检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Wang, Kaixi Cui, Yunhe Qian, Qing Chen, Yi Guo, Chun Shen, Guowei Engineering Research Center of Text Computing & Cognitive Intelligence Guizhou University China State Key Laboratory of Public Big Data Guizhou University China Guizhou Provincial Characteristic Key Laboratory of Software Engineering and Information Security Guizhou University China College of Computer Science and Technology Guizhou University China School of Information Guizhou University of Finance and Economics China

With the development of Software-Defined Networking (SDN), its security problems have become important research content. Among these security problems, saturation attack is one of the most destructive problems. Saturation attacks can destroy SDN networks. Currently, neural graph networks have already been used for detecting saturation attacks in SDN. When constructing the graph based on K-Nearest Neighbors (KNN) algorithm, the number of edges in the graph is fixed. That cannot reflect the different nodes’ relationship well. In addition, when using the Graph Convolutional Network (GCN) to detect saturation attack against SDN, only a partial graph structure and node features will be learned, causing the flow graph nodes information cannot be fully utilized. To overcome these issues, in this work, we propose USAGE, an uncertain flow graph and spatio-temporal graph network-based saturation attack detection method. More specifically, USAGE designs the CRAM algorithm and EGG model. The CRAM algorithm is designed to generate an uncertain flow graph for each traffic flow, which can represent the uncertain relationship among different nodes. EGG is a spatio-temporal graph convolutional network model, which is proposed to detect saturation attacks towards SDN switches. The evaluation results demonstrate that USAGE can generate a better graph than KNN and achieve high detection performance. Meanwhile, USAGE outperforms other methods in terms of TPR, TNR, accuracy, precision, recall, F-score, confusion matrix, ROC curves, and PR curves. © 2023, The Authors. All rights reserved.

关键词： Flow graphs

来源：评论

学校读者我要写书评

暂无评论

Human-cyber-physical systems:concepts,challenges,and research opportunities

引用

Frontiers of Information technology & Electronic Engineering 2020年第11期21卷 1535-1553页

作者： Zhiming LIU Ji WANG RISE-Centre for Research and Innovation in Software Engineering School of Computer and Information ScienceSouthwest UniversityChongqing 400715China State Key Laboratory for High Performance Computing School of ComputerNational University of Defense TechnologyChangsha 410073China

In this perspective article,we first recall the historic background of human-cyber-physical systems(HCPSs),and then introduce and clarify important *** discuss the key challenges in establishing the scientific foundation from a system engineering point of view,including(1)complex heterogeneity,(2)lack of appropriate abstractions,(3)dynamic black-box integration of heterogeneous systems,(4)complex requirements for functionalities,performance,and quality of services,and(5)design,implementation,and maintenance of HCPS to meet *** we propose four research directions to tackle the challenges,including(1)abstractions and computational theory of HCPS,(2)theories and methods of HCPS architecture modelling,(3)specification and verification of model properties,and(4)software-defined *** article also serves as the editorial of this special section on cyber-physical systems and summarises the four articles included in this special section.

关键词： Abstractions Architecture modelling Evolution Software-defined technology

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Recognizing Private Handwritten Numbers

Federated Learning for Recognizing Private Handwritten Numbe...

引用

2021 IEEE International Conference on Data science and computer Application, ICDSCA 2021

作者： Wang, Di Jiang, Yuchen Zhao, Yibo Chen, Panyang Li, Ang Pan, Kun Institution of Information Engineering Chinese Academy of Sciences State Key Laboratory of Information Security Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Computer Science and Technology College of Computer Science Chongqing University Chongqing China Zibo Shiyan High School International Division Zibo Shandong China Computer Science Department of Computer Science and Software Engineering Auburn University Auburn United States Shanghai Shangde Experimental School Shanghai China School of Computing University of Leeds Leeds United Kingdom

ISBN: (纸本)9781665440530

Federated learning (FL) is a new technology in the field of machine learning, which trains an algorithm across multiple decentralized edge devices or servers holding data samples, without exchanging their data samples. Horizontal Federated Learning (HFL) is a FL method focusing on using the same feature space across all users, which is suitable for situations where users' data feature dimensions overlap more. Because FL has the advantage of privacy protection in the field of manufacturing, we propose an HFL-based deep learning method named FedCNN, which realizes the digits handwritten recognition without violating the privacy or data sharing. Three different methods (local model, centralized model, and HFL-based FedCNN) are used on a public data set (MINIST) to compare the pros and cons of the solutions. The experimental results demonstrate that FedCNN scheme can simultaneously achieve practical privacy preservation and good model generalization performance with Homomorphic Encryption. © 2021 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

