计算机视觉、机器学习相关领域论文和源代码大集合

简介: 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…… zouxy09@qq.com http://blog.csdn.net/zouxy09 注:下面有project网站的大部分都有paper和相应的code。

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……

zouxy09@qq.com

http://blog.csdn.net/zouxy09

注:下面有project网站的大部分都有paper和相应的codeCode一般是C/C++或者Matlab代码。

最近一次更新:2013-3-17


一、特征提取Feature Extraction:

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

·         PCA-SIFT [2] [Project]

·         Affine-SIFT [3] [Project]

·         SURF [4] [OpenSURF] [Matlab Wrapper]

·         Affine Covariant Features [5] [Oxford project]

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

·         Geometric Blur [7] [Code]

·         Local Self-Similarity Descriptor [8] [Oxford implementation]

·         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 Oriented Gradients [Code]

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

·         Boundary Preserving Dense Local Regions [15][Project]

·         Weighted Histogram[Code]

·         Histogram-based Interest Points Detectors[Paper][Code]

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

·         Fast Sparse Representation with Prototypes[Project]

·         Corner Detection [Project]

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

·         Real-time Facial Feature Detection using Conditional Regression Forests[Project]

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

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

·         HOG[Project]

·         Online Selection of Discriminative 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 Image Segmentation [3] [C++ code] [Matlab wrapper]

·           Mean-Shift Image Segmentation [4] [EDISON C++ code] [Matlab wrapper]

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

·           Turbepixels [6] [Matlab code 32bit] [Matlab code 64bit] [Updated code]

·           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 Minimization via Graph Cuts[Paper][Code]

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

·           Isoperimetric Graph Partitioning for Image Segmentation[Paper][Code]

·           Random Walks for Image Segmentation[Paper][Code]

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

·           An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Computer Vision[Paper][Code]

·           Geodesic Star Convexity for Interactive Image Segmentation[Project]

·           Contour Detection and Image Segmentation Resources[Project][Code]

·           Biased Normalized Cuts[Project]

·           Max-flow/min-cut[Project]

·           Chan-Vese Segmentation using Level Set[Project]

·           A Toolbox of Level Set Methods[Project]

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

·           Improved C-V active contour model[Paper][Code]

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

·          Level Set Method Research by Chunming Li[Project]

·          ClassCut for Unsupervised Class Segmentation[code]

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

三、目标检测Object Detection:

·           A simple object detector with boosting [Project]

·           INRIA Object Detection and Localization Toolkit [1] [Project]

·           Discriminatively Trained Deformable Part Models [2] [Project]

·           Cascade Object Detection with Deformable Part Models [3] [Project]

·           Poselet [4] [Project]

·           Implicit Shape Model [5] [Project]

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

·           Bayesian Modelling of Dyanmic Scenes for Object Detection[Paper][Code]

·           Hand detection using multiple proposals[Project]

·           Color Constancy, Intrinsic Images, and Shape Estimation[Paper][Code]

·           Discriminatively trained deformable part models[Project]

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

·           Image Processing On Line[Project]

·           Robust Optical Flow Estimation[Project]

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

·           Scalable Multi-class Object Detection[Project]

·           Class-Specific Hough Forests for Object Detection[Project]

·         Deformed Lattice Detection In Real-World Images[Project]

·         Discriminatively trained deformable part models[Project]

四、显著性检测Saliency Detection:

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

·           Frequency-tuned salient region detection [2] [Project]

·           Saliency detection using maximum symmetric surround [3] [Project]

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

·           Context-aware saliency detection [5] [Matlab code]

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

·           Saliency detection: A spectral residual approach. [7] [Matlab code]

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

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

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

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

·           Global Contrast based Salient Region Detection [12] [Project]

·           Bayesian Saliency via Low and Mid Level Cues[Project]

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

·         Saliency Detection: A Spectral 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] [Matlab code]

·           Sparse Coding [4] [Project] [Matlab code]

·           Texture Classification [5] [Project]

·           Multiple Kernels for Image Classification [6] [Project]

·           Feature Combination [7] [Project]

·           SuperParsing [Code]

