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

858 篇 会议

馆藏范围

858 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

853 篇 工学
- 838 篇 计算机科学与技术...
- 27 篇 软件工程
- 15 篇 生物工程
- 10 篇 光学工程
- 9 篇 机械工程
- 8 篇 信息与通信工程
- 5 篇 控制科学与工程
- 3 篇 电气工程
- 3 篇 电子科学与技术（可...
- 3 篇 生物医学工程（可授...
- 2 篇 化学工程与技术
- 1 篇 建筑学
- 1 篇 交通运输工程
31 篇 理学
- 15 篇 生物学
- 10 篇 数学
- 9 篇 物理学
- 5 篇 统计学（可授理学、...
- 3 篇 化学
- 1 篇 地质学
5 篇 管理学
- 3 篇 图书情报与档案管...
- 2 篇 管理科学与工程(可...
3 篇 医学
- 3 篇 临床医学
- 2 篇 基础医学(可授医学...
- 1 篇 公共卫生与预防医...
- 1 篇 药学(可授医学、理...

主题

362 篇 deep learning
359 篇 recognition: det...
358 篇 categorization
357 篇 retrieval
128 篇 vision applicati...
121 篇 low-level vision
119 篇 representation l...
92 篇 vision + languag...
69 篇 segmentation
68 篇 image and video ...
63 篇 scene analysis a...
60 篇 grouping and sha...
54 篇 face
52 篇 gesture
51 篇 and body pose
51 篇 vision + graphic...
48 篇 computational ph...
45 篇 video analytics
44 篇 action recogniti...
42 篇 datasets and eva...

机构

27 篇 peng cheng lab p...
26 篇 univ chinese aca...
23 篇 chinese univ hon...
17 篇 sensetime res pe...
17 篇 nanyang technol ...
15 篇 univ sci & techn...
15 篇 carnegie mellon ...
15 篇 tsinghua univ pe...
15 篇 sun yat sen univ...
14 篇 johns hopkins un...
12 篇 stanford univ st...
11 篇 peking univ peop...
11 篇 incept inst arti...
11 篇 huawei noahs ark...
10 篇 facebook ai res ...
10 篇 univ maryland co...
10 篇 shanghai jiao to...
10 篇 univ calif berke...
9 篇 georgia inst tec...
9 篇 swiss fed inst t...

作者

10 篇 zhang lei
10 篇 wang xiaogang
10 篇 liu wei
10 篇 shao ling
9 篇 zheng wei-shi
9 篇 loy chen change
8 篇 timofte radu
7 篇 chun se young
7 篇 tao dacheng
7 篇 lin liang
7 篇 lin dahua
7 篇 zuo wangmeng
7 篇 yan junjie
7 篇 cheng ming-ming
6 篇 van gool luc
6 篇 chen xilin
6 篇 tian qi
6 篇 rohrbach marcus
6 篇 ji rongrong
6 篇 khan fahad shahb...

语言

858 篇 英文

检索条件"任意字段=32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019"

共 858 条记录，以下是131-140 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：

Shapes and Context: In-the-Wild Image Synthesis & Manipulation 32

Shapes and Context: In-the-Wild Image Synthesis & Manipulati...

引用

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

作者： Banssal, Aayush Sheikh, Yaser Ramanan, Deva Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781728132938

We introduce a data-driven model for interactively synthesizing in-the-wild images from semantic label input masks. Our approach is dramatically different from recent work in this space, in that we make use of no learning. Instead, our approach uses simple but classic tools for matching scene context, shapes, and parts to a stored library of exemplars. Though simple, this approach has several notable advantages over recent work: (1) because nothing is learned, it is not limited to specific training data distributions (such as cityscapes, facades, or faces);(2) it can synthesize arbitrarily high-resolution images, limited only by the resolution of the exemplar library;(3) by appropriately composing shapes and parts, it can generate an exponentially large set of viable candidate output images (that can say, be interactively searched by a user). We present results on the diverse COCO dataset, significantly outperforming learning-based approaches on standard image synthesis metrics. Finally, we explore user-interaction and user-controllability, demonstrating that our system can be used as a platform for user-driven content creation.

关键词： Big Data Grouping and Shape Image and Video Synthesis Large Scale Methods Segmentation vision + Graphics

来源：评论

学校读者我要写书评

暂无评论

2.5D Visual Sound 32

2.5D Visual Sound

引用

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

作者： Gao, Ruohan Grauman, Kristen Univ Texas Austin Austin TX 78712 USA Facebook AI Res Menlo Pk CA USA

ISBN: (纸本)9781728132938

Binaural audio provides a listener with 3D sound sensation, allowing a rich perceptual experience of the scene. However, binaural recordings are scarcely available and require nontrivial expertise and equipment to obtain. We propose to convert common monaural audio into binaural audio by leveraging video. The key idea is that visual frames reveal significant spatial cues that, while explicitly lacking in the accompanying single-channel audio, are strongly linked to it. Our multi-modal approach recovers this link from unlabeled video. We devise a deep convolutional neural network that learns to decode the monaural (single-channel) soundtrack into its binaural counterpart by injecting visual information about object and scene configurations. We call the resulting output 2.5D visual sound-the visual stream helps "lift" the flat single channel audio into spatialized sound. In addition to sound generation, we show the self-supervised representation learned by our network benefits audio-visual source separation.

