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

20,860 篇 会议
104 篇 期刊文献
43 册 图书

馆藏范围

21,006 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,619 篇 工学
- 11,055 篇 计算机科学与技术...
- 2,652 篇 机械工程
- 2,252 篇 软件工程
- 914 篇 光学工程
- 884 篇 电气工程
- 529 篇 控制科学与工程
- 477 篇 信息与通信工程
- 216 篇 测绘科学与技术
- 135 篇 生物工程
- 127 篇 生物医学工程（可授...
- 98 篇 电子科学与技术（可...
- 92 篇 仪器科学与技术
- 46 篇 安全科学与工程
- 40 篇 建筑学
- 40 篇 化学工程与技术
- 39 篇 土木工程
- 37 篇 交通运输工程
- 35 篇 力学（可授工学、理...
- 33 篇 航空宇航科学与技...
3,494 篇 医学
- 3,489 篇 临床医学
- 32 篇 基础医学(可授医学...
2,247 篇 理学
- 1,145 篇 物理学
- 1,081 篇 数学
- 401 篇 生物学
- 384 篇 统计学（可授理学、...
- 245 篇 系统科学
- 46 篇 化学
343 篇 管理学
- 176 篇 管理科学与工程(可...
- 168 篇 图书情报与档案管...
- 34 篇 工商管理
31 篇 法学
19 篇 农学
15 篇 教育学
8 篇 经济学
5 篇 艺术学
2 篇 军事学
1 篇 文学

主题

8,140 篇 computer vision
2,886 篇 training
2,840 篇 pattern recognit...
1,809 篇 computational mo...
1,715 篇 visualization
1,492 篇 cameras
1,433 篇 three-dimensiona...
1,433 篇 feature extracti...
1,366 篇 shape
1,360 篇 face recognition
1,243 篇 image segmentati...
1,135 篇 robustness
1,124 篇 semantics
992 篇 computer archite...
984 篇 object detection
982 篇 layout
959 篇 benchmark testin...
935 篇 codes
899 篇 computer science
898 篇 object recogniti...

机构

174 篇 univ sci & techn...
158 篇 univ chinese aca...
153 篇 carnegie mellon ...
145 篇 chinese univ hon...
109 篇 microsoft resear...
103 篇 zhejiang univ pe...
99 篇 swiss fed inst t...
95 篇 tsinghua univers...
90 篇 microsoft res as...
90 篇 tsinghua univ pe...
88 篇 shanghai ai lab ...
81 篇 zhejiang univers...
77 篇 alibaba grp peop...
74 篇 hong kong univ s...
73 篇 university of sc...
72 篇 peking univ peop...
72 篇 university of ch...
68 篇 shanghai jiao to...
66 篇 univ oxford oxfo...
65 篇 google res mount...

作者

80 篇 van gool luc
70 篇 zhang lei
58 篇 timofte radu
48 篇 yang yi
47 篇 luc van gool
46 篇 xiaoou tang
44 篇 tian qi
43 篇 darrell trevor
42 篇 loy chen change
42 篇 sun jian
41 篇 qi tian
40 篇 li stan z.
38 篇 li fei-fei
37 篇 chen xilin
36 篇 shan shiguang
35 篇 zhou jie
35 篇 vasconcelos nuno
35 篇 liu yang
35 篇 torralba antonio
34 篇 liu xiaoming

语言

20,981 篇 英文
10 篇 中文
7 篇 其他
5 篇 土耳其文
2 篇 日文
2 篇 葡萄牙文

检索条件"任意字段=2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016"

共 21007 条记录，以下是1221-1230 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：

SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders

SMAE: Few-shot Learning for HDR Deghosting with Saturation-A...

