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

1,535 篇 会议
21 册 图书
13 篇 期刊文献

馆藏范围

1,569 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,449 篇 工学
- 1,046 篇 计算机科学与技术...
- 655 篇 机械工程
- 358 篇 电气工程
- 111 篇 软件工程
- 55 篇 控制科学与工程
- 49 篇 信息与通信工程
- 35 篇 光学工程
- 28 篇 仪器科学与技术
- 17 篇 网络空间安全
- 15 篇 生物工程
- 9 篇 生物医学工程（可授...
- 8 篇 电子科学与技术（可...
- 8 篇 安全科学与工程
- 7 篇 测绘科学与技术
- 4 篇 化学工程与技术
- 3 篇 建筑学
112 篇 医学
- 108 篇 临床医学
- 6 篇 基础医学(可授医学...
- 4 篇 特种医学
87 篇 理学
- 38 篇 物理学
- 34 篇 数学
- 24 篇 生物学
- 12 篇 统计学（可授理学、...
- 9 篇 系统科学
- 5 篇 化学
42 篇 管理学
- 32 篇 图书情报与档案管...
- 10 篇 管理科学与工程(可...
24 篇 艺术学
- 24 篇 设计学（可授艺术学...
19 篇 法学
- 19 篇 社会学
15 篇 文学
- 15 篇 新闻传播学
2 篇 教育学
2 篇 农学
1 篇 经济学

主题

528 篇 computer vision
139 篇 face recognition
135 篇 pattern recognit...
135 篇 feature extracti...
130 篇 cameras
129 篇 image segmentati...
128 篇 object recogniti...
115 篇 object detection
103 篇 training
98 篇 robustness
94 篇 images
92 篇 image recognitio...
90 篇 shape
90 篇 layout
84 篇 visualization
77 篇 image reconstruc...
76 篇 humans
70 篇 computer science
66 篇 computational mo...
66 篇 image classifica...

机构

23 篇 rhein westfal th...
18 篇 carnegie mellon ...
16 篇 chinese acad sci...
15 篇 stanford univ st...
14 篇 univ chinese aca...
11 篇 australian natl ...
11 篇 univ calif berke...
10 篇 univ sci & techn...
10 篇 mit cambridge ma...
10 篇 univ maryland co...
9 篇 microsoft res as...
9 篇 univ washington ...
8 篇 microsoft resear...
8 篇 microsoft res re...
8 篇 natl univ singap...
7 篇 chinese univ hon...
7 篇 tech univ munich...
6 篇 mpi intelligent ...
6 篇 kaust thuwal
6 篇 imperial coll lo...

作者

20 篇 leibe bastian
12 篇 ji qiang
10 篇 li stan z.
9 篇 pal umapada
8 篇 zhang lei
8 篇 chellappa rama
8 篇 lei zhen
8 篇 zafeiriou stefan...
8 篇 hu weiming
8 篇 hua gang
7 篇 ramanan deva
7 篇 wang xiaogang
7 篇 yan shuicheng
7 篇 mubarak shah
6 篇 van gool luc
6 篇 darrell trevor
6 篇 luiten jonathon
6 篇 pollefeys marc
6 篇 bischof horst
6 篇 ghanem bernard

语言

1,554 篇 英文
9 篇 土耳其文
2 篇 日文
2 篇 其他
1 篇 西班牙文
1 篇 中文

检索条件"任意字段=26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR"

共 1569 条记录，以下是521-530 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：

Weighted-Entropy-based Quantization for Deep Neural Networks 30

Weighted-Entropy-based Quantization for Deep Neural Networks

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Park, Eunhyeok Ahn, Junwhan Yoo, Sungjoo Seoul Natl Univ Comp & Memory Architecture Lab Seoul South Korea Seoul Natl Univ Design Automat Lab Seoul South Korea