LHAASO-KM2A detector simulation using Geant4

引用

Radiation Detection technology and Methods 2024年第3期8卷 1437-1447页

作者： Zhen Cao F.Aharonian Q.An Axikegu Y.X.Bai Y.W.Bao D.Bastieri X.J.Bi Y.J.Bi J.T.Cai Q.Cao W.Y.Cao Zhe Cao J.Chang J.F.Chang A.M.Chen E.S.Chen Liang Chen Lin Chen Long Chen M.J.Chen M.L.Chen Q.H.Chen S.H.Chen S.Z.Chen T.L.Chen Y.Chen N.Cheng Y.D.Cheng M.Y.Cui S.W.Cui X.H.Cui Y.D.Cui B.Z.Dai H.L.Dai Z.G.Dai Danzengluobu X.Q.Dong K.K.Duan J.H.Fan Y.Z.Fan J.Fang K.Fang C.F.Feng L.Feng S.H.Feng X.T.Feng Y.L.Feng S.Gabici B.Gao C.D.Gao L.Q.Gao Q.Gao W.Gao W.K.Gao M.M.Ge L.S.Geng G.Giacinti G.H.Gong Q.B.Gou M.H.Gu F.L.Guo X.L.Guo Y.Q.Guo Y.Y.Guo Y.A.Han H.H.He H.N.He J.Y.He X.B.He Y.He Y.K.Hor B.W.Hou C.Hou X.Hou H.B.Hu Q.Hu S.C.Hu D.H.Huang T.Q.Huang W.J.Huang X.T.Huang X.Y.Huang Y.Huang Z.C.Huang X.L.Ji H.Y.Jia K.Jia K.Jiang X.W.Jiang Z.J.Jiang M.Jin M.M.Kang T.Ke D.Kuleshov K.Kurinov B.B.Li Cheng Li Cong Li D.Li F.Li H.B.Li H.C.Li H.Y.Li J.Li Jian Li Jie Li K.Li W.L.Li W.L.Li X.R.Li Xin Li Y.Z.Li Zhe Li Zhuo Li E.W.Liang Y.F.Liang S.J.Lin B.Liu C.Liu D.Liu H.Liu H.D.Liu J.Liu J.L.Liu J.Y.Liu M.Y.Liu R.Y.Liu S.M.Liu W.Liu Y.Liu Y.N.Liu R.Lu Q.Luo H.K.Lv B.Q.Ma L.L.Ma X.H.Ma J.R.Mao Z.Min W.Mitthumsiri H.J.Mu Y.C.Nan A.Neronov Z.W.Ou B.Y.Pang P.Pattarakijwanich Z.Y.Pei M.Y.Qi Y.Q.Qi B.Q.Qiao J.J.Qin D.Ruffolo A.Sáiz D.Semikoz C.Y.Shao L.Shao O.Shchegolev X.D.Sheng F.W.Shu H.C.Song Yu.V.Stenkin V.Stepanov Y.Su Q.N.Sun X.N.Sun Z.B.Sun P.H.T.Tam Q.W.Tang Z.B.Tang W.W.Tian C.Wang C.B.Wang G.W.Wang H.G.Wang H.H.Wang J.C.Wang K.Wang L.P.Wang L.Y.Wang P.H.Wang R.Wang W.Wang X.G.Wang X.Y.Wang Y.Wang Y.D.Wang Y.J.Wang Z.H.Wang Z.X.Wang Zhen Wang Zheng Wang D.M.Wei J.J.Wei Y.J.Wei T.Wen C.Y.Wu H.R.Wu S.Wu X.F.Wu Y.S.Wu S.Q.Xi J.Xia J.J.Xia G.M.Xiang D.X.Xiao G.Xiao G.G.Xin Y.L.Xin Y.Xing Z.Xiong D.L.Xu R.F.Xu R.X.Xu W.L.Xu L.Xue D.H.Yan J.Z.Yan T.Yan C.W.Yang F.Yang F.F.Yang H.W.Yang J.Y.Yang L.L.Yang M.J.Yang R.Z.Yang S.B.Yang Y.H.Yao Z.G.Yao Y.M.Ye L.Q.Yin N.Yin X.H.You Z.Y.You Y.H.Yu Q.Yuan H.Yue H.D.Zeng T.X.Zeng W.Zeng M.Zha B.B.Zhang F.Zhang H.M.Zhang H.Y.Zhang J.L.Zhang L.X.Zhang Li Zhang P.F.Zhang P.P.Zhang R.Zhang S.B.Zh Key Laboratory of Particle Astrophysics&Experimental Physics Division&Computing Center Institute of High Energy PhysicsChinese Academy of SciencesBeijing100049China University of Chinese Academy of Sciences Beijing100049China TIANFU Cosmic Ray Research Center ChengduSichuanChina Dublin Institute for Advanced Studies 31 Fitzwilliam Place2 DublinIreland Max-Planck-Institute for Nuclear Physics 69029Heidelberg103980Germany State Key Laboratory of Particle Detection and Electronics BeijingChina University of Science and Technology of China Hefei230026AnhuiChina School of Physical Science and Technology&School of Information Science and Technology Southwest Jiaotong UniversityChengdu610031SichuanChina School of Astronomy and Space Science Nanjing UniversityNanjing210023JiangsuChina Center for Astrophysics Guangzhou UniversityGuangzhou510006GuangdongChina Hebei Normal University Shijiazhuang050024HebeiChina Key Laboratory of Dark Matter and Space Astronomy&Key Laboratory of Radio Astronomy Purple Mountain ObservatoryChinese Academy of SciencesNanjing 210023JiangsuChina Tsung-Dao Lee Institute&School of Physics and Astronomy Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory for Research in Galaxies and Cosmology Shanghai Astronomical ObservatoryChinese Academy of SciencesShanghai 200030China Key Laboratory of Cosmic Rays(Tibet University) Ministry of EducationLhasa 850000TibetChina National Astronomical Observatories Chinese Academy of SciencesBeijing 100101China School of Physics and Astronomy(Zhuhai)&School of Physics(Guangzhou)&Sino-French Institute of Nuclear Engineering and Technology(Zhuhai) Sun Yat-sen UniversityGuangzhouZhuhai 510275519000GuangdongChina School of Physics and Astronomy Yunnan UniversityKunming 650091YunnanChina Institute of Frontier and Interdisciplinary Science Shandong UniversityQingdao 266237ShandongChina APC UniversitéParis CitéCNRS/IN2P3CEA/IRFUObservatoire de ParisParis 11975205France Department of Engineering Phys

