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

3,317 篇 会议
3 篇 期刊文献

馆藏范围

3,320 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,915 篇 工学
- 1,820 篇 计算机科学与技术...
- 376 篇 软件工程
- 142 篇 机械工程
- 136 篇 光学工程
- 42 篇 生物工程
- 28 篇 信息与通信工程
- 11 篇 控制科学与工程
- 9 篇 电气工程
- 9 篇 电子科学与技术（可...
- 9 篇 化学工程与技术
- 9 篇 交通运输工程
- 8 篇 生物医学工程（可授...
- 7 篇 安全科学与工程
- 4 篇 材料科学与工程（可...
- 4 篇 建筑学
- 3 篇 土木工程
- 3 篇 农业工程
174 篇 理学
- 136 篇 物理学
- 43 篇 生物学
- 29 篇 数学
- 16 篇 统计学（可授理学、...
- 10 篇 化学
29 篇 医学
- 28 篇 临床医学
- 3 篇 基础医学(可授医学...
15 篇 管理学
- 8 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
- 3 篇 工商管理
5 篇 法学
- 3 篇 社会学
- 2 篇 法学
2 篇 教育学
- 2 篇 教育学
2 篇 农学
1 篇 经济学

主题

1,179 篇 computer vision
801 篇 conferences
570 篇 training
484 篇 pattern recognit...
330 篇 computational mo...
279 篇 computer archite...
255 篇 visualization
180 篇 feature extracti...
160 篇 neural networks
153 篇 semantics
152 篇 task analysis
145 篇 cameras
143 篇 deep learning
140 篇 three-dimensiona...
139 篇 benchmark testin...
126 篇 low-level vision
117 篇 vision
115 篇 language
113 篇 image segmentati...
112 篇 estimation

机构

35 篇 tsinghua univ pe...
34 篇 univ sci & techn...
28 篇 shanghai ai lab ...
26 篇 chinese univ hon...
25 篇 university of sc...
25 篇 tsinghua univers...
24 篇 peng cheng labor...
23 篇 swiss fed inst t...
23 篇 swiss fed inst t...
23 篇 peng cheng lab p...
22 篇 zhejiang univ pe...
22 篇 carnegie mellon ...
20 篇 univ chinese aca...
20 篇 university of ch...
18 篇 harbin inst tech...
18 篇 shanghai jiao to...
18 篇 sensetime res pe...
16 篇 hong kong univ s...
15 篇 fudan univ peopl...
14 篇 national key lab...

作者

60 篇 timofte radu
26 篇 radu timofte
19 篇 van gool luc
16 篇 lei lei
15 篇 loy chen change
15 篇 qiao yu
14 篇 fan haoqiang
13 篇 zhang yulun
13 篇 liu shuaicheng
13 篇 luc van gool
12 篇 chen chen
12 篇 chen wei-ting
12 篇 li chongyi
11 篇 wangmeng zuo
11 篇 pan jinshan
11 篇 marcos v. conde
10 篇 wei dong
10 篇 zhou shangchen
10 篇 suiyi zhao
10 篇 yu lei

语言

3,319 篇 英文
1 篇 其他

检索条件"任意字段=2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023"

共 3320 条记录，以下是3201-3210 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：

Uncertainty-Aware vision-Based Metric Cross-View Geolocalization

Uncertainty-Aware Vision-Based Metric Cross-View Geolocaliza...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Florian Fervers Sebastian Bullinger Christoph Bodensteiner Michael Arens Rainer Stiefelhagen Fraunhofer IOSB Karlsruhe Institute of Technology