ISBN: (纸本)9781538604571

Quantization is considered as one of the most effective methods to optimize the inference cost of neural network models for their deployment to mobile and embedded systems, which have tight resource constraints. In such approaches, it is critical to provide low-cost quantization under a tight accuracy loss constraint (e.g., 1%). In this paper, we propose a novel method for quantizing weights and activations based on the concept of weighted entropy. Unlike recent work on binary-weight neural networks, our approach is multi-bit quantization, in which weights and activations can be quantized by any number of bits depending on the target accuracy. this facilitates much more flexible exploitation of accuracy-performance trade-off provided by different levels of quantization. Moreover, our scheme provides an automated quantization flow based on conventional training algorithms, which greatly reduces the design-time effort to quantize the network. According to our extensive evaluations based on practical neural network models for image classification (AlexNet, GoogLeNet and ResNet-50/101), object detection (R-FCN with ResNet-50), and language modeling (an LSTM network), our method achieves significant reductions in both the model size and the amount of computation with minimal accuracy loss. Also, compared to existing quantization schemes, ours provides higher accuracy with a similar resource constraint and requires much lower design effort.

关键词： Quantization model size Neural network design effort Activation Embedded systems Neural Networks (computer) Drill bits

来源：评论

学校读者我要写书评

暂无评论

Commonly Uncommon: Semantic Sparsity in Situation recognition 30

Commonly Uncommon: Semantic Sparsity in Situation Recognitio...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Yatskar, Mark Ordonez, Vicente Zettlemoyer, Luke Farhadi, Ali Univ Washington Comp Sci & Engn Seattle WA 98195 USA Allen Inst Artificial Intelligence AI2 Seattle WA USA Univ Virginia Dept Comp Sci Charlottesville VA 22903 USA

ISBN: (纸本)9781538604571

Semantic sparsity is a common challenge in structured visual classification problems;when the output space is complex, the vast majority of the possible predictions are rarely, if ever, seen in the training set. this paper studies semantic sparsity in situation recognition, the task of producing structured summaries of what is happening in images, including activities, objects and the roles objects play within the activity. For this problem, we find empirically that most substructures required for prediction are rare, and current state-of-the-art model performance dramatically decreases if even one such rare substructure exists in the target output. We avoid many such errors by (1) introducing a novel tensor composition function that learns to share examples across substructures more effectively and (2) semantically augmenting our training data with automatically gathered examples of rarely observed outputs using web data. When integrated within a complete CRF-based structured prediction model, the tensor-based approach outperforms existing state of the art by a relative improvement of 2.11% and 4.40% on top-5 verb and noun-role accuracy, respectively. Adding 5 million images with our semantic augmentation techniques gives further relative improvements of 6.23% and 9.57% on top-5 verb and noun-role accuracy.

关键词： Commonly Uncommon Semantic Sparsity Situation recognition Substructures state of the art Semantics recognition (Psychology) images

来源：评论

学校读者我要写书评

暂无评论

CATS: A Color and thermal Stereo Benchmark 30

CATS: A Color and Thermal Stereo Benchmark

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Treible, Wayne Saponaro, Philip Sorensen, Scott Kolagunda, Abhishek O'Neal, Michael Phelan, Brian Sherbondy, Kelly Kambhamettu, Chandra Univ Delaware Newark DE 19716 USA US Army Res Lab Adelphi MD USA Vis Syst Inc Providence RI USA

ISBN: (纸本)9781538604571

Stereo matching is a well researched area using visible-band color cameras. thermal images are typically lower resolution, have less texture, and are noisier compared to their visible-band counterparts and are more challenging for stereo matching algorithms. Previous benchmarks for stereo matching either focus entirely on visible-band cameras or contain only a single thermal camera. We present the Color And thermal Stereo (CATS) benchmark, a dataset consisting of stereo thermal, stereo color, and cross-modality image pairs with high accuracy ground truth (< 2mm) generated from a LiDAR. We scanned 100 cluttered indoor and 80 outdoor scenes featuring challenging environments and conditions. CATS contains approximately 1400 images of pedestrians, vehicles, electronics, and other thermally interesting objects in different environmental conditions, including nighttime, daytime, and foggy scenes. Ground truth was projected to each of the four cameras to generate color-color, thermal-thermal, and cross-modality disparity maps. A semi-automatic LiDAR to camera alignment procedure was developed that does not require a calibration target. We compare state-of-the-art algorithms to baseline the dataset and show that in the thermal and cross modalities there is still much room for improvement. We expect our dataset to provide researchers with a more diverse set of imaged locations, objects, and modalities than previous benchmarks for stereo matching.