KM2A is one of the main sub-arrays of LHAASO,working on gamma ray astronomy and cosmic ray physics at energies above 10 *** simulation is the important foundation for estimating detector performance and data *** is a big challenge to simulate the KM2A detector in the framework of Geant4 due to the need to track numerous photons from a large number of detector units(>6000)with large altitude difference(30)and huge coverage(1.3).In this paper,the design of the KM2A simulation code G4KM2A based on Geant4 is *** process of G4KM2A is optimized mainly in memory consumption to avoid memory *** simplifications are used to significantly speed up the execution of *** running time is reduced by at least 30 times compared to full detector *** particle distributions and the core/angle resolution comparison between simulation and experimental data of the full KM2A array are also presented,which show good agreement.

关键词： LHAASO KM2A Simulation GEANT4

来源：评论

学校读者我要写书评

暂无评论

Intensity correlations in decoy-state BB84 quantum key distribution systems

arXiv

引用

arXiv 2024年

作者： Trefilov, Daniil Sixto, Xoel Zapatero, Víctor Huang, Anqi Curty, Marcos Makarov, Vadim Vigo Quantum Communication Center University of Vigo VigoE-36310 Spain School of Telecommunication Engineering Department of Signal Theory and Communications University of Vigo VigoE-36310 Spain atlanTTic Research Center University of Vigo VigoE-36310 Spain Russian Quantum Center Skolkovo Moscow121205 Russia National Research University Higher School of Economics Moscow101000 Russia Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China NTI Center for Quantum Communications National University of Science and Technology MISiS Moscow119049 Russia

The decoy-state method is a prominent approach to enhance the performance of quantum key distribution (QKD) systems that operate with weak coherent laser sources. Due to the limited transmissivity of single photons in optical fiber, current experimental decoy-state QKD setups increase their secret key rate by raising the repetition rate of the transmitter. However, this usually leads to correlations between subsequent optical pulses. This phenomenon leaks information about the encoding settings, including the intensities of the generated signals, which invalidates a basic premise of decoy-state QKD. Here we characterize intensity correlations between the emitted optical pulses in two industrial prototypes of decoy-state BB84 QKD systems and show that they significantly reduce the asymptotic key rate. In contrast to what has been conjectured, we experimentally confirm that the impact of higher-order correlations on the intensity of the generated signals can be much higher than that of nearest-neighbour correlations. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering

arXiv

引用

arXiv 2023年

作者： Xu, Baixin Hu, Jiangbei Hou, Fei Lin, Kwan-Yee Wu, Wayne Qian, Chen He, Ying S-Lab Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore Dalian University of Technology China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China Shanghai AI Lab China SenseTime Research China