This paper proposes a novel method for vision-based metric cross-view geolocalization (CVGL) that matches the camera images captured from a ground-based vehicle with an aerial image to determine the vehicle's geo-pose. Since aerial images are globally available at low cost, they represent a potential compromise between two established paradigms of autonomous driving, i.e. using expensive high-definition prior maps or relying entirely on the sensor data captured at runtime. We present an end-to-end differentiable model that uses the ground and aerial images to predict a probability distribution over possible vehicle poses. We combine multiple vehicle datasets with aerial images from orthophoto providers on which we demonstrate the feasibility of our method. Since the ground truth poses are often inaccurate w.r.t. the aerial images, we implement a pseudo-label approach to produce more accurate ground truth poses and make them publicly available. While previous works require training data from the target region to achieve reasonable localization accuracy (i.e. same-area evaluation), our approach overcomes this limitation and outperforms previous results even in the strictly more challenging cross-area case. We improve the previous state-of-the-art by a large margin even without ground or aerial data from the test region, which highlights the model's potential for global-scale application. We further integrate the uncertainty-aware predictions in a tracking framework to determine the vehicle's trajectory over time resulting in a mean position error on KITTI-360 of 0.78m.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uni-Perceiver v2: A Generalist Model for Large-Scale vision and vision-Language Tasks

Uni-Perceiver v2: A Generalist Model for Large-Scale Vision ...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Hao Li Jinguo Zhu Xiaohu Jiang Xizhou Zhu Hongsheng Li Chun Yuan Xiaohua Wang Yu Qiao Xiaogang Wang Wenhai Wang Jifeng Dai CUHK-SenseTime Joint Laboratory The Chinese University of Hong Kong Xi'an Jiaotong University SIGS Tsinghua University SenseTime Research Shanghai Artificial Intelligence Laboratory Tsinghua University

Despite the remarkable success of foundation models, their task-specific fine-tuning paradigm makes them inconsistent with the goal of general perception modeling. The key to eliminating this inconsistency is to use generalist models for general task modeling. However, existing attempts at generalist models are inadequate in both versatility and performance. In this paper, we propose Uni-Perceiver v2, which is the first generalist model capable of handling major large-scale vision and vision-language tasks with competitive performance. Specifically, images are encoded as general region proposals, while texts are encoded via a Transformer-based language model. The encoded representations are transformed by a task-agnostic decoder. Different tasks are formulated as a unified maximum likelihood estimation problem. We further propose an effective optimization technique named Task-Balanced Gradient Normalization to ensure stable multi-task learning with an unmixed sampling strategy, which is helpful for tasks requiring large batch-size training. After being jointly trained on various tasks, Uni-Perceiver v2 is capable of directly handling downstream tasks without any task-specific adaptation. Results show that Uni-Perceiver v2 outperforms all existing generalist models in both versatility and performance. Meanwhile, compared with the commonly-recognized strong baselines that require tasks-specific fine-tuning, Uni-Perceiver v2 achieves competitive performance on a broad range of vision and vision-language tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PaCa-ViT: Learning Patch-to-Cluster Attention in vision Transformers

PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Tran...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Ryan Grainger Thomas Paniagua Xi Song Naresh Cuntoor Mun Wai Lee Tianfu Wu Department of ECE NC State An Independent Researcher BlueHalo

vision Transformers (ViTs) are built on the assumption of treating image patches as “visual tokens” and learn patch-to-patch attention. The patch embedding based tokenizer has a semantic gap with respect to its counterpart, the textual tokenizer. The patch-to-patch attention suffers from the quadratic complexity issue, and also makes it non-trivial to explain learned ViTs. To address these issues in ViT, this paper proposes to learn Patch-to-Cluster attention (PaCa) in ViT. Queries in our PaCa-ViT starts with patches, while keys and values are directly based on clustering (with a predefined small number of clusters). The clusters are learned end-to-end, leading to better tokenizers and inducing joint clustering-for-attention and attention-for-clustering for better and interpretable models. The quadratic complexity is relaxed to linear complexity. The proposed PaCa module is used in designing efficient and interpretable ViT backbones and semantic segmentation head networks. In experiments, the proposed methods are tested on ImageNet-1k image classification, MS-COCO object detection and instance segmentation and MIT-ADE20k semantic segmentation. Compared with the prior art, it obtains better performance in all the three benchmarks than the SWin [32] and the PVTs [47], [48] by significant margins in ImageNet-1k and MIT-ADE20k. It is also significantly more efficient than PVT models in MS-COCO and MIT-ADE20k due to the linear complexity. The learned clusters are semantically meaningful. Code and model checkpoints are available at https:/***/iVMCL/PaCaViT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2024 Image Shadow Removal Challenge Report

