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

3,915 篇 会议
2 篇 期刊文献

馆藏范围

3,917 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,011 篇 工学
- 2,919 篇 计算机科学与技术...
- 216 篇 软件工程
- 141 篇 机械工程
- 133 篇 光学工程
- 42 篇 生物工程
- 28 篇 信息与通信工程
- 25 篇 电气工程
- 17 篇 控制科学与工程
- 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
1,559 篇 医学
- 1,558 篇 临床医学
- 3 篇 基础医学(可授医学...
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
14 篇 管理学
- 7 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

2,408 篇 computer vision
1,085 篇 training
1,043 篇 pattern recognit...
805 篇 conferences
709 篇 computational mo...
543 篇 visualization
491 篇 computer archite...
446 篇 three-dimensiona...
410 篇 semantics
409 篇 benchmark testin...
383 篇 codes
331 篇 transformers
290 篇 deep learning
277 篇 feature extracti...
260 篇 neural networks
256 篇 task analysis
238 篇 shape
216 篇 image segmentati...
204 篇 measurement
202 篇 object detection

机构

72 篇 tsinghua univ pe...
59 篇 univ sci & techn...
55 篇 zhejiang univ pe...
55 篇 chinese univ hon...
51 篇 carnegie mellon ...
51 篇 peng cheng lab p...
49 篇 swiss fed inst t...
47 篇 sensetime res pe...
46 篇 shanghai ai lab ...
42 篇 univ hong kong p...
38 篇 huawei noahs ark...
35 篇 univ chinese aca...
35 篇 shanghai jiao to...
33 篇 alibaba grp peop...
32 篇 tech univ munich...
31 篇 stanford univ st...
30 篇 peking univ peop...
30 篇 swiss fed inst t...
29 篇 adobe res san jo...
29 篇 google res mount...

作者

63 篇 timofte radu
30 篇 van gool luc
19 篇 yang yi
19 篇 qiao yu
18 篇 loy chen change
16 篇 zhang lei
16 篇 radu timofte
15 篇 sun jian
14 篇 liu yang
14 篇 liu shuaicheng
14 篇 tao dacheng
13 篇 li xin
13 篇 fan haoqiang
13 篇 chen wei-ting
12 篇 luo ping
12 篇 chen dongdong
12 篇 wang kai
12 篇 wang xinchao
12 篇 torralba antonio
12 篇 ghanem bernard

语言

3,916 篇 英文
1 篇 其他

检索条件"任意字段=2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022"

共 3917 条记录，以下是3791-3800 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：

The MTA Dataset for Multi Target Multi Camera Pedestrian Tracking by Weighted Distance Aggregation

The MTA Dataset for Multi Target Multi Camera Pedestrian Tra...

引用

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

作者： Philipp Köhl Andreas Specker Arne Schumann Jürgen Beyerer Fraunhofer IOSB Karlsruhe Germany Vision and Fusion Lab Institute for Anthropomatics and Robotics Karlsruhe Germany

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

Existing multi target multi camera tracking (MTMCT) datasets are small in terms of the number of identities and video length. The creation of new real world datasets is hard as privacy has to be guaranteed and the labeling is tedious. Therefore in the scope of this work a mod for GTA V to record a MTMCT dataset has been developed and used to record a simulated MTMCT dataset called Multi Camera Track Auto (MTA). The MTA dataset contains over 2,800 person identities, 6 cameras and a video length of over 100 minutes per camera. Additionally a MTMCT system has been implemented to provide a baseline for the created dataset. The system's pipeline consists of stages for person detection, person re-identification, single camera multi target tracking, track distance calculation, and track association. The track distance calculation comprises a weighted aggregation of the following distances: a single camera time constraint, a multi camera time constraint using overlapping camera areas, an appearance feature distance, a homography matching with pairwise camera homographies, and a linear prediction based on the velocity and the time difference of tracks. When using all partial distances, we were able to surpass the results of state-of-the-art single camera trackers by +13% IDF1 score. The MTA dataset, code, and baselines are available at ***/schuar-iosb/mta-dataset.

