计算机视觉、机器学习相关领域论文…

http://blog.csdn.net/zouxy09/article/details/8550952 

顶] 计算机视觉、机器学习相关领域论文和源代码大集合--持续更新……

计算机视觉、机器学习相关领域论文和源代码大集合--持续更新……

[e-mail] http://blog.csdn.net/zouxy09 

注：下面有project网站的大部分都有paper和相应的code。Code一般是C/C++或者Matlab代码。最近一次更新：2013-3-17

 一、特征提取FeatureExtraction：

·        SIFT [1] [Demo program][SIFT Library] [VLFeat]

·        PCA-SIFT [2] [Project]

·        Affine-SIFT [3] [Project]

·        SURF [4] [OpenSURF][MatlabWrapper]

·        Affine Covariant Features [5][Oxfordproject]

·        MSER [6] [Oxford project] [VLFeat]

·        Geometric Blur [7] [Code]

·        Local Self-Similarity Descriptor [8][Oxfordimplementation]

·        Global and Efficient Self-Similarity[9] [Code]

·        Histogram of Oriented Graidents [10][INRIA Object Localization Toolkit][OLT toolkit for Windows]

·        GIST [11] [Project]

·        Shape Context [12] [Project]

·        Color Descriptor [13] [Project]

·        Pyramids of Histograms of OrientedGradients [Code]

·        Space-Time Interest Points (STIP)[14][Project] [Code]

·        Boundary Preserving Dense LocalRegions [15][Project]

·        Weighted Histogram[Code]

·        Histogram-based Interest PointsDetectors[Paper][Code]

·        An OpenCV - C++ implementation ofLocal Self Similarity Descriptors [Project]

·        Fast Sparse Representation withPrototypes[Project]

·        Corner Detection [Project]

·        AGAST Corner Detector: faster thanFAST and even FAST-ER[Project]

·         Real-timeFacial Feature Detection using Conditional RegressionForests[Project]

·       Global and EfficientSelf-Similarity for Object Classification and Detection[code]

·        WαSH:Weighted α-Shapes for Local Feature Detection[Project]

·       HOG[Project]

·       Online Selection ofDiscriminative Tracking Features[Project]

                        

二、图像分割Image Segmentation：

·          Normalized Cut [1] [Matlab code]

·          Gerg Mori’ Superpixel code [2][Matlab code]

·          Efficient Graph-based ImageSegmentation [3] [C++ code] [Matlabwrapper]

·          Mean-Shift Image Segmentation [4][EDISONC++ code] [Matlabwrapper]

·          OWT-UCM Hierarchical Segmentation [5][Resources]

·          Turbepixels [6] [Matlabcode 32bit] [Matlab code 64bit] [Updatedcode]

·          Quick-Shift [7] [VLFeat]

·          SLIC Superpixels [8] [Project]

·          Segmentation by Minimum Code Length[9] [Project]

·          Biased Normalized Cut [10] [Project]

·          Segmentation Tree [11-12] [Project]

·          Entropy Rate Superpixel Segmentation[13] [Code]

·          Fast Approximate Energy Minimizationvia Graph Cuts[Paper][Code]

·          Efficient Planar Graph Cuts withApplications in Computer Vision[Paper][Code]

·          Isoperimetric Graph Partitioning forImage Segmentation[Paper][Code]

·          Random Walks for ImageSegmentation[Paper][Code]

·          Blossom V: A new implementation of aminimum cost perfect matching algorithm[Code]

·          An Experimental Comparison ofMin-Cut/Max-Flow Algorithms for Energy Minimization in ComputerVision[Paper][Code]

·          Geodesic Star Convexity forInteractive Image Segmentation[Project]

·          Contour Detection and ImageSegmentation Resources[Project][Code]

·          Biased Normalized Cuts[Project]

·          Max-flow/min-cut[Project]

·          Chan-Vese Segmentation using LevelSet[Project]

·          A Toolbox of Level SetMethods[Project]

·          Re-initialization Free Level SetEvolution via Reaction Diffusion[Project]

·          Improved C-V active contourmodel[Paper][Code]

·          A Variational Multiphase Level SetApproach to Simultaneous Segmentation and Bias Correction[Paper][Code]

·        Level Set MethodResearch by Chunming Li[Project]