NTIRE 2024 Image Shadow Removal Challenge Report

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Florin-Alexandru Vasluianu Tim Seizinger Zhuyun Zhou Zongwei Wu Cailian Chen Radu Timofte Wei Dong Han Zhou Yuqiong Tian Jun Chen Xueyang Fu Xin Lu Yurui Zhu Xi Wang Dong Li Jie Xiao Yunpeng Zhang Zheng-Jun Zha Zhao Zhang Suiyi Zhao Bo Wang Yan Luo Yanyan Wei Zhihao Zhao Long Sun Tingting Yang Jinshan Pan Jiangxin Dong Jinhui Tang Bilel Benjdira Mohammed Nassif Anis Koubaa Ahmed Elhayek Anas M. Ali Kyotaro Tokoro Kento Kawai Kaname Yokoyama Takuya Seno Yuki Kondo Norimichi Ukita Chenghua Li Bo Yang Zhiqi Wu Gao Chen Yihan Yu Sixiang Chen Kai Zhang Tian Ye Wenbin Zou Yunlong Lin Zhaohu Xing Jinbin Bai Wenhao Chai Lei Zhu Ritik Maheshwari Rakshank Verma Rahul Tekchandani Praful Hambarde Satya Narayan Tazi Santosh Kumar Vipparthi Subrahmanyam Murala Jaeho Lee Seongwan Kim Sharif S M A Nodirkhuja Khujaev Roman Tsoy Fan Gao Weidan Yan Wenze Shao Dengyin Zhang Bin Chen Siqi Zhang Yanxin Qian Yuanbin Chen Yuanbo Zhou Tong Tong Rongfeng Wei Ruiqi Sun Yue Liu Nikhil Akalwadi Amogh Joshi Sampada Malagi Chaitra Desai Ramesh Ashok Tabib Uma Mudenagudi Ali Murtaza Uswah Khairuddin Ahmad ’Athif Mohd Faudzi Adinath Dukre Vivek Deshmukh Shruti S. Phutke Ashutosh Kulkarni Anil Gonde Arun karthik K Manasa N Shri Hari Priya Wei Hao Xingzhuo Yan Minghan Fu

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

This work reviews the results of the NTIRE 2024 Challenge on Shadow Removal. Building on the last year edition, the current challenge was organized in two tracks, with a track focused on increased fidelity reconstruction, and a separate ranking for high performing perceptual quality solutions. Track 1 (fidelity) had 214 registered participants, with 17 teams submitting in the final phase, while Track 2 (perceptual) registered 185 participants, resulting in 18 final phase submissions. Both tracks were based on data from the WSRD dataset, simulating interactions between self-shadows and cast shadows, with a large variety of represented objects, textures, and materials. Improved image alignment enabled increased fidelity reconstruction, with restored frames mostly indistinguishable from the references images for top performing solutions.

关键词： computer vision Reviews Image synthesis conferences Buildings Image restoration pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Improving vision-and-Language Navigation by Generating Future-View Image Semantics

Improving Vision-and-Language Navigation by Generating Futur...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Jialu Li Mohit Bansal UNC Chapel Hill

