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

23,135 篇 会议
91 篇 期刊文献
15 册 图书

馆藏范围

23,240 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,631 篇 工学
- 11,162 篇 计算机科学与技术...
- 3,337 篇 软件工程
- 2,414 篇 机械工程
- 1,662 篇 光学工程
- 1,204 篇 电气工程
- 973 篇 控制科学与工程
- 738 篇 信息与通信工程
- 381 篇 仪器科学与技术
- 322 篇 生物工程
- 239 篇 生物医学工程（可授...
- 188 篇 电子科学与技术（可...
- 109 篇 化学工程与技术
- 104 篇 安全科学与工程
- 99 篇 测绘科学与技术
- 85 篇 建筑学
- 82 篇 土木工程
- 82 篇 交通运输工程
- 56 篇 力学（可授工学、理...
3,696 篇 医学
- 3,684 篇 临床医学
- 76 篇 基础医学(可授医学...
3,137 篇 理学
- 1,880 篇 物理学
- 1,604 篇 数学
- 547 篇 统计学（可授理学、...
- 466 篇 生物学
- 243 篇 系统科学
- 107 篇 化学
491 篇 管理学
- 290 篇 图书情报与档案管...
- 212 篇 管理科学与工程(可...
- 74 篇 工商管理
252 篇 艺术学
- 251 篇 设计学（可授艺术学...
58 篇 法学
38 篇 农学
25 篇 教育学
19 篇 经济学
10 篇 军事学
3 篇 文学

主题

10,396 篇 computer vision
3,893 篇 pattern recognit...
3,101 篇 training
2,104 篇 computational mo...
1,898 篇 visualization
1,800 篇 cameras
1,487 篇 feature extracti...
1,475 篇 three-dimensiona...
1,464 篇 shape
1,447 篇 image segmentati...
1,287 篇 robustness
1,234 篇 computer archite...
1,213 篇 semantics
1,112 篇 benchmark testin...
1,111 篇 conferences
1,104 篇 layout
1,093 篇 object detection
1,085 篇 computer science
1,026 篇 codes
907 篇 face recognition

机构

137 篇 univ sci & techn...
124 篇 univ chinese aca...
121 篇 chinese univ hon...
108 篇 tsinghua univers...
108 篇 carnegie mellon ...
105 篇 microsoft resear...
97 篇 zhejiang univ pe...
91 篇 swiss fed inst t...
85 篇 university of sc...
84 篇 zhejiang univers...
81 篇 shanghai ai lab ...
79 篇 university of ch...
75 篇 shanghai jiao to...
69 篇 microsoft res as...
68 篇 alibaba grp peop...
66 篇 adobe research
65 篇 national laborat...
64 篇 peking univ peop...
61 篇 univ oxford oxfo...
59 篇 peng cheng labor...

作者

80 篇 van gool luc
71 篇 timofte radu
65 篇 zhang lei
43 篇 luc van gool
40 篇 yang yi
37 篇 loy chen change
34 篇 li stan z.
33 篇 liu yang
33 篇 xiaoou tang
33 篇 murino vittorio
33 篇 chen chen
33 篇 qi tian
33 篇 li fei-fei
32 篇 tian qi
32 篇 sun jian
30 篇 ying shan
30 篇 pascal fua
29 篇 darrell trevor
28 篇 li xin
28 篇 hanqing lu

语言

23,162 篇 英文
52 篇 其他
20 篇 中文
5 篇 土耳其文
2 篇 日文

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

共 23241 条记录，以下是4961-4970 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：

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization

MultiBodySync: Multi-Body Segmentation and Motion Estimation...

