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

383 篇 会议

馆藏范围

383 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

383 篇 工学
- 383 篇 计算机科学与技术...
2 篇 医学
- 2 篇 临床医学

主题

383 篇 recognition: det...
382 篇 categorization
380 篇 retrieval
200 篇 deep learning
81 篇 representation l...
38 篇 vision applicati...
35 篇 segmentation
35 篇 scene analysis a...
27 篇 grouping and sha...
24 篇 gesture
24 篇 face
23 篇 and body pose
23 篇 datasets and eva...
20 篇 3d from multivie...
19 篇 video analytics
17 篇 statistical lear...
17 篇 vision + languag...
16 篇 optimization met...
13 篇 robotics + drivi...
13 篇 others

机构

16 篇 univ chinese aca...
15 篇 chinese univ hon...
11 篇 sun yat sen univ...
11 篇 sensetime res pe...
11 篇 peng cheng lab p...
9 篇 huawei noahs ark...
9 篇 carnegie mellon ...
8 篇 univ sci & techn...
8 篇 tsinghua univ pe...
8 篇 johns hopkins un...
7 篇 facebook ai res ...
7 篇 sun yat sen univ...
7 篇 minist educ key ...
7 篇 nanyang technol ...
6 篇 cas ctr excellen...
6 篇 hong kong univ s...
6 篇 tencent youtu la...
6 篇 tech univ munich...
6 篇 univ calif berke...
6 篇 univ texas austi...

作者

7 篇 zheng wei-shi
7 篇 wang xiaogang
7 篇 lin dahua
6 篇 ji rongrong
6 篇 yan junjie
5 篇 grauman kristen
5 篇 lin liang
5 篇 doermann david
5 篇 shao ling
5 篇 liang xiaodan
4 篇 shan shiguang
4 篇 zhang baochang
4 篇 girshick ross
4 篇 loy chen change
4 篇 chen xilin
4 篇 rastegari mohamm...
4 篇 tian qi
4 篇 lu cewu
4 篇 ouyang wanli
4 篇 schiele bernt

语言

383 篇 英文

检索条件"主题词=Recognition: Detection"

共 383 条记录，以下是201-210 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：

Geometry-Aware Distillation for Indoor Semantic Segmentation 32

Geometry-Aware Distillation for Indoor Semantic Segmentation

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Jiao, Jianbo Wei, Yunchao Jie, Zequn Shi, Honghui Lau, Rynson Huang, Thomas S. Univ Oxford Dept Engn Sci Oxford OX1 2JD England UIUC Champaign IL USA Tencent AI Lab Bellevue WA USA IBM Res Armonk NY USA City Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781728132938

It has been shown that jointly reasoning the 2D appearance and 3D information from RGB-D domains is beneficial to indoor scene semantic segmentation. However, most existing approaches require accurate depth map as input to segment the scene which severely limits their applications. In this paper, we propose to jointly infer the semantic and depth information by distilling geometry-aware embedding to eliminate such strong constraint while still exploiting the helpful depth domain information. In addition, we use this learned embedding to improve the quality of semantic segmentation, through a proposed geometry-aware propagation framework followed by several multi-level skip feature fusion blocks. By decoupling the single task prediction network into two joint tasks of semantic segmentation and geometry embedding learning, together with the proposed information propagation and feature fusion architecture, our method is shown to perform favorably against state-of-the-art methods for semantic segmentation on publicly available challenging indoor datasets.

关键词： Categorization Deep Learning Grouping and Shape recognition: detection Retrieval Scene Analysis and Understanding Segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Sketch-Shape Hashing with Segmented 3D Stochastic Viewing 32

Deep Sketch-Shape Hashing with Segmented 3D Stochastic Viewi...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Chen, Jiaxin Qin, Jie Liu, Li Zhu, Fan Shen, Fumin Xie, Jin Shao, Ling Incept Inst Artificial Intelligence IIAI Abu Dhabi U Arab Emirates Univ Elect Sci & Technol China Chengdu Peoples R China Nanjing Univ Sci & Technol Nanjing Peoples R China