The advancements in neural rendering have increased the need for techniques that enable intuitive editing of 3D objects represented as neural implicit surfaces. This paper introduces a novel neural algorithm for parameterizing neural implicit surfaces to simple parametric domains like spheres and polycubes. Our method allows users to specify the number of cubes in the parametric domain, learning a configuration that closely resembles the target 3D object’s geometry. It computes bidirectional deformation between the object and the domain using a forward mapping from the object’s zero level set and an inverse deformation for backward mapping. We ensure nearly bijective mapping with a cycle loss and optimize deformation smoothness. The parameterization quality, assessed by angle and area distortions, is guaranteed using a Laplacian regularizer and an optimized learned parametric domain. Our framework integrates with existing neural rendering pipelines, using multi-view images of a single object or multiple objects of similar geometries to reconstruct 3D geometry and compute texture maps automatically, eliminating the need for any prior information. We demonstrate the method’s effectiveness on images of human heads and man-made objects. The source code is available at https://***/neuparam. Copyright © 2023, The Authors. All rights reserved.

关键词： Parameterization

来源：评论

学校读者我要写书评

暂无评论

FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection

FishEye8K: A Benchmark and Dataset for Fisheye Camera Object...

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Munkhjargal Gochoo Munkh-Erdene Otgonbold Erkhembayar Ganbold Jun-Wei Hsieh Ming-Ching Chang Ping-Yang Chen Byambaa Dorj Hamad Al Jassmi Ganzorig Batnasan Fady Alnajjar Mohammed Abduljabbar Fang-Pang Lin Department of Computer Science and Software Engineering United Arab Emirates University UAE Emirates Center for Mobility Research United Arab Emirates University UAE College of AI and Green Energy National Yang Ming Chiao Tung University Taiwan University at Albany — State University of New York NY USA Department of Computer Science National Yang Ming Chiao Tung University Taiwan Mongolian University of Science and Technology Mongolia National Center for High-Performance Computing Taiwan

With the advance of AI, road object detection has been a prominent topic in computer vision, mostly using perspective cameras. Fisheye lens provides omnidirectional wide coverage for using fewer cameras to monitor road intersections, however with view distortions. To our knowledge, there is no existing open dataset prepared for traffic surveillance on fisheye cameras. This paper introduces an open FishEye8K benchmark dataset for road object detection tasks, which comprises 157K bounding boxes across five classes (Pedestrian, Bike, Car, Bus, and Truck). In addition, we present benchmark results of state-of-The-Art (SoTA) models, including variations of YOLOv5, YOLOR, YOLO7, and YOLOv8. The dataset comprises 8,000 images recorded in 22 videos using 18 fisheye cameras for traffic monitoring in Hsinchu, Taiwan, at resolutions of 1080×1080 and 1280×1280. The data annotation and validation process were arduous and time-consuming, due to the ultra-wide panoramic and hemispherical fisheye camera images with large distortion and numerous road participants, particularly people riding scooters. To avoid bias, frames from a particular camera were assigned to either the training or test sets, maintaining a ratio of about 70:30 for both the number of images and bounding boxes in each class. Experimental results show that YOLOv8 and YOLOR outperform on input sizes 640×640 and 1280×1280, respectively. The dataset will be available on the GitHub link with PASCAL VOC, MS COCO, and YOLO annotation formats. The FishEye8K benchmark will provide significant contributions to the fisheye video analytics and smart city applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hsm2: A hybrid and scalable metadata management method in distributed file systems 10th

Hsm2: A hybrid and scalable metadata management method in di...