引用

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

作者： Huang, Jiahui Wang, He Birdal, Tolga Sung, Minhyuk Arrigoni, Federica Hu, Shi-Min Guibas, Leonidas Tsinghua Univ Beijing Peoples R China Stanford Univ Stanford CA 94305 USA Korea Adv Inst Sci & Technol Daejeon South Korea Univ Trento Trento TN Italy

ISBN: (纸本)9781665445092

We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The two non-trivial challenges posed by this multi-scan multibody setting that we investigate are: (i) guaranteeing correspondence and segmentation consistency across multiple input point clouds capturing different spatial arrangements of bodies or body parts;and (ii) obtaining robust motion-based rigid body segmentation applicable to novel object categories. We propose an approach to address these issues that incorporates spectral synchronization into an iterative deep declarative network, so as to simultaneously recover consistent correspondences as well as motion segmentation. At the same time, by explicitly disentangling the correspondence and motion segmentation estimation modules, we achieve strong generalizability across different object categories. Our extensive evaluations demonstrate that our method is effective on various datasets ranging from rigid parts in articulated objects to individually moving objects in a 3D scene, be it single-view or full point clouds. Code at https: //***/huangjh-pub/multibody-sync.

关键词： computer vision Three-dimensional displays Motion segmentation Scalability Motion estimation Pipelines Dynamics

来源：评论

学校读者我要写书评

暂无评论

SimPoE: Simulated Character Control for 3D Human Pose Estimation

SimPoE: Simulated Character Control for 3D Human Pose Estima...

引用

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

作者： Yuan, Ye Wei, Shih-En Simon, Tomas Kitani, Kris Saragih, Jason Carnegie Mellon Univ Pittsburgh PA 15213 USA Facebook Real Labs Redmond WA USA

ISBN: (纸本)9781665445092

Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces). To demonstrate this, we present SimPoE, a Simulation-based approach for 3D human Pose Estimation, which integrates image-based kinematic inference and physics-based dynamics modeling. SimPoE learns a policy that takes as input the current frame pose estimate and the next image frame to control a physically-simulated character to output the next-frame pose estimate. The policy contains a learnable kinematic pose refinement unit that uses 2D keypoints to iteratively refine its kinematic pose estimate of the next frame. Based on this refined kinematic pose, the policy learns to compute dynamics-based control (e.g., joint torques) of the character to advance the current frame pose estimate to the pose estimate of the next frame. This design couples the kinematic pose refinement unit with the dynamics-based control generation unit, which are learned jointly with reinforcement learning to achieve accurate and physically-plausible pose estimation. Furthermore, we propose a meta-control mechanism that dynamically adjusts the character's dynamics parameters based on the character state to attain more accurate pose estimates. Experiments on large-scale motion datasets demonstrate that our approach establishes the new state of the art in pose accuracy while ensuring physical plausibility.

关键词： Solid modeling computer vision Three-dimensional displays Pose estimation Dynamics Kinematics Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learning to Fuse Asymmetric Feature Maps in Siamese Trackers

Learning to Fuse Asymmetric Feature Maps in Siamese Trackers

引用

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

作者： Han, Wencheng Dong, Xingping Khan, Fahad Shahbaz Shao, Ling Shen, Jianbing Beijing Inst Technol Beijing Peoples R China Incept Inst Artificial Intelligence Abu Dhabi U Arab Emirates Mohamed Bin Zayed Univ Artificial Intelligence Abu Dhabi U Arab Emirates

ISBN: (纸本)9781665445092

Recently, Siamese-based trackers have achieved promising performance in visual tracking. Most recent Siamese-based trackers typically employ a depth-wise cross-correlation (DW-XCorr) to obtain multi-channel correlation information from the two feature maps (target and search region). However, DW-XCorr has several limitations within Siamese-based tracking: it can easily be fooled by distractors, has fewer activated channels and provides weak discrimination of object boundaries. Further, DW-XCorr is a handcrafted parameter-free module and cannot fully benefit from offline learning on large-scale data. We propose a learnable module, called the asymmetric convolution (ACM), which learns to better capture the semantic correlation information in offline training on largescale data. Different from DW-XCorr and its predecessor (XCorr), which regard a single feature map as the convolution kernel, our ACM decomposes the convolution operation on a concatenated feature map into two mathematically equivalent operations, thereby avoiding the need for the feature maps to be of the same size (width and height) during concatenation. Our ACM can incorporate useful prior information, such as bounding-box size, with standard visual features. Furthermore, ACM can easily be integrated into existing Siamese trackers based on DW-XCorr or XCorr. To demonstrate its generalization ability, we integrate ACM into three representative trackers: SiamFC, SiamRPN++ and SiamBAN. Our experiments reveal the benefits of the proposed ACM, which outperforms existing methods on six tracking benchmarks. On the LaSOT test set, our ACM-based tracker obtains a significant improvement of 5.8% in terms of success (AUC), over the baseline.