ISBN: (纸本)9781728132938

Sketch-based 3D shape retrieval has been extensively studied in recent works, most of which focus on improving the retrieval accuracy, whilst neglecting the efficiency. In this paper, we propose a novel framework for efficient sketch-based 3D shape retrieval, i.e., Deep Sketch-Shape Hashing (DSSH), which tackles the challenging problem from two perspectives. Firstly, we propose an intuitive 3D shape representation method to deal with unaligned shapes with arbitrary poses. Specifically, the proposed Segmented Stochastic-viewing Shape Network models discriminative 3D representations by a set of 2D images rendered from multiple views, which are stochastically selected from non-overlapping spatial segments of a 3D sphere. Secondly, Batch-Hard Binary Coding (BHBC) is developed to learn semantics-preserving compact binary codes by mining the hardest samples. The overall framework is jointly learned by developing an alternating iteration algorithm. Extensive experimental results on three benchmarks show that DSSH improves both the retrieval efficiency and accuracy remarkably, compared to the state-of-the-art methods.

关键词： 3D from Multiview and Sensors Categorization Deep Learning recognition: detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression 32

Exploiting Kernel Sparsity and Entropy for Interpretable CNN...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Li, Yuchao Lin, Shaohui Zhang, Baochang Liu, Jianzhuang Doermann, David Wu, Yongjian Huang, Feiyue Ji, Rongrong Xiamen Univ Sch Informat Sci & Engn Dept Cognit Sci Fujian Key Lab Sensing & Comp Smart City Xiamen Peoples R China Peng Cheng Lab Shenzhen Peoples R China Beihang Univ Beijing Peoples R China Huawei Noahs Ark Lab Hong Kong Peoples R China SUNY Buffalo Buffalo NY USA Tencent Technol Shanghai Co Ltd BestImage Shanghai Peoples R China

ISBN: (纸本)9781728132938

Compressing convolutional neural networks (CNNs) has received ever-increasing research focus. However, most existing CNN compression methods do not interpret their inherent structures to distinguish the implicit redundancy. In this paper, we investigate the problem of CNN compression from a novel interpretable perspective. The relationship between the input feature maps and 2D kernels is revealed in a theoretical framework, based on which a kernel sparsity and entropy (KSE) indicator is proposed to quantitate the feature map importance in a feature-agnostic manner to guide model compression. Kernel clustering is further conducted based on the KSE indicator to accomplish high-precision CNN compression. KSE is capable of simultaneously compressing each layer in an efficient way, which is significantly faster compared to previous data-driven feature map pruning methods. We comprehensively evaluate the compression and speedup of the proposed method on CIFAR-10, SVHN and ImageNet 2012. Our method demonstrates superior performance gains over previous ones. In particular, it achieves 4.7x FLOPs reduction and 2.9x compression on ResNet-50 with only a top-5 accuracy drop of 0.35% on ImageNet 2012, which significantly outperforms state-of-the-art methods.

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

Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation 32

Sliced Wasserstein Discrepancy for Unsupervised Domain Adapt...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Lee, Chen-Yu Batra, Tanmay Baig, Mohammad Haris Ulbricht, Daniel Apple Inc Cupertino CA 95014 USA

ISBN: (纸本)9781728132938

In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary [57] and the Wasserstein metric [72]. Our proposed sliced Wasserstein discrepancy (SWD) is designed to capture the natural notion of dissimilarity between the outputs of task-specific classifiers. It provides a geometrically meaningful guidance to detect target samples that are far from the support of the source and enables efficient distribution alignment in an end-to-end trainable fashion. In the experiments, we validate the effectiveness and genericness of our method on digit and sign recognition, image classification, semantic segmentation, and object detection.

关键词： Categorization Deep Learning recognition: detection Representation Learning Retrieval Scene Analysis and Understanding

来源：评论

学校读者我要写书评

暂无评论

AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations 32

AdaCos: Adaptively Scaling Cosine Logits for Effectively Lea...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Zhang, Xiao Zhao, Rui Qiao, Yu Wang, Xiaogang Li, Hongsheng Chinese Univ Hong Kong CUHK SenseTime Joint Lab Hong Kong Peoples R China SenseTime Res Hong Kong Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol SIAT SenseTime Joint Lab Shenzhen Peoples R China