引用

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

作者： Yan, Qingsen Zhang, Song Chen, Weiye Tang, Hao Zhu, Yu Sun, Jinqiu Van Gool, Luc Zhang, Yanning Northwestern Polytech Univ Fremont CA 94539 USA Xidian Univ Xian Peoples R China Swiss Fed Inst Technol CVL Zurich Switzerland

ISBN: (纸本)9798350301298

Generating a high-quality High Dynamic Range (HDR) image from dynamic scenes has recently been extensively studied by exploiting Deep Neural Networks (DNNs). Most DNNs-based methods require a large amount of training data with ground truth, requiring tedious and time-consuming work. Few-shot HDR imaging aims to generate satisfactory images with limited data. However, it is difficult for modern DNNs to avoid overfitting when trained on only a few images. In this work, we propose a novel semi-supervised approach to realize few-shot HDR imaging via two stages of training, called SSHDR. Unlikely previous methods, directly recovering content and removing ghosts simultaneously, which is hard to achieve optimum, we first generate content of saturated regions with a self-supervised mechanism and then address ghosts via an iterative semi-supervised learning framework. Concretely, considering that saturated regions can be regarded as masking Low Dynamic Range (LDR) input regions, we design a Saturated Mask AutoEncoder (SMAE) to learn a robust feature representation and reconstruct a non-saturated HDR image. We also propose an adaptive pseudo-label selection strategy to pick high-quality HDR pseudo-labels in the second stage to avoid the effect of mislabeled samples. Experiments demonstrate that SSHDR outperforms state-of-the-art methods quantitatively and qualitatively within and across different datasets, achieving appealing HDR visualization with few labeled samples.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling

NIRVANA: Neural Implicit Representations of Videos with Adap...

引用

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

作者： Maiya, Shishira R. Girish, Sharath Ehrlich, Max Wang, Hanyu Lee, Kwot Sin Poirson, Patrick Wu, Pengxiang Wang, Chen Shrivastava, Abhinav Univ Maryland College Pk MD 20742 USA Snap Inc Santa Monica CA 90405 USA

ISBN: (纸本)9798350301298

Implicit Neural Representations (INR) have recently shown to be powerful tool for high-quality video compression. However, existing works are are limiting as they do not exploit the temporal redundancy in videos, leading to a long encoding time. Additionally, these methods have fixed architectures which do not scale to longer videos or higher resolutions. To address these issues, we propose NIRVANA, which treats videos as groups of frames and fits separate networks to each group performing patch-wise prediction. The video representation is modeled autoregressively, with networks fit on a current group initialized using weights from the previous group's model. To enhance efficiency, we quantize the parameters during training, requiring no post-hoc pruning or quantization. When compared with previous works on the benchmark UVG dataset, NIRVANA improves encoding quality from 37.36 to 37.70 (in terms of PSNR) and the encoding speed by 12x, while maintaining the same compression rate. In contrast to prior video INR works which struggle with larger resolution and longer videos, we show that our algorithm scales naturally due to its patch-wise and autoregressive design. Moreover, our method achieves variable bitrate compression by adapting to videos with varying inter-frame motion. NIRVANA also achieves 6x decoding speed scaling well with more GPUs, making it practical for various deployment scenarios.(1)

关键词： Efficient and scalable vision

来源：评论

学校读者我要写书评

暂无评论

Adapting Shortcut with Normalizing Flow: An Efficient Tuning Framework for Visual recognition

Adapting Shortcut with Normalizing Flow: An Efficient Tuning...

引用

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

作者： Wang, Yaoming Shi, Bowen Zhang, Xiaopeng Li, Jin Liu, Yuchen Dai, Wenrui Li, Chenglin Xiong, Hongkai Tian, Qi Shanghai Jiao Tong Univ Shanghai Peoples R China Huawei Cloud Shenzhen Peoples R China

ISBN: (纸本)9798350301298

Pretraining followed by fine-tuning has proven to be effective in visual recognition tasks. However, fine-tuning all parameters can be computationally expensive, particularly for large-scale models. To mitigate the computational and storage demands, recent research has explored Parameter-Efficient Fine-Tuning (PEFT), which focuses on tuning a minimal number of parameters for efficient adaptation. Existing methods, however, fail to analyze the impact of the additional parameters on the model, resulting in an unclear and suboptimal tuning process. In this paper, we introduce a novel and effective PEFT paradigm, named SNF (Shortcut adaptation via Normalization Flow), which utilizes normalizing flows to adjust the shortcut layers. We highlight that layers without Lipschitz constraints can lead to error propagation when adapting to down-stream datasets. Since modifying the over-parameterized residual connections in these layers is expensive, we focus on adjusting the cheap yet crucial shortcuts. Moreover, learning new information with few parameters in PEFT can be challenging, and information loss can result in label information degradation. To address this issue, we propose an information-preserving normalizing flow. Experimental results demonstrate the effectiveness of SNF. Specifically, with only 0.036M parameters, SNF surpasses previous approaches on both the FGVC and VTAB-1k benchmarks using ViT/B-16 as the backbone. The code is available at https://***/Wang-Yaoming/SNF

关键词： continual low-shot meta or long-tail learning Transfer

来源：评论

学校读者我要写书评

暂无评论

3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification

3D-Aware Object Goal Navigation via Simultaneous Exploration...