·        ClassCut for Unsupervised ClassSegmentation[code]

·       SEEDS: SuperpixelsExtracted via Energy-Driven Sampling [Project][other]

 

三、目标检测Object Detection：

·          A simple object detector with boosting[Project]

·          INRIA Object Detection andLocalization Toolkit [1] [Project]

·          Discriminatively Trained DeformablePart Models [2] [Project]

·          Cascade Object Detection withDeformable Part Models [3] [Project]

·          Poselet [4] [Project]

·          Implicit Shape Model [5] [Project]

·          Viola and Jones’s Face Detection [6][Project]

·          Bayesian Modelling of Dyanmic Scenesfor Object Detection[Paper][Code]

·          Hand detection using multipleproposals[Project]

·          Color Constancy, Intrinsic Images, andShape Estimation[Paper][Code]

·          Discriminatively trained deformablepart models[Project]

·          Gradient Response Maps for Real-TimeDetection of Texture-Less Objects: LineMOD [Project]

·          Image Processing On Line[Project]

·          Robust Optical FlowEstimation[Project]

·          Where's Waldo: Matching People inImages of Crowds[Project]

·           ScalableMulti-class Object Detection[Project]

·           Class-SpecificHough Forests for Object Detection[Project]

·       Deformed LatticeDetection In Real-World Images[Project]

·       Discriminatively traineddeformable part models[Project]

 

四、显著性检测Saliency Detection：

·          Itti, Koch, and Niebur’ saliencydetection [1] [Matlab code]

·          Frequency-tuned salient regiondetection [2] [Project]

·          Saliency detection using maximumsymmetric surround [3] [Project]

·          Attention via Information Maximization[4] [Matlab code]

·          Context-aware saliency detection [5][Matlabcode]

·          Graph-based visual saliency [6][Matlab code]

·          Saliency detection: A spectralresidual approach. [7] [Matlabcode]

·          Segmenting salient objects from imagesand videos. [8] [Matlab code]

·          Saliency Using Natural statistics. [9][Matlab code]

·          Discriminant Saliency for VisualRecognition from Cluttered Scenes. [10] [Code]

·          Learning to Predict Where Humans Look[11] [Project]

·          Global Contrast based Salient RegionDetection [12] [Project]

·          Bayesian Saliency via Low and MidLevel Cues[Project]

·          Top-Down Visual Saliency via Joint CRFand Dictionary Learning[Paper][Code]

·       Saliency Detection: ASpectral Residual Approach[Code]

 

五、图像分类、聚类Image Classification,Clustering

·          Pyramid Match [1] [Project]

·          Spatial Pyramid Matching [2] [Code]

·          Locality-constrained Linear Coding [3][Project][Matlabcode]

·          Sparse Coding [4] [Project] [Matlabcode]

·          Texture Classification [5] [Project]

·          Multiple Kernels for ImageClassification [6] [Project]

·          Feature Combination [7] [Project]

·          SuperParsing [Code]

·          Large Scale Correlation ClusteringOptimization[Matlabcode]

·          Detecting and Sketching theCommon[Project]

·          Self-Tuning SpectralClustering[Project][Code]

·          User Assisted Separation ofReflections from a Single Image Using a Sparsity Prior[Paper][Code]

·          Filters for TextureClassification[Project]

·          Multiple Kernel Learning for ImageClassification[Project]

·        SLICSuperpixels[Project]

 

六、抠图Image Matting

·          A Closed Form Solution to NaturalImage Matting [Code]

·          Spectral Matting [Project]

·          Learning-based Matting [Code]

 

七、目标跟踪Object Tracking：

·          A Forest of Sensors - TrackingAdaptive Background Mixture Models [Project]

·          Object Tracking via Partial LeastSquares Analysis[Paper][Code]

·          Robust Object Tracking with OnlineMultiple Instance Learning[Paper][Code]

·          Online Visual Tracking with Histogramsand Articulating Blocks[Project]

·          Incremental Learning for Robust VisualTracking[Project]

·          Real-time CompressiveTracking[Project]

·          Robust Object Tracking viaSparsity-based Collaborative Model[Project]

·          Visual Tracking via AdaptiveStructural Local Sparse Appearance Model[Project]

·          Online Discriminative Object Trackingwith Local Sparse Representation[Paper][Code]