ISBN: (纸本)9781728132938

The cosine-based softmax losses [21, 28, 39, 8] and their variants [40, 38, 7] achieve great success in deep learning based face recognition. However, hyperparameter settings in these losses have significant influences on the optimization path as well as the final recognition performance. Manually tuning those hyperparameters heavily relies on user experience and requires many training tricks. In this paper, we investigate in depth the effects of two important hyperparameters of cosine-based softmax losses, the scale parameter and angular margin parameter, by analyzing how they modulate the predicted classification probability. Based on these analysis, we propose a novel cosine-based softmax loss, AdaCos, which is hyperparameter-free and leverages an adaptive scale parameter to automatically strengthen the training supervisions during the training process. We apply the proposed AdaCos loss to large-scale face verification and identification datasets, including LFW [13], MegaFace [16], and IJB-C [23] 1:1 Verification. Our results show that training deep neural networks with the AdaCos loss is stable and able to achieve high face recognition accuracy. Our method outperforms state-of-the-art softmax losses [28, 40, 7] on all the three datasets.

关键词： And Body Pose Biometrics Categorization Deep Learning Face Gesture recognition: detection Representation Learn Retrieval

来源：评论

学校读者我要写书评

暂无评论

Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning 32

Iterative Reorganization with Weak Spatial Constraints: Solv...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Wei, Chen Xie, Lingxi Ren, Xutong Xia, Yingda Su, Chi Liu, Jiaying Tian, Qi Yuille, Alan L. Peking Univ Beijing Peoples R China Johns Hopkins Univ Baltimore MD 21218 USA Huawei Inc Noahs Ark Lab Shenzhen Guangdong Peoples R China Kingsoft Cloud Beijing Peoples R China

ISBN: (纸本)9781728132938

Learning visual features from unlabeled image data is an important yet challenging task, which is often achieved by training a model on some annotation-free information. We consider spatial contexts, for which we solve so-called jigsaw puzzles, i.e., each image is cut into grids and then disordered, and the goal is to recover the correct configuration. Existing approaches formulated it as a classification task by defining a fixed mapping from a small subset of configurations to a class set, but these approaches ignore the underlying relationship between different configurations and also limit their applications to more complex scenarios. This paper presents a novel approach which applies to jigsaw puzzles with an arbitrary grid size and dimensionality. We provide a fundamental and generalized principle, that weaker cues are easier to be learned in an unsupervised manner and also transfer better. In the context of puzzle recognition, we use an iterative manner which, instead of solving the puzzle all at once, adjusts the order of the patches in each step until convergence. In each step, we combine both unary and binary features of each patch into a cost function judging the correctness of the current configuration. Our approach, by taking similarity between puzzles into consideration, enjoys a more efficient way of learning visual knowledge. We verify the effectiveness of our approach from two aspects. First, it solves arbitrarily complex puzzles, including high-dimensional puzzles, that prior methods are difficult to handle. Second, it serves as a reliable way of network initialization, which leads to better transfer performance in visual recognition tasks including classification, detection and segmentation.

关键词： Categorization recognition: detection Representation Learning Retrieval

来源：评论

学校读者我要写书评

暂无评论

Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression 32

Generalized Intersection over Union: A Metric and A Loss for...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Rezatofighi, Hamid Tsoi, Nathan Gwak, JunYoung Sadeghian, Amir Reid, Ian Savarese, Silvio Stanford Univ Dept Comp Sci Stanford CA 94305 USA Univ Adelaide Sch Comp Sci Adelaide SA Australia Aibee Inc Palo Alto CA USA

ISBN: (纸本)9781728132938

Intersection over Union (IoU) is the most popular evaluation metric used in the object detection benchmarks. However, there is a gap between optimizing the commonly used distance losses for regressing the parameters of a bounding box and maximizing this metric value. The optimal objective for a metric is the metric itself. In the case of axisaligned 2D bounding boxes, it can be shown that IoU can be directly used as a regression loss. However, IoU has a plateau making it infeasible to optimize in the case of non-overlapping bounding boxes. In this paper, we address the weaknesses of IoU by introducing a generalized version as both a new loss and a new metric. By incorporating this generalized IoU (GIoU) as a loss into the state-of-the-art object detection frameworks, we show a consistent improvement on their performance using both the standard, IoU based, and new, GIoU based, performance measures on popular object detection benchmarks such as PASCAL VOC and MS COCO.

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

Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning 32

Revisiting Local Descriptor based Image-to-Class Measure for...