vision-and-Language Navigation (VLN) is the task that requires an agent to navigate through the environment based on natural language instructions. At each step, the agent takes the next action by selecting from a set of navigable locations. In this paper, we aim to take one step further and explore whether the agent can benefit from generating the potential future view during navigation. Intuitively, humans will have an expectation of how the future environment will look like, based on the natural language instructions and surrounding views, which will aid correct navigation. Hence, to equip the agent with this ability to generate the semantics of future navigation views, we first propose three proxy tasks during the agent's in-domain pre-training: Masked Panorama Modeling (MPM), Masked Trajectory Modeling (MTM), and Action Prediction with Image Generation (APIG). These three objectives teach the model to predict missing views in a panorama (MPM), predict missing steps in the full trajectory (MTM), and generate the next view based on the full instruction and navigation history (APIG), respectively. We then fine-tune the agent on the VLN task with an auxiliary loss that minimizes the difference between the view semantics generated by the agent and the ground truth view semantics of the next step. Empirically, our VLN-SIG achieves the new state-of-the-art on both Room-to-Room dataset and CVDN dataset. We further show that our agent learns to fill in missing patches in future views qualitatively, which brings more interpretability over agents' predicted actions. Lastly, we demonstrate that learning to predict future view semantics also enables the agent to have better performance on longer paths. 1 1 Code is available at https://***/jialuli-luka/***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Token Contrast for Weakly-Supervised Semantic Segmentation

Token Contrast for Weakly-Supervised Semantic Segmentation

引用

conference on computer vision and pattern recognition (CVPR)

作者： Lixiang Ru Heliang Zheng Yibing Zhan Bo Du Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University China JD Explore Academy China

Weakly-Supervised Semantic Segmentation (WSSS) using image-level labels typically utilizes Class Activation Map (CAM) to generate the pseudo labels. Limited by the local structure perception of CNN, CAM usually cannot identify the integral object regions. Though the recent vision Transformer (ViT) can remedy this flaw, we observe it also brings the over-smoothing issue, i.e., the final patch tokens incline to be uniform. In this work, we propose Token Contrast (ToCo) to address this issue and further explore the virtue of ViT for WSSS. Firstly, motivated by the observation that intermediate layers in ViT can still retain semantic diversity, we designed a Patch Token Contrast module (PTC). PTC supervises the final patch tokens with the pseudo token relations derived from intermediate layers, allowing them to align the semantic regions and thus yield more accurate CAM. Secondly, to further differentiate the low-confidence regions in CAM, we devised a Class Token Contrast module (CTC) inspired by the fact that class tokens in ViT can capture high-level semantics. CTC facilitates the representation consistency between uncertain local regions and global objects by contrasting their class tokens. Experiments on the PASCAL VOC and MS COCO datasets show the proposed ToCo can remarkably surpass other single-stage competitors and achieve comparable performance with state-of-the-art multi-stage methods. Code is available at https://***/rulixiang/ToCo.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IFSeg: Image-free Semantic Segmentation via vision-Language Model

IFSeg: Image-free Semantic Segmentation via Vision-Language ...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Sukmin Yun Seong Hyeon Park Paul Hongsuck Seo Jinwoo Shin Korea Advanced Institute of Science and Technology (KAIST) Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Google Research

vision-language (VL) pre-training has recently gained much attention for its transferability and flexibility in novel concepts (e.g., cross-modality transfer) across various visual tasks. However, VL-driven segmentation has been under-explored, and the existing approaches still have the burden of acquiring additional training images or even segmentation annotations to adapt a VL model to downstream segmentation tasks. In this paper, we introduce a novel image-free segmentation task where the goal is to perform semantic segmentation given only a set of the target semantic categories, but without any task-specific images and annotations. To tackle this challenging task, our proposed method, coined IFSeg, generates VL-driven artificial image-segmentation pairs and updates a pretrained VL model to a segmentation task. We construct this artificial training data by creating a 2D map of random semantic categories and another map of their corresponding word tokens. Given that a pretrained VL model projects visual and text tokens into a common space where tokens that share the semantics are located closely, this artificially generated word map can replace the real image inputs for such a VL model. Through an extensive set of experiments, our model not only establishes an effective baseline for this novel task but also demonstrates strong performances compared to existing methods that rely on stronger supervision, such as task-specific images and segmentation masks. Code is available at https://***/alinlab/ifseg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Position-Guided Text Prompt for vision-Language Pre-Training

Position-Guided Text Prompt for Vision-Language Pre-Training

引用

conference on computer vision and pattern recognition (CVPR)