关键词： Training Visualization Target tracking Correlation Convolution Fuses pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Improving OCR-based Image Captioning by Incorporating Geometrical Relationship

Improving OCR-based Image Captioning by Incorporating Geomet...

引用

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

作者： Wang, Jing Tang, Jinhui Yang, Mingkun Bai, Xiang Luo, Jiebo Nanjing Univ Sci & Technol Nanjing Peoples R China Huazhong Univ Sci & Technol Wuhan Peoples R China Univ Rochester Rochester NY 14627 USA

ISBN: (纸本)9781665445092

OCR-based image captioning aims to automatically describe images based on all the visual entities (both visual objects and scene text) in images. Compared with conventional image captioning, the reasoning of scene text is required for OCR-based image captioning since the generated descriptions often contain multiple OCR tokens. Existing methods attempt to achieve this goal via encoding the OCR tokens with rich visual and semantic representations. However, strong correlations between OCR tokens may not be established with such limited representations. In this paper, we propose to enhance the connections between OCR tokens from the viewpoint of exploiting the geometrical relationship. We comprehensively consider the height, width, distance, IoU and orientation relations between the OCR tokens for constructing the geometrical relationship. To integrate the learned relation as well as the visual and semantic representations into a unified framework, a Long Short-Term Memory plus Relation-aware pointer network (LSTM-R) architecture is presented in this paper. Under the guidance of the geometrical relationship between OCR tokens, our LSTM-R capitalizes on a newly-devised relation-aware pointer network to select OCR tokens from the scene text for OCR-based image captioning. Extensive experiments demonstrate the effectiveness of our LSTM-R. More remarkably, LSTM-R achieves state-of-the-art performance on TextCaps, with the CIDEr-D score being increased from 98.0% to 109.3%.

关键词： Training Visualization computer vision Correlation Computational modeling Semantics computer architecture

来源：评论

学校读者我要写书评

暂无评论

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

Rethinking Semantic Segmentation from a Sequence-to-Sequence...

引用

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

作者： Zheng, Sixiao Lu, Jiachen Zhao, Hengshuang Zhu, Xiatian Luo, Zekun Wang, Yabiao Fu, Yanwei Feng, Jianfeng Xiang, Tao Torr, Philip H. S. Zhang, Li Fudan Univ Shanghai Peoples R China Univ Oxford Oxford England Univ Surrey Guildford Surrey England Tencent Youtu Lab Shanghai Peoples R China Facebook AI Menlo Pk CA USA

ISBN: (纸本)9781665445092

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (i.e., without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE2OK test server leaderboard on the day of submission.

关键词： Image segmentation Visualization Semantics Transformers Decoding pattern recognition Servers

来源：评论

学校读者我要写书评

暂无评论

Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification

Farewell to Mutual Information: Variational Distillation for...