·          Superpixel Tracking[Project]

·          Learning Hierarchical ImageRepresentation with Sparsity, Saliency and Locality[Paper][Code]

·          Online Multiple Support InstanceTracking [Paper][Code]

·          Visual Tracking with Online MultipleInstance Learning[Project]

·          Object detection andrecognition[Project]

·          Compressive Sensing Resources[Project]

·          Robust Real-Time Visual Tracking usingPixel-Wise Posteriors[Project]

·          Tracking-Learning-Detection[Project][OpenTLD/C++ Code]

·           theHandVu：vision-based hand gesture interface[Project]

·        Learning ProbabilisticNon-Linear Latent Variable Models for Tracking ComplexActivities[Project]

 

八、Kinect：

·          Kinect toolbox[Project]

·          OpenNI[Project]

·          zouxy09 CSDN Blog[Resource]

·           FingerTracker手指跟踪[code]

 

九、3D相关：

·          3D Reconstruction of a MovingObject[Paper][Code]

·          Shape From Shading Using LinearApproximation[Code]

·          Combining Shape from Shading andStereo Depth Maps[Project][Code]

·          Shape from Shading: A Survey[Paper][Code]

·          A Spatio-Temporal Descriptor based on3D Gradients (HOG3D)[Project][Code]

·          Multi-camera Scene Reconstruction viaGraph Cuts[Paper][Code]

·          A Fast Marching Formulation ofPerspective Shape from Shading under Frontal Illumination[Paper][Code]

·          Reconstruction:3D Shape, Illumination,Shading, Reflectance, Texture[Project]

·          Monocular Tracking of 3D Human Motionwith a Coordinated Mixture of Factor Analyzers[Code]

·          Learning 3-D Scene Structure from aSingle Still Image[Project]

 

十、机器学习算法：

·          Matlab class for computing ApproximateNearest Nieghbor (ANN) [Matlabclass providing interface toANN library]

·          Random Sampling[code]

·          Probabilistic Latent Semantic Analysis(pLSA)[Code]

·          FASTANN and FASTCLUSTER forapproximate k-means (AKM)[Project]

·          Fast Intersection / Additive KernelSVMs[Project]

·          SVM[Code]

·          Ensemble learning[Project]

·          Deep Learning[Net]

·           DeepLearning Methods for Vision[Project]

·          Neural Network for Recognition ofHandwritten Digits[Project]

·          Training a deep autoencoder or aclassifier on MNIST digits[Project]

·        THE MNIST DATABASE ofhandwritten digits[Project]

·        Ersatz：deep neuralnetworks in the cloud[Project]

·        Deep Learning [Project]

·        sparseLM : SparseLevenberg-Marquardt nonlinear least squares in C/C++[Project]

·        Weka 3: Data MiningSoftware in Java[Project]

·        Invited talk "ATutorial on Deep Learning" by Dr. Kai Yu (余凯)[Video]

·        CNN - Convolutionalneural network class[MatlabTool]

·        Yann LeCun'sPublications[Wedsite]

·        LeNet-5, convolutionalneural networks[Project]

·        Training a deepautoencoder or a classifier on MNIST digits[Project]

·        Deep Learning 大牛Geoffrey E.Hinton's HomePage[Website]

·       Multiple InstanceLogistic Discriminant-based Metric Learning (MildML) and LogisticDiscriminant-based Metric Learning (LDML)[Code]

·       Sparse coding simulationsoftware[Project]

·       Visual Recognition andMachine Learning Summer School[Software]

 

十一、目标、行为识别Object, ActionRecognition：

·          Action Recognition by DenseTrajectories[Project][Code]

·          Action Recognition Using a DistributedRepresentation of Pose and Appearance[Project]

·          Recognition Using Regions[Paper][Code]

·          2D Articulated Human PoseEstimation[Project]

·          Fast Human Pose Estimation UsingAppearance and Motion via Multi-Dimensional BoostingRegression[Paper][Code]

·          Estimating Human Pose from OccludedImages[Paper][Code]

·          Quasi-dense wide baselinematching[Project]

·           ChaLearnGesture Challenge: Principal motion: PCA-basedreconstruction of motion histograms[Project]

·           RealTime Head Pose Estimation with Random RegressionForests[Project]

·           2DAction Recognition Serves 3D Human Pose Estimation[Project]