关键词： Cameras Laser radar Benchmark testing Image color analysis three-dimensional displays Cats Calibration Lidar Cats three-dimensional displays Benchmark testing Cameras image colour analysis FAM64A gene computer ASSISTED TRACKING SYSTEM Dataset BENCHMARKS thermal Calibration

来源：评论

学校读者我要写书评

暂无评论

Deep Co-occurrence Feature Learning for Visual Object recognition 30

Deep Co-occurrence Feature Learning for Visual Object Recogn...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Shih, Ya-Fang Yeh, Yang-Ming Lin, Yen-Yu Weng, Ming-Fang Lu, Yi-Chang Chuang, Yung-Yu Acad Sinica Res Ctr Informat Technol Innovat Taipei Taiwan Natl Taiwan Univ Dept Comp Sci & Informat Engn Taipei Taiwan Natl Taiwan Univ Grad Inst Elect Engn Taipei Taiwan Inst Informat Ind Smart Network Syst Inst Taipei Taiwan

ISBN: (纸本)9781538604571

this paper addresses three issues in integrating part-based representations into convolutional neural networks (CNNs) for object recognition. First, most part-based models rely on a few pre-specified object parts. However, the optimal object parts for recognition often vary from category to category. Second, acquiring training data with part-level annotation is labor-intensive. third, modeling spatial relationships between parts in CNNs often involves an exhaustive search of part templates over multiple network streams. We tackle the three issues by introducing a new network layer, called co-occurrence layer. It can extend a convolutional layer to encode the co-occurrence between the visual parts detected by the numerous neurons, instead of a few pre-specified parts. To this end, the feature maps serve as both filters and images, and mutual correlation filtering is conducted between them. the co-occurrence layer is end-to-end trainable. the resultant co-occurrence features are rotation-and translation-invariant, and are robust to object deformation. By applying this new layer to the VGG-16 and ResNet-152, we achieve the recognition rates of 83.6% and 85.8% on the Caltech-UCSD bird benchmark, respectively. the source code is available at https://github. com/yafangshih/Deep-COOC.

关键词： object recognition feature map network layer exhaustive search Source code end-to-end recognition (Psychology) Visualization Filters

来源：评论

学校读者我要写书评

暂无评论

Improving training of deep neural networks via Singular Value Bounding 30

Improving training of deep neural networks via Singular Valu...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Jia, Kui Tao, Dacheng Gao, Shenghua Xu, Xiangmin South China Univ Technol Sch Elect & Informat Engn Guangzhou Guangdong Peoples R China Univ Sydney UBTech Sydney AI Inst SIT FEIT Sydney NSW Australia ShanghaiTech Univ Sch Informat Sci & Technol Shanghai Peoples R China

ISBN: (纸本)9781538604571

Deep learning methods achieve great success recently on many computer vision problems. In spite of these practical successes, optimization of deep networks remains an active topic in deep learning research. In this work, we focus on investigation of the network solution properties that can potentially lead to good performance. Our research is inspired by theoretical and empirical results that use orthogonal matrices to initialize networks, but we are interested in investigating how orthogonal weight matrices perform when network training converges. To this end, we propose to constrain the solutions of weight matrices in the orthogonal feasible set during the whole process of network training, and achieve this by a simple yet effective method called Singular Value Bounding (SVB). In SVB, all singular values of each weight matrix are simply bounded in a narrow band around the value of 1. Based on the same motivation, we also propose Bounded Batch Normalization (BBN), which improves Batch Normalization by removing its potential risk of ill-conditioned layer transform. We present both theoretical and empirical results to justify our proposed methods. Experiments on benchmark image classification datasets show the efficacy of our proposed SVB and BBN. In particular, we achieve the state-of-the-art results of 3.06% error rate on CIFAR10 and 16.90% on CIFAR100, using off-the-shelf network architectures (Wide ResNets). Our preliminary results on ImageNet also show the promise in large- scale learning. We release the implementation code of our methods at ***/research/svb.