关键词： Cameras Target tracking Task analysis Synchronization Games Data privacy

来源：评论

学校读者我要写书评

暂无评论

ReweightOOD: Loss Reweighting for Distance-based OOD Detection

ReweightOOD: Loss Reweighting for Distance-based OOD Detecti...

引用

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

作者： Sudarshan Regmi Bibek Panthi Yifei Ming Prashnna K Gyawali Danail Stoyanov Binod Bhattarai University College London UK NepAl Applied Mathematics and Informatics Institute for Research Nepal University of Wisconsin-Madison USA West Virginia University USA University of Aberdeen UK

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Out-of-Distribution (OOD) detection is crucial for ensuring safety and reliability of neural networks in critical applications. Distance-based OOD detection is based on the assumption that OOD samples are mapped far from In-Distribution (ID) clusters in embedding space. A recent approach for obtaining OOD-detection-friendly embedding space has been contrastive optimization of pulling similar pairs and pushing apart dissimilar pairs. It assigns equal significance to all similarity instances with the implicit objective of maximizing the mean proximity between samples with their corresponding hypothetical class centroids. However, the emphasis should be directed towards reducing the Minimum Enclosing Sphere (MES) for each class and achieving higher inter-class dispersion to effectively mitigate the potential for ID-OOD overlap. Optimizing low-signal dissimilar pairs might potentially act against achieving maximal inter-class dispersion while less-optimized similar pairs prevent achieving smaller MES. Based on this, we propose a reweighting scheme ReweightOOD, that adopts the similarity optimization which prioritizes the optimization of less-optimized contrasting pairs while assigning lower importance to already well-optimized contrasting pairs. Such a reweighting scheme serves to minimize the MES for each class while achieving maximal interclass dispersion. Experimental results on a challenging CIFAR100 benchmark using ResNet-18 network demonstrate that ReweightOOD outperforms supervised contrastive loss by a whopping 38% in the average FPR metric. In various classification datasets, our method provides a promising solution for enhancing OOD detection capabilities in neural networks.

关键词： Measurement computer vision conferences Neural networks Benchmark testing Safety pattern recognition

来源：评论

学校读者我要写书评

暂无评论

MvAV-pix2pixHD: Multi-view Aerial View Image Translation

MvAV-pix2pixHD: Multi-view Aerial View Image Translation

引用

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

作者： Jun Yu Keda Lu Shenshen Du Lin Xu Peng Chang Houde Liu Bin Lan Tianyu Liu University of Science and Technology of China Ping An Technology Co. Ltd China PAII Inc. Tsinghua Shenzhen International Graduate School Jianghuai Advance Technology Center

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Multi-modal aerial view image translation involves converting aerial images from one modality to another while preserving basic details and features. These modalities encompass Synthetic Aperture Radar (SAR), Infrared (IR), Visible Light (RGB), Electro-Optical (EO), and other image types. Recently, various methods have been proposed to tackle this task, but the focus tends to be on paired image research, overlooking the discrepancies found in aerial images of the same location captured at different times and angles, termed incomplete matching or multi-view image translation. Consequently, we propose MvAV-pix2pixHD to address this issue. For multi-view data sampling, we propose two methods: random sampling and time-priority sampling. Additionally, within the pix2pixHD framework, we introduce an inverse generator to ensure the basic semantic features of the generated images and incorporate three robust loss functions to constrain the authenticity of the generated images. We conduct extensive experiments on two multi-view image translation tasks in the Multi-modal Aerial View Imagery Challenge: Translation (MAVIC-T). Experimental results demonstrate the superiority of our proposed method, and we achieved second place in the MAVIC-T competition in the 20th ieee Workshop on Perception Beyond the Visible Spectrum of the CVPR 2024.