引用

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

作者： Zhang, Jiazhao Dai, Liu Meng, Fanpeng Fan, Qingnan Chen, Xuelin Xu, Kai Wang, He Peking Univ CFCS Beijing Peoples R China Beijing Acad Artificial Intelligence Beijing Peoples R China Tongji Univ CEIE Shanghai Peoples R China Huazhong Univ Sci & Technol Wuhan Peoples R China Tencent AI Lab Shenzhen Peoples R China Natl Univ Def Technol Changsha Peoples R China

ISBN: (纸本)9798350301298

Object goal navigation (ObjectNav) in unseen environments is a fundamental task for Embodied AI. Agents in existing works learn ObjectNav policies based on 2D maps, scene graphs, or image sequences. Considering this task happens in 3D space, a 3D-aware agent can advance its ObjectNav capability via learning from fine-grained spatial information. However, leveraging 3D scene representation can be prohibitively unpractical for policy learning in this floor-level task, due to low sample efficiency and expensive computational cost. In this work, we propose a framework for the challenging 3D-aware ObjectNav based on two straightforward sub-policies. The two sub-polices, namely corner-guided exploration policy and category-aware identification policy, simultaneously perform by utilizing online fused 3D points as observation. Through extensive experiments, we show that this framework can dramatically improve the performance in ObjectNav through learning from 3D scene representation. Our framework achieves the best performance among all modular-based methods on the Matterport3D and Gibson datasets, while requiring (up to 30x) less computational cost for training. The code will be released to benefit the community.

关键词： Embodied vision: Active agents simulation

来源：评论

学校读者我要写书评

暂无评论

Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval

Towards Fast Adaptation of Pretrained Contrastive Models for...

引用

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

作者： Lin, Xudong Tiwari, Simran Huang, Shiyuan Li, Manling Shou, Mike Zheng Ji, Heng Chang, Shih-Fu Columbia Univ New York NY 10027 USA UIUC Champaign IL USA Natl Univ Singapore Singapore Singapore

ISBN: (纸本)9798350301298

Multi-channel video-language retrieval require models to understand information from different channels (e.g. video+question, video+speech) to correctly link a video with a textual response or query. Fortunately, contrastive multimodal models are shown to be highly effective at aligning entities in images/videos and text, e.g., CLIP [20];text contrastive models are extensively studied recently for their strong ability of producing discriminative sentence embeddings, e.g., SimCSE [5]. However, there is not a clear way to quickly adapt these two lines to multi-channel video-language retrieval with limited data and resources. In this paper, we identify a principled model design space with two axes: how to represent videos and how to fuse video and text information. Based on categorization of recent methods, we investigate the options of representing videos using continuous feature vectors or discrete text tokens;for the fusion method, we explore the use of a multimodal transformer or a pretrained contrastive text model. We extensively evaluate the four combinations on five video-language datasets. We surprisingly find that discrete text tokens coupled with a pretrained contrastive text model yields the best performance, which can even outperform state-of-the-art on the iVQA and How2QA datasets without additional training on millions of video-text data. Further analysis shows that this is because representing videos as text tokens captures the key visual information and text tokens are naturally aligned with text models that are strong retrievers after the contrastive pretraining process. All the empirical analysis establishes a solid foundation for future research on affordable and upgradable multimodal intelligence.

关键词： and reasoning language vision

来源：评论

学校读者我要写书评

暂无评论

Human Guided Ground-truth Generation for Realistic Image Super-resolution

Human Guided Ground-truth Generation for Realistic Image Sup...