关键词： Training Machine learning Optimization computer vision Neural networks Standards Histograms

来源：评论

学校读者我要写书评

暂无评论

G²DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual recognition 30

G<SUP>2</SUP>DeNet: Global Gaussian Distribution Embedding N...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Wang, Qilong Li, Peihua Zhang, Lei Dalian Univ Technol Dalian Peoples R China Hong Kong Polytech Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781538604571

Recently, plugging trainable structural layers into deep convolutional neural networks (CNNs) as image representations has made promising progress. However, there has been little work on inserting parametric probability distributions, which can effectively model feature statistics, into deep CNNs in an end-to-end manner. this paper proposes a Global Gaussian Distribution embedding Network (G2DeNet) to take a step towards addressing this problem. the core of G2DeNet is a novel trainable layer of a global Gaussian as an image representation plugged into deep CNNs for end-to-end learning. the challenge is that the proposed layer involves Gaussian distributions whose space is not a linear space, which makes its forward and backward propagations be non-intuitive and non-trivial. To tackle this issue, we employ a Gaussian embedding strategy which respects the structures of both Riemannian manifold and smooth group of Gaussians. Based on this strategy, we construct the proposed global Gaussian embedding layer and decompose it into two sub-layers: the matrix partition sub-layer decoupling the mean vector and covariance matrix entangled in the embedding matrix, and the square-rooted, symmetric positive definite matrix sub-layer. In this way, we can derive the partial derivatives associated with the proposed structural layer and thus allow backpropagation of gradients. Experimental results on large scale region classification and fine-grained recognition tasks show that G2DeNet is superior to its counterparts, capable of achieving state-of-the-art performance.

关键词： G~2DeNet: Global Gaussian Application Visual recognition Gaussian distribution image representation embedding Gauss end-to-end PLUGGING back propagation

来源：评论

学校读者我要写书评

暂无评论

Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification 30

Learning Spatial Regularization with Image-level Supervision...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Zhu, Feng Li, Hongsheng Ouyang, Wanli Yu, Nenghai Wang, Xiaogang Univ Sci & Technol China Hefei Anhui Peoples R China Univ Sydney Sydney NSW Australia Chinese Univ Hong Kong Dept Elect Engn Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781538604571

Multi-label image classification is a fundamental but challenging task in computer vision. Great progress has been achieved by exploiting semantic relations between labels in recent years. However, conventional approaches are unable to model the underlying spatial relations between labels in multi-label images, because spatial annotations of the labels are generally not provided. In this paper, we propose a unified deep neural network that exploits both semantic and spatial relations between labels with only image-level supervisions. Given a multi-label image, our proposed Spatial Regularization Network (SRN) generates attention maps for all labels and captures the underlying relations between them via learnable convolutions. By aggregating the regularized classification results with original results by a ResNet-101 network, the classification performance can be consistently improved. the whole deep neural network is trained end-to-end with only image-level annotations, thus requires no additional efforts on image annotations. Extensive evaluations on 3 public datasets with different types of labels show that our approach significantly outperforms state-of-the-arts and has strong generalization capability. Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance.

关键词： dimensional relationship images Image classification Semantics computer vision ANNOTATIONS end-to-end

来源：评论

学校读者我要写书评

暂无评论

Deep Joint Rain Detection and Removal from a Single Image 30

Deep Joint Rain Detection and Removal from a Single Image

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Yang, Wenhan Tan, Robby T. Feng, Jiashi Liu, Jiaying Guo, Zongming Yan, Shuicheng Peking Univ Inst Comp Sci & Technol Beijing Peoples R China Natl Univ Singapore Singapore Singapore Yale NUS Coll Singapore Singapore 360 AI Inst Beijing Peoples R China

ISBN: (纸本)9781538604571

In this paper, we address a rain removal problem from a single image, even in the presence of heavy rain and rain streak accumulation. Our core ideas lie in our new rain image model and new deep learning architecture. We add a binary map that provides rain streak locations to an existing model, which comprises a rain streak layer and a background layer. We create a model consisting of a component representing rain streak accumulation (where individual streaks cannot be seen, and thus visually similar to mist or fog), and another component representing various shapes and directions of overlapping rain streaks, which usually happen in heavy rain. Based on the model, we develop a multi-task deep learning architecture that learns the binary rain streak map, the appearance of rain streaks, and the clean background, which is our ultimate output. the additional binary map is critically beneficial, since its loss function can provide additional strong information to the network. To handle rain streak accumulation (again, a phenomenon visually similar to mist or fog) and various shapes and directions of overlapping rain streaks, we propose a recurrent rain detection and removal network that removes rain streaks and clears up the rain accumulation iteratively and progressively. In each recurrence of our method, a new contextualized dilated network is developed to exploit regional contextual information and to produce better representations for rain detection. the evaluation on real images, particularly on heavy rain, shows the effectiveness of our models and architecture.