关键词： Categorization recognition: Detection Representation Learning Retrieval Video Analytics

来源：评论

学校读者我要写书评

暂无评论

Incremental Object Learning from Contiguous Views 32

Incremental Object Learning from Contiguous Views

引用

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

作者： Stojanov, Stefan Mishra, Samarth Ngoc Anh Thai Dhanda, Nikhil Humayun, Ahmad Yu, Chen Smith, Linda B. Rehg, James M. Georgia Inst Technol Atlanta GA 30332 USA Indiana Univ Bloomington IN 47405 USA

ISBN: (纸本)9781728132938

In this work, we present CRIB (Continual recognition Inspired by Babies), a synthetic incremental object learning environment that can produce data that models visual imagery produced by object exploration in early infancy. CRIB is coupled with a new 3D object dataset, Toys-200, that contains 200 unique toy-like object instances, and is also compatible with existing 3D datasets. Through extensive empirical evaluation of state-of-the-art incremental learning algorithms, we find the novel empirical result that repetition can significantly ameliorate the effects of catastrophic forgetting. Furthermore, we find that in certain cases repetition allows for performance approaching that of batch learning algorithms. Finally, we propose an unsupervised incremental learning task with intriguing baseline results.

关键词： Categorization Datasets and Evaluation Deep Learning Image and Video Synthesis recognition: Detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

Factor Graph Attention 32

Factor Graph Attention

引用

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

作者： Schwartz, Idan Yu, Seunghak Hazan, Tamir Schwing, Alexander Technion Haifa Israel MIT CSAIL Cambridge MA USA UIUC Urbana IL USA Samsung Res Seoul South Korea

ISBN: (纸本)9781728132938

Dialog is an effective way to exchange information, but subtle details and nuances are extremely important. While significant progress has paved a path to address visual dialog with algorithms, details and nuances remain a challenge. Attention mechanisms have demonstrated compelling results to extract details in visual question answering and also provide a convincing framework for visual dialog due to their interpretability and effectiveness. However, the many data utilities that accompany visual dialog challenge existing attention techniques. We address this issue and develop a general attention mechanism for visual dialog which operates on any number of data utilities. To this end, we design a factor graph based attention mechanism which combines any number of utility representations. We illustrate the applicability of the proposed approach on the challenging and recently introduced VisDial datasets, outperforming recent state-of-the-art methods by 1.1% for VisDial0.9 and by 2% for VisDial1.0 on MRR. Our ensemble model improved the MRR score on VisDial1.0 by more than 6%.

关键词： vision + Language Visual Reasoning

来源：评论

学校读者我要写书评

暂无评论

Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks 32

Local to Global Learning: Gradually Adding Classes for Train...

引用

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

作者： Cheng, Hao Lian, Dongze Deng, Bowen Gao, Shenghua Tan, Tao Geng, Yanlin ShanghaiTech Univ Sch Informat Sci & Technol Shanghai 201210 Peoples R China Eindhoven Univ Technol Ctr Anal Dept Math & Comp Sci Eindhoven Netherlands Xidian Univ State Key Lab ISN Xian 710071 Shaanxi Peoples R China

ISBN: (纸本)9781728132938

We propose a new learning paradigm, Local to Global Learning (LGL), for Deep Neural Networks (DNNs) to improve the performance of classification problems. The core of LGL is to learn a DNN model from fewer categories (local) to more categories (global) gradually within the entire training set. LGL is most related to the Self-Paced Learning (SPL) algorithm but its formulation is different from SPL. SPL trains its data from simple to complex, while LGL from local to global. In this paper, we incorporate the idea of LGL into the learning objective of DNNs and explain why LGL works better from an information-theoretic perspective. Experiments on the toy data, CIFAR-I0, CIFAR-100, and ImageNet dataset show that LGL outperforms the baseline and SPL-based algorithms.

关键词： computer vision Theory Deep Learning Representation Learning Statistical Learning

来源：评论

学校读者我要写书评

暂无评论

A Bayesian Perspective on the Deep Image Prior 32

A Bayesian Perspective on the Deep Image Prior

引用

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

作者： Cheng, Zezhou Gadelha, Matheus Maji, Subhransu Sheldon, Daniel Univ Massachusetts Amherst MA 01003 USA

ISBN: (纸本)9781728132938

The deep image prior was recently introduced as a prior for natural images. It represents images as the output of a convolutional network with random inputs. For inference, gradient descent is performed to adjust network parameters to make the output match observations. This approach yields good performance on a range of image reconstruction tasks. We show that the deep image prior is asymptotically equivalent to a stationary Gaussian process prior in the limit as the number of channels in each layer of the network goes to infinity, and derive the corresponding kernel. This informs a Bayesian approach to inference. We show that by conducting posterior inference using stochastic gradient Langevin dynamics we avoid the need for early stopping, which is a drawback of the current approach, and improve results for denoising and impainting tasks. We illustrate these intuitions on a number of 1D and 2D signal reconstruction tasks.