·           AHough Transform-Based Voting Framework for ActionRecognition[Project]

·         Motion InterchangePatterns for Action Recognition in Unconstrained Videos[Project]

·        2Darticulated human pose estimation software[Project]

·       Learning and detectingshape models [code]

·       Progressive Search SpaceReduction for Human Pose Estimation[Project]

·       Learning Non-Rigid 3DShape from 2D Motion[Project]

 

十二、图像处理：

·         DistanceTransforms of Sampled Functions[Project]

·       The Computer Vision Homepage[Project]

·       Efficient appearance distances betweenwindows[code]

·        ImageExploration algorithm[code]

·       Motion Magnification运动放大 [Project]

·       Bilateral Filtering forGray and Color Images 双边滤波器 [Project]

·        AFast Approximation of the Bilateral Filter using a SignalProcessing Approach [Project]

                  

十三、一些实用工具：

·          EGT: a Toolbox for Multiple ViewGeometry and Visual Servoing[Project] [Code]

·          a development kit of matlab mexfunctions for OpenCV library[Project]

·          Fast Artificial Neural NetworkLibrary[Project]

 

十四、人手及指尖检测与识别：

  finger-detection-and-gesture-recognition [Code]

  Hand andFinger Detection using JavaCV[Project]

  Handand fingers detection[Code]

 

十五、场景解释：

   Nonparametric Scene Parsingvia Label Transfer [Project]

 

十六、光流Opticalflow：

  High accuracy optical flow using a theory forwarping [Project]

  DenseTrajectories Video Description [Project]

  SIFTFlow: Dense Correspondence across Scenes and itsApplications[Project]

  KLT:An Implementation of the Kanade-Lucas-Tomasi Feature Tracker[Project]

  Tracking Cars Using Optical Flow[Project]

  Secretsof optical flow estimation and their principles[Project]

·       implmentation of theBlack and Anandan dense optical flow method[Project]

·       Optical FlowComputation[Project]

·       Beyond Pixels: ExploringNew Representations and Applications for Motion Analysis[Project]

·       A Database andEvaluation Methodology for Optical Flow[Project]

·       optical flowrelative[Project]

·       Robust Optical FlowEstimation [Project]

·       opticalflow[Project]

十七、图像检索ImageRetrieval：

   Semi-Supervised DistanceMetric Learning for Collaborative ImageRetrieval [Paper][code]

 

十八、马尔科夫随机场Markov RandomFields：

   Markov Random Fields forSuper-Resolution [Project]

  A Comparative Study of Energy MinimizationMethods for Markov Random Fields with Smoothness-Based Priors[Project]

十九、运动检测Motiondetection：

·         MovingObject Extraction, Using Models or Analysis ofRegions [Project]

·       Background Subtraction:Experiments and Improvements for ViBe [Project]

·       A Self-OrganizingApproach to Background Subtraction for Visual SurveillanceApplications [Project]

·       changedetection.net: Anew change detection benchmark dataset[Project]

·       ViBe - a powerfultechnique for background detection and subtraction in videosequences[Project]

·       Background SubtractionProgram[Project]

·       Motion DetectionAlgorithms[Project]

·       Stuttgart ArtificialBackground Subtraction Dataset[Project]

·       Object Detection, MotionEstimation, and Tracking[Project]

============================================================================================

下述信息来源于中科院自动化所网站

http://www.sigvc.org/why/resource.htm

People (Currentlyrelated to me, but NOT ALL, ref. [HongboFu's link]):

Current：

Hao LiMichael WandDaniel VlasicCedric CagniartJuergen GallJonathan StarckAndriy MyronenkoRadu Patrice HORAUDDragomir Anguelov (Drago)Qi-xing HuangWillChangMisha Kazhdan codesNiloy J. MitraRuigang Yangpointclouds库pascal fuaRyanSchmidt (图形学源码)Daniel Sýkora（卡通）Mingtian Zhao（卡通）Tai-Pang Wu(照片立体重建)Xuejin Chen (科大)Vladlen Koltun (NIPS/Siggraph)Point cloud library, blog,blog2,liuce(视觉，视频运动代码)LeFang（北航），RonaldFedkiw（Stanford）Iain Matthews (AAM)Vladimir G. Kim (形状对应,princeton)Lorenzo Torresani (NIPS) codeNilsHasler (统计人体模型)Alexandru Balan （三维人体from图片）Marcel Germann (运动场multiview三维显示)Voicu PopescuFaceAPIAAM, AAM2