关键词： Rain Atmospheric modeling Shape Feature extraction Machine learning Image restoration computer vision rain Streak Atmospheric models images rainstorms image restoration technique computer vision Feature extraction mist NEBULISED fog fogs Shape

来源：评论

学校读者我要写书评

暂无评论

Not Afraid of the Dark: NIR-VIS Face recognition via Cross-spectral Hallucination and Low-rank Embedding 30

Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-s...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Lezama, Jose Qiu, Qiang Sapiro, Guillermo Univ Republica IIE Montevideo Uruguay Duke Univ ECE Durham NC 27706 USA

ISBN: (纸本)9781538604571

Surveillance cameras today often capture NIR (near in-frared) images in low-light environments. However, most face datasets accessible for training and verification are only collected in the VIS (visible light) spectrum. It remains a challenging problem to match NIR to VIS face images due to the different light spectrum. Recently, breakthroughs have been made for VIS face recognition by applying deep learning on a huge amount of labeled VIS face samples. the same deep learning approach cannot be simply applied to NIR face recognition for two main reasons: First, much limited NIR face images are available for training compared to the VIS spectrum. Second, face galleries to be matched are mostly available only in the VIS spectrum. In this paper, we propose an approach to extend the deep learning breakthrough for VIS face recognition to the NIR spectrum, without retraining the underlying deep models that see only VIS faces. Our approach consists of two core components, cross-spectral hallucination and low-rank embedding, to optimize respectively input and output of a VIS deep model for cross-spectral face recognition. Cross-spectral hallucination produces VIS faces from NIR images through a deep learning approach. Low-rank embedding restores a low-rank structure for faces deep features across both NIR and VIS spectrum. We observe that it is often equally effective to perform hallucination to input NIR images or low-rank embedding to output deep features for a VIS deep model for cross-spectral recognition. When hallucination and low-rank embedding are deployed together, we observe significant further improvement;we obtain state-of-the-art accuracy on the CASIA NIR-VIS v2.0 benchmark, without the need at all to re-train the recognition system.

关键词： Face Face recognition Neural networks Training Feature extraction Machine learning Image recognition

来源：评论

学校读者我要写书评

暂无评论

Removing rain from single images via a deep detail network 30

Removing rain from single images via a deep detail network

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Fu, Xueyang Huang, Jiabin Zeng, Delu Huang, Yue Ding, Xinghao Paisley, John Xiamen Univ Minist Educ Key Lab Underwater Acoust Commun & Marine Informa Xiamen Peoples R China Xiamen Univ Sch Informat Sci & Engn Xiamen Peoples R China South China Univ Technol Sch Math Guangzhou Guangdong Peoples R China Columbia Univ Dept Elect Engn New York NY 10027 USA Columbia Univ Data Sci Inst New York NY 10027 USA

ISBN: (纸本)9781538604571

We propose a new deep network architecture for removing rain streaks from individual images based on the deep convolutional neural network (CNN). Inspired by the deep residual network (ResNet) that simplifies the learning process by changing the mapping form, we propose a deep detail network to directly reduce the mapping range from input to output, which makes the learning process easier. To further improve the de-rained result, we use a priori image domain knowledge by focusing on high frequency detail during training, which removes background interference and focuses the model on the structure of rain in images. this demonstrates that a deep architecture not only has benefits for high-level vision tasks but also can be used to solve low-level imaging problems. though we train the network on synthetic data, we find that the learned network generalizes well to real-world test images. Experiments show that the proposed method significantly outperforms state-of-the-art methods on both synthetic and real-world images in terms of both qualitative and quantitative measures. We discuss applications of this structure to denoising and JPEG artifact reduction at the end of the paper.

关键词： images rain Learning processes NETWORK STRUCTURE Noise reduction synthetic data Network SYNthETICS Qualitative High-Level vision

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157页 << < 49 50 51 52 53 54 55 56 57 58 > >>

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：