关键词： computer vision Image resolution conferences Computational modeling Semantics computer architecture Generators

来源：评论

学校读者我要写书评

暂无评论

Task Navigator: Decomposing Complex Tasks for Multimodal Large Language Models

Task Navigator: Decomposing Complex Tasks for Multimodal Lar...

引用

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

作者： Feipeng Ma Yizhou Zhou Yueyi Zhang Siying Wu Zheyu Zhang Zilong He Fengyun Rao Xiaoyan Sun University of Science and Technology of China WeChat Tencent Inc. Institute of Artificial Intelligence Hefei Comprehensive National Science Center

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Inspired by the remarkable progress achieved by recent Large Language Models (LLMs), Multimodal Large Language Models (MLLMs) take LLMs as their brains, and have achieved surprising results in many downstream tasks by training on a large amount of task-specific data. However, when faced with complex tasks that require the collaboration of multiple capabilities, existing MLLMs recollect training data and retrain the model, ignoring the systematic utilization of LLMs and their possessed capabilities learned in downstream tasks. Inspired by the way humans tackle complex questions, in this paper, we propose a novel framework called Task Navigator. In our framework, LLMs act as navigators to chart a viable path for solving complex tasks and guide MLLMs through the process step by step. Specifically, LLMs iteratively break down sub-problems and refine them to be more reasonable and answerable, which are subsequently resolved by MLLMs to obtain relevant subanswers, until the LLMs have collected enough information to answer the initial question. Task Navigator provides an effective way to extend MLLMs to tackle complex tasks, thus broadening MLLMs’ applicability. To evaluate the performance of the proposed framework, we have curated a carefully designed benchmark called VersaChallenge. Experiments on VersaChallenge demonstrate the effectiveness of our proposed method.

关键词： Training computer vision Systematics Navigation Large language models conferences Training data

来源：评论

学校读者我要写书评

暂无评论

TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals

TCCT-Net: Two-Stream Network Architecture for Fast and Effic...

引用

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

作者： Alexander Vedernikov Puneet Kumar Haoyu Chen Tapio Seppänen Xiaobai Li Center for Machine Vision and Signal Analysis University of Oulu Finland State Key Laboratory of Blockchain and Data Security Zhejiang University China

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Engagement analysis finds various applications in healthcare, education, advertisement, services. Deep Neural Networks, used for analysis, possess complex architecture and need large amounts of input data, computational power, inference time. These constraints challenge embedding systems into devices for real-time use. To address these limitations, we present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain and boost processing speed, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form. Evaluated on the EngageNet dataset, the proposed method outperforms existing baselines, utilizing only two behavioral features (head pose rotations) compared to the 98 used in baseline models. Furthermore, comparative analysis shows TCCT-Net’s architecture offers an order-of-magnitude improvement in inference speed compared to state-of-the-art image-based Recurrent Neural Network (RNN) methods. The code will be released at https://***/vedernikovphoto/TCCT_Net.

关键词： Convolutional codes Accuracy Recurrent neural networks Continuous wavelet transforms Wavelet domain Convolution Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Evaluating Multimodal Large Language Models across Distribution Shifts and Augmentations

Evaluating Multimodal Large Language Models across Distribut...

引用

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

作者： Aayush Atul Verma Amir Saeidi Shamanthak Hegde Ajay Therala Fenil Denish Bardoliya Nagaraju Machavarapu Shri Ajay Kumar Ravindhiran Srija Malyala Agneet Chatterjee Yezhou Yang Chitta Baral Arizona State University