作者： Jinpeng Wang Pan Zhou Mike Zheng Shou Shuicheng Yan Show Lab National University of Singapore Sea AI Lab

vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into N x N blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates the visual grounding task into a fill-in-the-blank problem given a PTP by encouraging the model to predict the objects in the given blocks or regress the blocks of a given object, e.g. filling “[P]” or “[O]” in a PTP “The block [P] has a [O]”. This mechanism improves the visual grounding capability of VLP models and thus helps them better handle various downstream tasks. By introducing PTP into several state-of-the-art VLP frameworks, we observe consistently significant improvements across representative cross-modal learning model architectures and several benchmarks, e.g. zero-shot Flickr30K Retrieval (+4.8 in average recall@1) for ViLT [16] baseline, and COCO Captioning (+5.3 in CIDEr) for SOTA BLIP [19] baseline. Moreover, PTP achieves comparable results with object-detector based methods [8, 23, 45], and much faster inference speed since PTP discards its object detector for inference while the later cannot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Path: Scaling vision-and-Language Navigation with Synthetic Instructions and Imitation Learning

A New Path: Scaling Vision-and-Language Navigation with Synt...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Aishwarya Kamath Peter Anderson Su Wang Jing Yu Koh Alexander Ku Austin Waters Yinfei Yang Jason Baldridge Zarana Parekh New York University Google Research Carnegie Mellon University Apple

Recent studies in vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the scarcity of human instruction data and limited diversity in the training environments, these agents still struggle with complex language grounding and spatial language understanding. Pretraining on large text and image-text datasets from the web has been extensively explored but the improvements are limited. We investigate large-scale augmentation with synthetic instructions. We take 500+ indoor environments captured in densely-sampled 360 ° panoramas, construct navigation trajectories through these panoramas, and generate a visually-grounded instruction for each trajectory using Marky [63], a high-quality multilingual navigation instruction generator. We also synthesize image observations from novel viewpoints using an image-to-image GAN [27]. The resulting dataset of 4.2M instruction-trajectory pairs is two orders of magnitude larger than existing human-annotated datasets, and contains a wider variety of environments and viewpoints. To efficiently leverage data at this scale, we train a simple transformer agent with imitation learning. On the challenging RxR dataset, our approach outperforms all existing RL agents, improving the state-of-the-art NDTW from 71.1 to 79.1 in seen environments, and from 64.6 to 66.8 in unseen test environments. Our work points to a new path to improving instruction-following agents, emphasizing large-scale training on near-human quality synthetic instructions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering

GCFAgg: Global and Cross-View Feature Aggregation for Multi-...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Weiqing Yan Yuanyang Zhang Chenlei Lv Chang Tang Guanghui Yue Liang Liao Weisi Lin School of Computer and Control Engineering Yantai University Yantai China School of Computer Science and Engineering Nanyang Technological University Singapore College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computer China University of Geosciences Wuhan China School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China

Multi-view clustering can partition data samples into their categories by learning a consensus representation in unsupervised way and has received more and more attention in recent years. However, most existing deep clustering methods learn consensus representation or view-specific representations from multiple views via view-wise aggregation way, where they ignore structure relationship of all samples. In this paper, we propose a novel multi-view clustering network to address these problems, called Global and Cross-view Feature Aggregation for Multi-View Clustering (GCFAggMVC). Specifically, the consensus data presentation from multiple views is obtained via cross-sample and cross-view feature aggregation, which fully explores the complementary of similar samples. Moreover, we align the consensus representation and the view-specific representation by the structure-guided contrastive learning module, which makes the view-specific representations from different samples with high structure relationship similar. The proposed module is a flexible multi-view data representation module, which can be also embedded to the incomplete multi-view data clustering task via plugging our module into other frameworks. Extensive experiments show that the proposed method achieves excellent performance in both complete multi-view data clustering tasks and incomplete multi-view data clustering tasks.

关键词：

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332页 << < 317 318 319 320 321 322 323 324 325 326 > >>

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：