关键词： Deep Learning Low-level vision Optimization Methods Statistical Learning

来源：评论

学校读者我要写书评

暂无评论

Triangulation Learning Network: from Monocular to Stereo 3D Object Detection 32

Triangulation Learning Network: from Monocular to Stereo 3D ...

引用

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

作者： Qin, Zengyi Wang, Jinglu Lu, Yan Tsinghua Univ Beijing Peoples R China Microsoft Res Beijing Peoples R China

ISBN: (纸本)9781728132938

In this paper, we study the problem of 3D object detection from stereo images, in which the key challenge is how to effectively utilize stereo information. Different from previous methods using pixel-level depth maps, we propose employing 3D anchors to explicitly construct object-level correspondences between the regions of interest in stereo images, from which the deep neural network learns to detect and triangulate the targeted object in 3D space. We also introduce a cost-efficient channel reweighting strategy that enhances representational features and weakens noisy signals to facilitate the learning process. All of these are flexibly integrated into a solid baseline detector that uses monocular images. We demonstrate that both the monocular baseline and the stereo triangulation learning network outperform the prior state-of-the-arts in 3D object detection and localization on the challenging KITTI dataset.

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

AIRD: Adversarial Learning Framework for Image Repurposing Detection 32

AIRD: Adversarial Learning Framework for Image Repurposing D...

引用

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

作者： Jaiswal, Ayush Wu, Yue Abd Almageed, Wael Masi, Iacopo Natarajan, Premkumar USC Informat Sci Inst Marina Del Rey CA 90292 USA

ISBN: (纸本)9781728132938

Image repurposing is a commonly used method for spreading misinformation on social media and online forums, which involves publishing untampered images with modified metadata to create rumors and further propaganda. While manual verification is possible, given vast amounts of verified knowledge available on the internet, the increasing prevalence and ease of this form of semantic manipulation call for the development of robust automatic ways of assessing the semantic integrity of multimedia data. In this paper, we present a novel method for image repurposing detection that is based on the real-world adversarial interplay between a bad actor who repurposes images with counterfeit metadata and a watchdog who verifies the semantic consistency between images and their accompanying metadata, where both players have access to a reference dataset of verified content, which they can use to achieve their goals. The proposed method exhibits state-of-the-art performance on location-identity, subject-identity and painting-artist verification, showing its efficacy across a diverse set of scenarios.

关键词： Deep Learning vision Applications and Systems

来源：评论

学校读者我要写书评

暂无评论

Dance with Flow: Two-in-One Stream Action Detection 32

Dance with Flow: Two-in-One Stream Action Detection

引用

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

作者： Zhao, Jiaojiao Snoek, Cees G. M. Univ Amsterdam Amsterdam Netherlands

ISBN: (纸本)9781728132938

The goal of this paper is to detect the spatio-temporal extent of an action. The two-stream detection network based on RGB and flow provides state-of-the-art accuracy at the expense of a large model-size and heavy computation. We propose to embed RGB and optical-flow into a single two in-one stream network with new layers. A motion condition layer extracts motion information from flow images, which is leveraged by the motion modulation layer to generate transformation parameters for modulating the low-level RGB features. The method is easily embedded in existing appearance- or two-stream action detection networks, and trained end-to-end. Experiments demonstrate that leveraging the motion condition to modulate RGB features improves detection accuracy. With only half the computation and parameters of the state-of-the-art two-stream methods, our two-in-one stream still achieves impressive results on UCF101-24, UCFSports and J-HMDB.

关键词： Action recognition

来源：评论

学校读者我要写书评

暂无评论

Semantically Aligned Bias Reducing Zero Shot Learning 32

Semantically Aligned Bias Reducing Zero Shot Learning

引用

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

作者： Paul, Akanksha Krishnan, Narayanan C. Munjal, Prateek Indian Inst Technol Ropar India

ISBN: (纸本)9781728132938

Zero shot learning (ZSL) aims to recognize unseen classes by exploiting semantic relationships between seen and unseen classes. Two major problems faced by ZSL algorithms are the hubness problem and the bias towards the seen classes. Existing ZSL methods focus on only one of these problems in the conventional and generalized ZSL setting. In this work, we propose a novel approach, Semantically Aligned Bias Reducing (SABR) ZSL, which focuses on solving both the problems. It overcomes the hubness problem by learning a latent space that preserves the semantic relationship between the labels while encoding the discriminating information about the classes. Further we also propose ways to reduce bias of the seen classes through a simple cross-validation process in the inductive setting and a novel weak transfer constraint in the transductive setting. Extensive experiments on three benchmark datasets suggest that the proposed model significantly outperforms existing state-of-the-art algorithms by similar to 1.5-9% in the conventional ZSL setting and by similar to 2-14% in the generalized ZSL for both the inductive and transductive settings.

关键词： Categorization Deep Learning recognition: Detection Retrieval

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86页 << < 10 11 12 13 14 15 16 17 18 19 > >>

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：