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Foundational models such as Multimodal Large Language Models (MLLMs) with their ability to interpret images and generate intricate responses has led to their widespread adoption across multiple computer vision and natural language processing tasks. However, they suffer from hallucinations and struggle to reason over complex reasoning tasks. In this work, we evaluate the performance of MLLMs across multiple multimodal augmentations and evaluate their performance in out-of-distribution settings. We benchmark 3 models, across 2 vision-language datasets, VQAv2 and CLEVR, and assess their performance across adversarial transformations in both the vision and language modalities. We introduce image perturbations using various augmentations, including noise addition, blurring, and median filtering and generate adversarial questions which contain conjunctions, disjunctions and negations. Additionally, we conduct a detailed fine-grained analysis to assess the model’s performance on particular question categories, such as those related to shape and color, across images featuring identical or varying objects. Our findings indicate a notable decrease in the performance of current MLLMs for synthetic images, with a gradual decline observed across both vision and language augmentations. Specifically, Gaussian Noise Addition emerges as the most detrimental augmentation, and we observe a significant drop in performance with complex questions containing multiple connectives. In these times of rapid development and deployment of MLLMs in real-world settings, we believe our findings are a first step towards benchmarking the robustness and out-of-distribution behavior of such models.

关键词： computer vision Analytical models Shape Large language models Computational modeling Perturbation methods Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Learning a Controller Fusion Network by Online Trajectory Filtering for vision-Based UAV Racing

Learning a Controller Fusion Network by Online Trajectory Fi...

引用

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

作者： Matthias Müller Guohao Li Vincent Casser Neil Smith Dominik L. Michels Bernard Ghanem King Abdullah University of Science and Technology Thuwal Saudi Arabia Visual Computing Center King Abdullah University of Science and Technology Saudi Arabia

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

Autonomous UAV racing has recently emerged as an interesting research problem. The dream is to beat humans in this new fast-paced sport. A common approach is to learn an end-to-end policy that directly predicts controls from raw images by imitating an expert. However, such a policy is limited by the expert it imitates and scaling to other environments and vehicle dynamics is difficult. One approach to overcome the drawbacks of an end-to-end policy is to train a network only on the perception task and handle control with a PID or MPC controller. However, a single controller must be extensively tuned and cannot usually cover the whole state space. In this paper, we propose learning an optimized controller using a DNN that fuses multiple controllers. The network learns a robust controller with online trajectory filtering, which suppresses noisy trajectories and imperfections of individual controllers. The result is a network that is able to learn a good fusion of filtered trajectories from different controllers leading to significant improvements in overall performance. We compare our trained network to controllers it has learned from, end-to-end baselines and human pilots in a realistic simulation; our network beats all baselines in extensive experiments and approaches the performance of a professional human pilot.

关键词： Trajectory Training Task analysis Aerospace electronics Navigation Robustness Neural networks

来源：评论

学校读者我要写书评

暂无评论

Virtually Enriched NYU Depth V2 Dataset for Monocular Depth Estimation: Do We Need Artificial Augmentation?

Virtually Enriched NYU Depth V2 Dataset for Monocular Depth ...

引用

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

作者： Dmitry Ignatov Andrey Ignatov Radu Timofte Computer Vision Lab CAIDAS & IFI University of Wurzburg Germany Computer Vision Lab ETH Zurich Switzerland

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

We present ANYU, a new virtually augmented version of the NYU depth v2 dataset, designed for monocular depth estimation. In contrast to the well-known approach where full 3D scenes of a virtual world are utilized to generate artificial datasets, ANYU was created by incorporating RGB-D representations of virtual reality objects into the original NYU depth v2 images. We specifically did not match each generated virtual object with an appropriate texture and a suitable location within the real-world image. Instead, an assignment of texture, location, lighting, and other rendering parameters was randomized to maximize a diversity of the training data, and to show that it is randomness that can improve the generalizing ability of a dataset. By conducting extensive experiments with our virtually modified dataset and validating on the original NYU depth v2 and iBims-1 benchmarks, we show that ANYU improves the monocular depth estimation performance and generalization of deep neural networks with considerably different architectures, especially for the current state-of-the-art VPD model. To the best of our knowledge, this is the first work that augments a real-world dataset with randomly generated virtual 3D objects for monocular depth estimation. We make our ANYU dataset publicly available in two training configurations with 10% and 100% additional synthetically enriched RGB-D pairs of training images, respectively, for efficient training and empirical exploration of virtual augmentation at https://***/ABrain-One/ANYU.

