propose a radar-to-pixel association stage which learns a mapping from radar returns to pixels. This mapping also serves to densify radar returns. Using this as a first stage, followed by a more traditional depth completion method, we are able to achieve imageguided depth completion with radar and video. We demonstrate performance superior to camera and radar alone on the nuScenes dataset. Our source code is available at https://***/longyunf/rc-pda.

关键词： Training computer vision Laser radar Radar measurements Image color analysis Radar detection Radar

来源：评论

学校读者我要写书评

暂无评论

Bush Detection for vision-based UGV Guidance in Blueberry Orchards: Data Set and Methods

Bush Detection for Vision-based UGV Guidance in Blueberry Or...

引用

2023 ieee/cvf conference on computer vision and pattern recognition Workshops, cvprW 2023

作者： Filipović, Vladan Stefanović, Dimitrije Pajević, Nina Grbović, Željana Djuric, Nemanja Panić, Marko BioSense Institute Novi Sad Serbia

ISBN: (纸本)9798350302493

Object detection has reached strong performance in the last decade, having seen its usage spreading to various application areas, such as medicine, transportation, sports, and others. However, one of the more underutilized areas where advanced detection methods have yet to fully fulfill their promise is in the area of agriculture, where a strong potential exists for applying learned models to achieve practical, real-world impact affecting a large number of people. In this work, we focus on this application area and consider the problem of orchard guidance for ground robots, focusing on obstacle and plant detection from RGB camera images. First, we present an overview of public data sets used to train models to detect relevant objects from camera images and other sensor inputs. Then we introduce a novel data set collected in blueberry orchards that contains camera images in various conditions and provides blueberry bushes as targets for detection. The introduced data set provides the research community with a novel task of blueberry bush detection, which was not commonly considered thus far due to the lack of relevant data sets. We describe a detailed analysis of the data set, and finally provide an experimental study with several state-of-the-art deep object detection models, that set a baseline for the performance on this novel data set. The data set is made available online, enriching the variability of the existing tasks in the field and supporting further development of smart agriculture applications. © 2023 ieee.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Complementary Relation Contrastive Distillation

Complementary Relation Contrastive Distillation

引用

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

作者： Zhu, Jinguo Tang, Shixiang Chen, Dapeng Yu, Shijie Liu, Yakun Rong, Mingzhe Yang, Aijun Wang, Xiaohua Xi An Jiao Tong Univ Xian Peoples R China Univ Sydney Sydney NSW Australia Sensetime Grp Ltd Hong Kong Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China

ISBN: (纸本)9781665445092

Knowledge distillation aims to transfer representation ability from a teacher model to a student model. Previous approaches focus on either individual representation distillation or inter-sample similarity preservation. While we argue that the inter-sample relation conveys abundant information and needs to be distilled in a more effective way. In this paper, we propose a novel knowledge distillation method, namely Complementary Relation Contrastive Distillation (CRCD), to transfer the structural knowledge from the teacher to the student. Specifically, we estimate the mutual relation in an anchor-based way and distill the anchor-student relation under the supervision of its corresponding anchor-teacher relation. To make it more robust, mutual relations are modeled by two complementary elements: the feature and its gradient. Furthermore, the low bound of mutual information between the anchor-teacher relation distribution and the anchor-student relation distribution is maximized via relation contrastive loss, which can distill both the sample representation and the inter-sample relations. Experiments on different benchmarks demonstrate the effectiveness of our proposed CRCD.

关键词： computer vision Benchmark testing pattern recognition Mutual information

来源：评论

学校读者我要写书评

暂无评论

Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories

Beyond Short Clips: End-to-End Video-Level Learning with Col...

引用

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

作者： Yang, Xitong Fan, Haoqi Torresani, Lorenzo Davis, Larry Wang, Heng Univ Maryland College Pk MD 20742 USA Facebook AI Menlo Pk CA USA

ISBN: (纸本)9781665445092

The standard way of training video models entails sampling at each iteration a single clip from a video and optimizing the clip prediction with respect to the video-level label. We argue that a single clip may not have enough temporal coverage to exhibit the label to recognize, since video datasets are often weakly labeled with categorical information but without dense temporal annotations. Furthermore, optimizing the model over brief clips impedes its ability to learn long-term temporal dependencies. To overcome these limitations, we introduce a collaborative memory mechanism that encodes information across multiple sampled clips of a video at each training iteration. This enables the learning of long-range dependencies beyond a single clip. We explore different design choices for the collaborative memory to ease the optimization difficulties. Our proposed framework is end-to-end trainable and significantly improves the accuracy of video classification at a negligible computational overhead. Through extensive experiments, we demonstrate that our framework generalizes to different video architectures and tasks, outperforming the state of the art on both action recognition (e.g., Kinetics-400 & 700, Charades, Something-Something-VI) and action detection (e.g., AVA v2.1 & v2.2).

关键词： Training computer vision Collaboration computer architecture Predictive models Fasteners pattern recognition

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 << < 455 456 457 458 459 460 461 462 463 464 > >>

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：