　US：

Raif M.RustamovRonaldFedkiw, Leo Guibas, Pat Hanrahan, Marc Levoy@Stanford, ZoranPopović, （运动捕捉）Steven M. Seitz, BrianCurless, David H.Salesin@Washington, SaraMcMains, David A.Forsyth, James F.O'Brien, Brian A.Barsky, Carlo H.Séquin, JonathanShewchuk, MartinIsenburg, ManeeshAgrawala@Berkeley, HuguesHoppe, （网格渐进压缩）Ross T. WhitakerCharlesLoop, JimBlinn, MichaelCohen, RichardSzeliski@Microsoft, Levent Burak Kara, KenjiShimada, Jessica K.Hodgins@CMU, Ken Perlin, Denis Zorin@NYU, Alan H. Barr,MathieuDesbrun, （微分几何）Peter Schröder, Yiying Tong@CalTech,（DEC）Lexing Ying@UTexas, FrédoDurand (Bookmarks), AnatLevin, SylvainParis, JovanPopović@MIT, （动画）Anil N.Hirani, （DEC）YizhouYu, （形变）Michael Garland, （网格简化、处理）John C.Hart@UIUC, EitanGrinspun, Shree K.Nayar, (视觉图形渲染)RaviRamamoorthi@Columbia, Szymon Rusinkiewicz, Adam Finkelstein, Thomas A.Funkhouser@Princeton, StevenJ. Gortler@Harvard, Henry Fuchs, Dinesh ManochaUNC, Ming C. Lin@UNC, Ken Joy,BerndHamann, NinaAmenta, Kwan-LiuMa@UC Davis, Arie Kaufman, XianfengGu,（几何处理，Conformal Structure ，General Purpose Mesh Library） HongQin@SunySB, （几何处理）Henrik WannJensen, MatthiasZwicker@UCSD, DougDeCarlo@Rutgers, David H.Laidlaw, Andy van Dam, Gabriel Taubin, John F.Hughes@Brown, Scott Schaefer, Ron Goldman, Joe Warren@Rice, JorgPeters@UFL, IrfanEssa, Peter J.Mucha, JarekRossignac, GregTurk@GaTech, Jonathan D.Cohen, MichaelKazhdan@JHU, CindyGrimm, （参数化）TaoJu@WUSTL, （几何处理）Ilya Eckstein（几何流，变分）ClaudioSilva@Utah, Tamal K. Dey@Ohio State, WojciechMatusik, Ramesh Raskar, HanspeterPfister@Merl, Jos Stam@Autodesk, UlrichNeumann, Paul Debevec@USC, KaruhiroSaitou, LeeMarkosian, Igor Guskov@Umich, （DGP）Normann I. Badler @Upenn, ValerioPascucci, Peter Lindstrom@LLNL, Fuhua(Frank) Cheng@Kentucky, BaoquanChen@UMN, Ioana Boier-Martin@IBM, HerbertEdelsbrunner@Duke, AndreiKhodakovsky@nVidia, VadimShapiro, Michael Gleicher@Wisconsin, DavidEbert @Purdue, GopiMeenakshisundaram@UCI, TomasSederberg@Brigham Young Univ., Doug L. James@Cornell, PetrosFaloutsos, DemetriTerzopoulos@UCLA, Chandrajit Bajaj, Okan Arikan@Texas, AmitabhVarshney@Maryland, JulieDorsey@Yale, RuiWang@UMass CarstenRother（图像纹理）HaibinLing（视觉图像）JohnSchreiner （参数化、remesh；surface triangulation源码）Dr.Benedict J. Brown（几何匹配，文化遗产保护，源码和博士论文）Song-ChunZhu（视觉，统计，Markov Chain Monte Carlo for Computer VisionICCV05教程）Ross T.Whitaker（可视化、图像，视觉）ZhengyouZhangStéphane Mallat（小波）Yingnian Wu（UCLA统计）TimCootes（AAM，ASM）David Lowe（Sift）Jinxiang ChaiMichael M. Bronstein (CG& CV)Jean-YvesBouguet （标定，重建）