引用

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

作者： Chen, Du Liang, Jie Zhang, Xindong Liu, Ming Zeng, Hui Zhang, Lei Hong Kong Polytech Univ Hong Kong Peoples R China OPPO Res Inst Shenzhen Peoples R China Harbin Inst Technol Harbin Peoples R China

ISBN: (纸本)9798350301298

How to generate the ground-truth (GT) image is a critical issue for training realistic image super-resolution (Real-ISR) models. Existing methods mostly take a set of high-resolution (HR) images as GTs and apply various degradations to simulate their low-resolution (LR) counterparts. Though great progress has been achieved, such an LR-HR pair generation scheme has several limitations. First, the perceptual quality of HR images may not be high enough, limiting the quality of Real-ISR outputs. Second, existing schemes do not consider much human perception in GT generation, and the trained models tend to produce over-smoothed results or unpleasant artifacts. With the above considerations, we propose a human guided GT generation scheme. We first elaborately train multiple image enhancement models to improve the perceptual quality of HR images, and enable one LR image having multiple HR counterparts. Human subjects are then involved to annotate the high quality regions among the enhanced HR images as GTs, and label the regions with unpleasant artifacts as negative samples. A human guided GT image dataset with both positive and negative samples is then constructed, and a loss function is proposed to train the Real-ISR models. Experiments show that the Real-ISR models trained on our dataset can produce perceptually more realistic results with less artifacts. Dataset and codes can be found at https://***/ChrisDud0257/HGGT.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

Photo Pre-Training, But for Sketch

Photo Pre-Training, But for Sketch

引用

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

作者： Ke, L. Pang, Kaiyue Song, Yi-Zhe Beijing Univ Posts & Telecommunicat Sch Artificial Intelligence Beijing Peoples R China Univ Surrey SketchX CNSSP Surrey England

ISBN: (纸本)9798350301298

The sketch community has faced up to its unique challenges over the years, that of data scarcity however still remains the most significant to date. This lack of sketch data has imposed on the community a few "peculiar" design choices - the most representative of them all is perhaps the coerced utilisation of photo-based pre-training (i.e., no sketch), for many core tasks that otherwise dictates specific sketch understanding. In this paper, we ask just the one question - can we make such photo-based pre-training, to actually benefit sketch? Our answer lies in cultivating the topology of photo data learned at pre-training, and use that as a "free" source of supervision for downstream sketch tasks. In particular, we use fine-grained sketch-based image retrieval (FG-SBIR), one of the most studied and data-hungry sketch tasks, to showcase our new perspective on pre-training. In this context, the topology-informed supervision learned from photos act as a constraint that take effect at every fine-tuning step - neighbouring photos in the pre-trained model remain neighbours under each FG-SBIR updates. We further portray this neighbourhood consistency constraint as a photo ranking problem and formulate it into a neat cross-modal triplet loss. We also show how this target is better leveraged as a meta objective rather than optimised in parallel with the main FG-SBIR objective. With just this change on pre-training, we beat all previously published results on all five product-level FG-SBIR benchmarks with significant margins (sometimes >10%). And the most beautiful thing, as we note, is such gigantic leap is made possible within just a few extra lines of code! Our implementation is available at https: / / github. com/ KeLi- SketchX / Photo - Pre Training-But- for-Sketch

关键词： detection recognition: Categorization retrieval

来源：评论

学校读者我要写书评

暂无评论

Boost vision Transformer with GPU-Friendly Sparsity and Quantization

Boost Vision Transformer with GPU-Friendly Sparsity and Quan...

引用

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

作者： Yu, Chong Chen, Tao Gan, Zhongxue Fan, Jiayuan Fudan Univ Acad Engn & Technol Shanghai Peoples R China NVIDIA Corp Taipei Taiwan Fudan Univ Sch Informat Sci & Technol Shanghai Peoples R China