引用

IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Li, Wenbin Wang, Lei Xu, Jinglin Huo, Jing Gao, Yang Luo, Jiebo Nanjing Univ Nanjing Peoples R China Univ Wollongong Wollongong NSW Australia Northwestern Polytech Univ Xian Peoples R China Univ Rochester Rochester NY 14627 USA

ISBN: (纸本)9781728132938

Few-shot learning in image classification aims to learn a classifier to classify images when only few training examples are available for each class. Recent work has achieved promising classification performance, where an image-level feature based measure is usually used. In this paper we argue that a measure at such a level may not be effective enough in light of the scarcity of examples in few-shot learning. Instead, we think a local descriptor based image-to-class measure should be taken, inspired by its surprising success in the heydays of local invariant features. Specifically, building upon the recent episodic training mechanism, we propose a Deep Nearest Neighbor Neural Network (DN4 in short) and train it in an end-to-end manner. Its key difference from the literature is the replacement of the image-level feature based measure in the final layer by a local descriptor based image-to-class measure. This measure is conducted online via a k-nearest neighbor search over the deep local descriptors of convolutional feature maps. The proposed DN4 not only learns the optimal deep local descriptors for the image-to-class measure, but also utilizes the higher efficiency of such a measure in the case of example scarcity, thanks to the exchangeability of visual patterns across the images in the same class. Our work leads to a simple, effective, and computationally efficient framework for few-shot learning. Experimental study on benchmark datasets consistently shows its superiority over the related state-of-the-art, with the largest absolute improvement of 17% over the next best.

关键词： Categorization recognition: detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction 32

Hierarchy Denoising Recursive Autoencoders for 3D Scene Layo...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Shi, Yifei Chang, Angel Xuan Wu, Zhelun Savva, Manolis Xu, Kai Natl Univ Def Technol Changsha Hunan Peoples R China Simon Fraser Univ Burnaby BC Canada Princeton Univ Princeton NJ 08544 USA

ISBN: (纸本)9781728132938

Indoor scenes exhibit rich hierarchical structure in 3D object layouts. Many tasks in 3D scene understanding can benefit from reasoning jointly about the hierarchical context of a scene, and the identities of objects. We present a variational denoising recursive autoencoder (VDRAE) that generates and iteratively refines a hierarchical representation of 3D object layouts, interleaving bottom-up encoding for context aggregation and top-down decoding for propagation. We train our VDRAE on large-scale 3D scene datasets to predict both instance-level segmentations and a 3D object detections from an over-segmentation of an input point cloud. We show that our VDRAE improves object detection performance on real-world 3D point cloud datasets compared to baselines from prior work.

关键词： Categorization Grouping and Shape recognition: detection Retrieval Scene Analysis and Understanding Segmentation

来源：评论

学校读者我要写书评

暂无评论

Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples 32

Feature Distillation: DNN-Oriented JPEG Compression Against ...

引用

IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Liu, Zihao Liu, Qi Liu, Tao Xu, Nuo Lin, Xue Wang, Yanzhi Wen, Wujie Florida Int Univ Miami FL 33199 USA Northeastern Univ Boston MA 02115 USA

ISBN: (纸本)9781728132938

Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently. However, prior works mainly rely on directly tuning parameters like compression rate, to blindly reduce image features, thereby lacking guarantee on both defense efficiency (i.e. accuracy of polluted images) and classification accuracy of benign images, after applying defense methods. To overcome these limitations, we propose a JPEG-based defensive compression framework, namely "feature distillation", to effectively rectify adversarial examples without impacting classification accuracy on benign data. Our framework significantly escalates the defense efficiency with marginal accuracy reduction using a two-step method: First, we maximize malicious features filtering of adversarial input perturbations by developing defensive, quantization infrequency domain of JPEG compression or decompression, guided by a semi-analytical method;Second, we suppress the distortions of benign features to restore classification accuracy through a DNN-oriented quantization refine process. Our experimental results show that proposed "feature distillation " can significantly surpass the latest input-transformation based mitigations such as Quilting and TV Minimization in three aspects, including defense efficiency (improve classification accuracy from similar to 20% to similar to 90% on adversarial examples), accuracy of benign images after defense (<= 1% accuracy degradation), and processing time per image (similar to 259 x Speedup). Moreover, our solution can also provide the best defense efficiency (similar to 60% accuracy) against the recent adaptive attack with least accuracy reduction (similar to 1%) on benign images when compared with other input-transformation based defense methods.

关键词： Categorization Others 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39页 << < 17 18 19 20 21 22 23 24 25 26 > >>

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：