引用

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

作者： Tian, Xudong Zhang, Zhizhong Lin, Shaohui Qu, Yanyun Xie, Yuan Ma, Lizhuang East China Normal Univ Shanghai Peoples R China Xiamen Univ Xiamen Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China

ISBN: (纸本)9781665445092

The Information Bottleneck (IB) provides an information theoretic principle for representation learning, by retaining all information relevant for predicting label while minimizing the redundancy. Though IB principle has been applied to a wide range of applications, its optimization remains a challenging problem which heavily relies on the accurate estimation of mutual information. In this paper, we present a new strategy, Variational Self-Distillation (VSD), which provides a scalable, flexible and analytic solution to essentially fitting the mutual information but without explicitly estimating it. Under rigorously theoretical guarantee, VSD enables the IB to grasp the intrinsic correlation between representation and label for supervised training. Furthermore, by extending VSD to multi-view learning, we introduce two other strategies, Variational Cross-Distillation (VCD) and Variational Mutual-Learning (VML), which significantly improve the robustness of representation to viewchanges by eliminating view-specific and task-irrelevant information. To verify our theoretically grounded strategies, we apply our approaches to cross-modal person Re-ID, and conduct extensive experiments, where the superior performance against state-of-the-art methods are demonstrated. Our intriguing findings highlight the need to rethink the way to estimate mutual information.

关键词： Training Correlation Fitting Redundancy Estimation Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Not just Compete, but Collaborate: Local Image-to-Image Translation via Cooperative Mask Prediction

Not just Compete, but Collaborate: Local Image-to-Image Tran...

引用

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

作者： Kim, Daejin Khan, Mohammad Azam Choo, Jaegul Korea Adv Inst Sci & Technol Daejeon South Korea Dhaka Power Distribut Co Ltd Dhaka Bangladesh

ISBN: (纸本)9781665445092

Facial attribute editing aims to manipulate the image with the desired attribute while preserving the other details. Recently, generative adversarial networks along with the encoder-decoder architecture have been utilized for this task owing to their ability to create realistic images. However, the existing methods for the unpaired dataset cannot still preserve the attribute-irrelevant regions properly due to the absence of the ground truth image. This work proposes a novel, intuitive loss function called the CAM-consistency loss, which improves the consistency of an input image in image translation. While the existing cycle-consistency loss ensures that the image can be translated back, our approach makes the model further preserve the attribute-irrelevant regions even in a single translation to another domain by using the Grad-CAM output computed from the discriminator. Our CAM-consistency loss directly optimizes such a Grad-CAM output from the discriminator during training, in order to properly capture which local regions the generator should change while keeping the other regions unchanged. In this manner, our approach allows the generator and the discriminator to collaborate with each other to improve the image translation quality. In our experiments, we validate the effectiveness and versatility of our proposed CAM-consistency loss by applying it to several representative models for facial image editing, such as StarGAN, AttGAN, and STGAN.

关键词： Training computer vision Computational modeling computer architecture Predictive models Generative adversarial networks Generators

来源：评论

学校读者我要写书评

暂无评论

Isolated Sign Language recognition with Multi-Scale Spatial-Temporal Graph Convolutional Networks

Isolated Sign Language Recognition with Multi-Scale Spatial-...

引用

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

作者： Vazquez-Enriquez, Manuel Alba-Castro, Jose L. Docio-Fernandez, Laura Rodriguez-Banga, Eduardo Univ Vigo AtlanTTic Res Ctr Vigo 36310 Spain

ISBN: (纸本)9781665448994

Isolated Sign Language recognition (ISLR) fits nicely in the domain of problems that can be handled by graph-structured spatial-temporal algorithms. A recent multi-scale spatial-temporal graph convolution operator, MS-G3D, takes advantage of the semantic connectivity among non-neighbor nodes of the graph in a flexible temporal scale, which results in improved performance in classical Human Action recognition datasets. In this work, we present a solution for ISLR using a skeleton graph that includes body and finger joints and makes use of this specific property of MS-G3D, which seems crucial to capture the internal relationship among semantically connected distant nodes in sign language dynamics. To complete the analysis, we compare the results with a 3D-CNN architecture, S3D, already used for SLR, and fuse it with MS-G3D. The performance achieved on the AUTSL dataset shows that MS-G3D alone stands out as a viable technique for ISLR. In fact, the improvement after fusing with a 3D-CNN approach, at least on this medium-scale dataset, appears marginal. The transfer learning capability of the trained models is also explored using pre-training with the larger WLASL dataset and post-training with the smaller LSE_UVIGO dataset. The classification performance based on the MS-G3D model over AUTSL does not benefit from pre-training with WLASL, but the performance on the more similarly acquired LSE UVIGO dataset improves significantly from fine-tuning the MS-G3D AUTSL model.