ISBN: (纸本)9798350301298

The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision transformer on GPU hardware is challenging and also rarely studied. This paper thoroughly designs a compression scheme to maximally utilize the GPU-friendly 2:4 fine-grained structured sparsity and quantization. Specially, an original large model with dense weight parameters is first pruned into a sparse one by 2:4 structured pruning, which considers the GPU's acceleration of 2:4 structured sparse pattern with FP16 data type, then the floating-point sparse model is further quantized into a fixed-point one by sparse-distillation-aware quantization aware training, which considers GPU can provide an extra speedup of 2:4 sparse calculation with integer tensors. A mixed-strategy knowledge distillation is used during the pruning and quantization process. The proposed compression scheme is flexible to support supervised and unsupervised learning styles. Experiment results show GPUSQ-ViT scheme achieves state-of-the-art compression by reducing vision transformer models 6.4-12.7x on model size and 30.3-62x on FLOPs with negligible accuracy degradation on ImageNet classification, COCO detection and ADE20K segmentation benchmarking tasks. Moreover, GPUSQ-ViT can boost actual deployment performance by 1.39-1.79x and 3.22-3.43x of latency and throughput on A100 GPU, and 1.57-1.69x and 2.11-2.51x improvement of latency and throughput on AGX Orin.

关键词： Efficient and scalable vision

来源：评论

学校读者我要写书评

暂无评论

Semantic Prompt for Few-Shot Image recognition

Semantic Prompt for Few-Shot Image Recognition

引用

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

作者： Chen, Wentao Si, Chenyang Zhang, Zhang Wang, Liang Wang, Zilei Tan, Tieniu Univ Sci & Technol China Hefei Peoples R China CASIA NLPR Ctr Res Intelligent Percept & Comp Hangzhou Peoples R China Nanyang Technol Univ Singapore Singapore Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9798350301298

Few-shot learning is a challenging problem since only a few examples are provided to recognize a new class. Several recent studies exploit additional semantic information, e.g. text embeddings of class names, to address the issue of rare samples through combining semantic prototypes with visual prototypes. However, these methods still suffer from the spurious visual features learned from the rare support samples, resulting in limited benefits. In this paper, we propose a novel Semantic Prompt (SP) approach for few-shot learning. Instead of the naive exploitation of semantic information for remedying classifiers, we explore leveraging semantic information as prompts to tune the visual feature extraction network adaptively. Specifically, we design two complementary mechanisms to insert semantic prompts into the feature extractor: one is to enable the interaction between semantic prompts and patch embeddings along the spatial dimension via self-attention, another is to supplement visual features with the transformed semantic prompts along the channel dimension. By combining these two mechanisms, the feature extractor presents a better ability to attend to the class-specific features and obtains more generalized image representations with merely a few support samples. Through extensive experiments on four datasets, the proposed approach achieves promising results, improving the 1-shot learning accuracy by 3.67% on average.

关键词： continual low-shot meta or long-tail learning Transfer

来源：评论

学校读者我要写书评

暂无评论

Adaptive Data-Free Quantization

Adaptive Data-Free Quantization

引用

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

作者： Qian, Biao Wang, Yang Hong, Richang Wang, Meng Hefei Univ Technol Key Lab Knowledge Engn Big Data Minist Educ Sch Comp Sci & Informat Engn Hefei Peoples R China

ISBN: (纸本)9798350301298

Data-free quantization (DFQ) recovers the performance of quantized network (Q) without the original data, but generates the fake sample via a generator (G) by learning from full-precision network (P), which, however, is totally independent of Q, overlooking the adaptability of the knowledge from generated samples, i.e., informative or not to the learning process of Q, resulting into the overflow of generalization error. Building on this, several critical questions how to measure the sample adaptability to Q under varied bit-width scenarios? whether the largest adaptability is the best? how to generate the samples with adaptive adaptability to improve Q's generalization? To answer the above questions, in this paper, we propose an Adaptive Data-Free Quantization (AdaDFQ) method, which revisits DFQ from a zero-sum game perspective upon the sample adaptability between two players - a generator and a quantized network. Following this viewpoint, we further define the disagreement and agreement samples to form two boundaries, where the margin between two boundaries is optimized to adaptively regulate the adaptability of generated samples to Q, so as to address the over-and-under fitting issues. Our AdaDFQ reveals: 1) the largest adaptability is NOT the best for sample generation to benefit Q's generalization;2) the knowledge of the generated sample should not be informative to Q only, but also related to the category and distribution information of the training data for P. The theoretical and empirical analysis validate the advantages of AdaDFQ over the state-of-the-arts. Our code is available at https://***/hfutqian/AdaDFQ.

关键词： Efficient and scalable 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500页 << < 119 120 121 122 123 124 125 126 127 128 > >>

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：