引用

10th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2019

作者： Wang, Yiduo Chen, Youxu Shao, Xinyang Chen, Jinzhong Yuan, Liu Xu, Yinlong School of Computer Science and Technology University of Science and Technology of China AnHui Province Key Laboratory of High Performance Computing Hefei China East China Research Institute of Electronic Engineering Hefei China China Academy of Electronics and Information Technology Beijing China

In the bigdata era, metadata performance is critical in modern distributed file systems. Traditionally, the metadata management strategies like the subtree partitioning method focus on keeping namespace locality, while the other ones like the hash-based mapping method aim to offer good load balance. Nevertheless, none of these methods achieve the two desirable properties simultaneously. To close this gap, in this paper, we propose a novel metadata management scheme, HSM2, which combines the subtree partitioning and hash-based mapping method together. We implemented HSM2 in CephFS, a widely deployed distributed file systems, and conducted a comprehensive set of metadata-intensive experiments. Experimental results show that HSM2 can achieve better namespace locality and load balance simultaneously. Compared with CephFS, HSM2 can reduce the completion time by 70% and achieve 3.9× overall throughput speedup for a file-scanning workload. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

HVIS: A Human-like Vision and Inference System for Human Motion Prediction 39

HVIS: A Human-like Vision and Inference System for Human Mot...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lyu, Kedi Chen, Haipeng Liu, Zhenguang Yin, Yifang Lin, Yukang Jiao, Yingying College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Hangzhou China Institute for Infocomm Research (I2R) A*STAR Singapore Tsinghua Shenzhen International Graduate School Nanshan District Shenzhen China

ISBN: (纸本)157735897X

Grasping the intricacies of human motion, which involve perceiving spatio-temporal dependence and multi-scale effects, is essential for predicting human motion. While humans inherently possess the requisite skills to navigate this issue, it proves to be markedly more challenging for machines to emulate. To bridge the gap, we propose the Human-like Vision and Inference System (HVIS) for human motion prediction, which is designed to emulate human observation and forecast future movements. HVIS comprises two components: the human-like vision encode (HVE) module and the human-like motion inference (HMI) module. The HVE module mimics and refines the human visual process, incorporating a retina-analog component that captures spatiotemporal information separately to avoid unnecessary crosstalk. Additionally, a visual cortex-analogy component is designed to hierarchically extract and treat complex motion features, focusing on both global and local features of human poses. The HMI is employed to simulate the multi-stage learning model of the human brain. The spontaneous learning network simulates the neuronal fracture generation process for the adversarial generation of future motions. Subsequently, the deliberate learning network is optimized for hard-to-train joints to prevent misleading learning. Experimental results demonstrate that our method achieves new state-of-the-art performance, significantly outperforming existing methods by 19.8% on Human3.6M, 15.7% on CMU Mocap, and 11.1% on G3D. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Cluster Assumption-Guided Timestamp-Supervised Temporal Action Segmentation

引用

IEEE Transactions on Multimedia 2025年

作者： Ren, Ziyou Li, Guozhang Cheng, Nan Wu, Anqi Wang, Nannan Gao, Xinbo Xidian University State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Shaanxi Xi'an710071 China Carnegie Mellon University Robotics Institute School of Computer Science PittsburghPA15213 United States Beijing Normal University School of Artificial Intelligence Haidian District Beijing100875 China Georgia Institute of Technology School of Computational Science and Engineering College of Computing AtlantaGA30308 United States Xidian University School of Electronic Engineering Xi'an710071 China Chongqing University of Posts and Telecommunications Chongqing Key Laboratory of Image Cognition Chongqing400065 China

Current timestamp-supervised temporal action segmentation (TS-TAS) methods typically follow a two-phase pipeline: initializing the model with timestamp labels and refining it with pseudo-labels. However, limited by the sparsity of timestamp annotations, current methods' performance is sub-optimal. Specifically, initializing the model with only timestamp annotations may cause overfitting to labeled frames. Additionally, sparse timestamp annotations cannot capture the diverse action representations throughout the whole instance, especially those near the ambiguous action boundaries, leading to pseudo-label noise. Inspired by the cluster assumption of semi-supervised learning (SSL) that points within the same manifold likely share the same label, we here model TS-TAS as an SSL problem. Specifically, we propose a Temporal Embedding Consistency (TEC) strategy to mitigate the excessive focus on annotated frames. The TEC strategy encourages frames with similar representations within the video to have similar classification probability distributions, thereby propagating labeled frames' information to implicit ones. Besides, we design a TS-Mix strategy to further leverage unlabeled data to mitigate the influence of pseudo-label noise in a consistency regularization manner. The TS-Mix strategy includes intra-mix, which adds linear interpolation of two adjacent timestamps to every frame between them, and inter-mix, which mixes frames from two different untrimmed videos frame-by-frame. Then the mixed video is trained with the correspondingly mixed pseudo-labels. Comprehensive experimental results on different benchmarks show that we achieve new state-of-the-art performances. Furthermore, the proposed method can seamlessly enhance existing methods, significantly improving their performances. © 1999-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：