关键词： Training Solid modeling Three-dimensional displays Computational modeling Estimation Training data Lighting

来源：评论

学校读者我要写书评

暂无评论

LaDiffGAN: Training GANs with Diffusion Supervision in Latent Spaces

LaDiffGAN: Training GANs with Diffusion Supervision in Laten...

引用

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

作者： Xuhui Liu Bohan Zeng Sicheng Gao Shanglin Li Yutang Feng Hong Li Boyu Liu Jianzhuang Liu Baochang Zhang Beihang University Shenzhen Institute of Advanced Technology Shenzhen China Zhongguancun Laboratory Beijing China Nanchang Institute of Technology Nanchang China

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Diffusion models have recently become increasingly popular in a number of computer vision tasks, but they fail to achieve satisfactory results for unsupervised image-to-image translation, since they require massive training data and rely heavily on extra guidance. In this scenario, GANs can alleviate these issues existing in diffusion models, albeit with suboptimal quality. In this paper, we leverage the advantages of both GANs and diffusion models by training GANs with diffusion supervision in latent spaces (LaDiffGAN) to solve the unsupervised image-to-image translation task. Firstly, to promote style transfer quality, we encode the data in specific latent spaces with styles of the target and source domains. Secondly, we introduce the diffusion process with different amounts of Gaussian noise to enhance the modeling capability of GANs on the complex data distribution. We accordingly design a latent diffusion GAN loss to align the latent features between generated and training images. Lastly, we introduce a heterogeneous conditional denoising loss that incorporates image-level supervision to further improve the quality of generated results. Our LaDiffGAN significantly alleviates the drawbacks associated with diffusion models, such as data leakage, high inference cost, and high dependence on large training data sets. Extensive experiments show that LaDiffGAN outperforms previous GAN models and delivers comparable or even better performance than diffusion models.

关键词： Training computer vision Image synthesis Gaussian noise Noise reduction Training data Diffusion processes

来源：评论

学校读者我要写书评

暂无评论

COOD: Combined out-of-distribution detection using multiple measures for anomaly & novel class detection in large-scale hierarchical classification

COOD: Combined out-of-distribution detection using multiple ...

引用

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

作者： Laurens E. Hogeweg Rajesh Gangireddy Django Brunink Vincent J. Kalkman Ludo Cornelissen Jacob W. Kamminga Intel Naturalis Biodiversity Center University of Twente

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

High-performing out-of-distribution (OOD) detection, both anomaly and novel class, is an important prerequisite for the practical use of classification models. In this paper we focus on the species recognition task in images, concerned with large databases, a large number of fine-grained hierarchical classes, severe class imbalance, and varying image quality. We propose a framework for combining individual OOD measures into one combined OOD (COOD) measure using a supervised model. The individual measures are several existing state-of-the-art measures and several novel OOD measures developed with novel class detection and hierarchical class structure in mind. COOD was extensively evaluated on three large-scale (500k+ images) biodiversity datasets in the context of anomaly and novel class detection. We show that COOD outperforms individual, including state-of-the-art, OOD measures by a large margin in terms of TPR@1%FPR in the majority of experiments, e.g., improving detecting ImageNet images (OOD) from 54.3% to 83.3% for the iNaturalist 2018 dataset. SHAP (feature contribution) analysis shows that different individual OOD measures are essential for various tasks, indicating that multiple OOD measures and combinations are needed to generalize. Additionally, we show that explicitly considering ID images that are incorrectly classified for the original (species) recognition task is important for constructing high-performing OOD detection methods and for practical applicability. The framework can easily be extended or adapted to other tasks and media modalities.

关键词： Image quality computer vision Image recognition Databases conferences Biological system modeling Media

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392页 << < 376 377 378 379 380 381 382 383 384 385 > >>

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：