关键词： computer vision Fuses Convolution Assistive technology Computational modeling conferences Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Group-aware Label Transfer for Domain Adaptive Person Re-identification

Group-aware Label Transfer for Domain Adaptive Person Re-ide...

引用

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

作者： Zheng, Kecheng Liu, Wu He, Lingxiao Mei, Tao Luo, Jiebo Zha, Zheng-Jun Univ Sci & Technol China Hefei Peoples R China AI Res JD Mountain View CA USA Univ Rochester Rochester NY 14627 USA

ISBN: (纸本)9781665445092

Unsupervised Domain Adaptive (UDA) person reidentification (ReID) aims at adapting the model trained on a labeled source-domain dataset to a target-domain dataset without any further annotations. Most successful UDA-ReID approaches combine clustering-based pseudo-label prediction with representation learning and perform the two steps in an alternating fashion. However, offline interaction between these two steps may allow noisy pseudo labels to substantially hinder the capability of the model. In this paper, we propose a Group-aware Label Transfer (GLT) algorithm, which enables the online interaction and mutual promotion of pseudo-label prediction and representation learning. Specifically, a label transfer algorithm simultaneously uses pseudo labels to train the data while refining the pseudo labels as an online clustering algorithm. It treats the online label refinery problem as an optimal transport problem, which explores the minimum cost for assigning M samples to N pseudo labels. More importantly, we introduce a group-aware strategy to assign implicit attribute group IDs to samples. The combination of the online label refining algorithm and the group-aware strategy can better correct the noisy pseudo label in an online fashion and narrow down the search space of the target identity. The effectiveness of the proposed GLT is demonstrated by the experimental results (Rank-1 accuracy) for Market1501 -> DukeMTMC (82.0%) and DukeMTMC -> Market1501 (92.2%), remarkably closing the gap between unsupervised and supervised performance on person re-identification. (1)

关键词： Training computer vision Costs Annotations Refining Clustering algorithms Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection

Glance and Gaze: Inferring Action-aware Points for One-Stage...

引用

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

作者： Zhong, Xubin Qu, Xian Ding, Changxing Tao, Dacheng South China Univ Technol Guangzhou Peoples R China Pazhou Lab Guangzhou Peoples R China Univ Sydney Sydney NSW Australia

ISBN: (纸本)9781665445092

Modern human-object interaction (HOI) detection approaches can be divided into one-stage methods and two-stage ones. One-stage models are more efficient due to their straightforward architectures, but the two-stage models are still advantageous in accuracy. Existing one-stage models usually begin by detecting predefined interaction areas or points, and then attend to these areas only for interaction prediction;therefore, they lack reasoning steps that dynamically search for discriminative cues. In this paper, we propose a novel one-stage method, namely Glance and Gaze Network (GGNet), which adaptively models a set of action-aware points (ActPoints) via glance and gaze steps. The glance step quickly determines whether each pixel in the feature maps is an interaction point. The gaze step leverages feature maps produced by the glance step to adaptively infer ActPoints around each pixel in a progressive manner. Features of the refined ActPoints are aggregated for interaction prediction. Moreover, we design an action-aware approach that effectively matches each detected interaction with its associated human-object pair, along with a novel hard negative attentive loss to improve the optimization of GGNet. All the above operations are conducted simultaneously and efficiently for all pixels in the feature maps. Finally, GGNet outperforms state-of-the-art methods by significant margins on both V-COCO and HICO-DET benchmarks. Code of GGNet is available at https://***/SherlockHolmes221/GGNet.

关键词： Adaptation models Visualization computer vision Codes Color Predictive models Feature extraction

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：