Germany：

Alexander G. Belyaev, Zachi Karni, RhalebZayer, （DGP）Hans-PeterSeidel@MPI, Leif Kobbelt@RWTH, （大组）OlgaSorkine, （几何处理）MarcAlexa@TU Berlin, KonradPolthier@FU Berlin, Stefan Gumhold@TU dresden, Hans-ChristianHege@ZIB, Kai Hormann@TU Clausthal（参数化）VolkerBlanz（morphing model）Holger Theisel（可视化、图形学结合）Daniel Weiskopf（可视化）

Canada：

VladislavKraevoy, （DGP）AllaSheffa, Dinesh K.Pai@UBC, Aaron Hertzmann, KaranSingh, Eugene Fiume@Toronto,Hao Zhang@SFU, @Waterloo（谱分析，DGP课程）Oliver Matiasvan Kaick（谱方法，压缩）Martin Reuter(谱方法，MIT)

UK：

Frank Langbein, Ralph R.Martin@Cardiff, Jiang J Zhang@Bournemouth, AlanChalmers@Bristol, NeilDodgson, PeterRobinson@Cambridge VladimirKolmogorov （graphcut，Markov Random Fields(MRFs)，courses）EdwinHancock（图论统计视觉）ChristopherM. Bishop

China Mainland：

Hongxin Zhang, （数学课程）雍俊海Ligang Liu, （刘利刚）潘春洪Xiaogang Jin, GuopingWang, 北大软件研究所XinguoLiu, Wei Chen,JiaoyingShi, QunshengPeng, 王文成HujunBao@ZJU, Shimin Hu@tsinghua, 雍俊海Kun Zhou, 浙大，blogXin Tong, （渲染）Jian Sun, Stephen Lin, BainingGuo, Heung-Yeung Shum@MSRA, Hongbin Zha@PKU, Falai Chen@USTC 陈宝权（深圳研究院，可视化，三维扫描）郭延文（图像纹理）章国锋（浙大，视频视觉处理）WeiChen（图像，可视化，有PDE和游戏的课程）胡事民LiefengBo（西电，机器学习，SVM代码）Haifeng GongGang ZENG Yong Liu （蒋田仔医学图象）刘青山林倞

Taiwan：

Tong-Yee Lee@ncku

HongKong：

Chiew-Lan Tai, Long Quan, Chi-Keung Tang,Huamin Qu, Philip Fu, AlbertCHUNG, PedroSander, KaiTang@HKUST, WenpingWang@HKU, （CAD）Charlie C.L. Wang, JiayaJia, Tien-TsinWong, （渲染）HengPheng-Ann@CUHK, ???@CityU, BACIUGeorgei@PolyU Dr. Kenneth K.Y.Wong(视觉建模)Hongbo FuOscar Kin-ChungAu（形变建模）Tai-Pang WU（图像视觉）Horace IpHo-shing

Macao：

EnhuaWu@UMac

Israel：

Yaron Lipman, （微分几何建模）DanielCohen-Or, （几何处理，大组）DavidLevin@Tel Aviv, Craig Gotsman, GillBarequet, GershonElber, RonKimmel, Ayellet Tal@Technion, Dani Lischinski@HUJI AndreiSharf（几何建模，修复）SagiKatz （网格分割）Nir Sochen (CVBeltrami)

Austria：

Helmut Pottmann,（几何）Qixing Huang, MichaelHofer, AndreasAsperl, MartinPeternell, Johannes Wallner, Werner Purgathofer@TU Wien, BertJüttler@JKU Dr. AJMAL S.MIAN（视觉建模）LiangWang
　

Japan：

TomoyukiNishita, Takashi Kanai, Takeo Igarashi@Toyko, （sketch）Yutaka Ohtake@RIKENKenichi Kanatani （射影几何代码）Andrew Nealen （sketch）

Korea：

Myung-SooKim, Hyeong-Seok Ko@Seoul, SungYong Shin@KAIST Yunjin Lee（分割）

Singapore：

MichaelBrown@NTU, Tan Tiow Seng, ZhiyongHuang, Chionh EngWee@NUS ShuichengYan（视觉机器学习）谭平（视觉建模）

发Science paper的人：JoshTenenbaum （MIT）； Tomaso Poggio（MIT）