·           Large Scale Correlation Clustering Optimization[Matlab code]

·           Detecting and Sketching the Common[Project]

·           Self-Tuning Spectral Clustering[Project][Code]

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

·           Filters for Texture Classification[Project]

·           Multiple Kernel Learning for Image Classification[Project]

·          SLIC Superpixels[Project]

六、抠图Image Matting

·           A Closed Form Solution to Natural Image Matting [Code]

·           Spectral Matting [Project]

·           Learning-based Matting [Code]

七、目标跟踪Object Tracking:

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

·           Object Tracking via Partial Least Squares Analysis[Paper][Code]

·           Robust Object Tracking with Online Multiple Instance Learning[Paper][Code]

·           Online Visual Tracking with Histograms and Articulating Blocks[Project]

·           Incremental Learning for Robust Visual Tracking[Project]

·           Real-time Compressive Tracking[Project]

·           Robust Object Tracking via Sparsity-based Collaborative Model[Project]

·           Visual Tracking via Adaptive Structural Local Sparse Appearance Model[Project]

·           Online Discriminative Object Tracking with Local Sparse Representation[Paper][Code]

·           Superpixel Tracking[Project]

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

·           Online Multiple Support Instance Tracking [Paper][Code]

·           Visual Tracking with Online Multiple Instance Learning[Project]

·           Object detection and recognition[Project]

·           Compressive Sensing Resources[Project]

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

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

·           the HandVu:vision-based hand gesture interface[Project]

·           Learning Probabilistic Non-Linear Latent Variable Models for Tracking Complex Activities[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 Moving Object[Paper] [Code]

·           Shape From Shading Using Linear Approximation[Code]

·           Combining Shape from Shading and Stereo Depth Maps[Project][Code]

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

·           A Spatio-Temporal Descriptor based on 3D Gradients (HOG3D)[Project][Code]

·           Multi-camera Scene Reconstruction via Graph Cuts[Paper][Code]

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

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

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

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

十、机器学习算法:

·           Matlab class for computing Approximate Nearest Nieghbor (ANN) [Matlab class providing interface toANN library]

·           Random Sampling[code]

·           Probabilistic Latent Semantic Analysis (pLSA)[Code]

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

·           Fast Intersection / Additive Kernel SVMs[Project]

·           SVM[Code]

·           Ensemble learning[Project]

·           Deep Learning[Net]

·           Deep Learning Methods for Vision[Project]

·           Neural Network for Recognition of Handwritten Digits[Project]

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

·          THE MNIST DATABASE of handwritten digits[Project]

·          Ersatz:deep neural networks in the cloud[Project]

·          Deep Learning [Project]

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

·          Weka 3: Data Mining Software in Java[Project]

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

·          CNN - Convolutional neural network class[Matlab Tool]

·          Yann LeCun's Publications[Wedsite]

·          LeNet-5, convolutional neural networks[Project]

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

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

·         Multiple Instance Logistic Discriminant-based Metric Learning (MildML) and Logistic Discriminant-based Metric Learning (LDML)[Code]

·         Sparse coding simulation software[Project]

·         Visual Recognition and Machine Learning Summer School[Software]

十一、目标、行为识别Object, Action Recognition:

·           Action Recognition by Dense Trajectories[Project][Code]

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

·           Recognition Using Regions[Paper][Code]

·           2D Articulated Human Pose Estimation[Project]

·           Fast Human Pose Estimation Using Appearance and Motion via Multi-Dimensional Boosting Regression[Paper][Code]

·           Estimating Human Pose from Occluded Images[Paper][Code]

·           Quasi-dense wide baseline matching[Project]

·           ChaLearn Gesture Challenge: Principal motion: PCA-based reconstruction of motion histograms[Project]

·           Real Time Head Pose Estimation with Random Regression Forests[Project]

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

·           A Hough Transform-Based Voting Framework for Action Recognition[Project]

·           Motion Interchange Patterns for Action Recognition in Unconstrained Videos[Project]

·         2D articulated human pose estimation software[Project]

·         Learning and detecting shape models [code]

·         Progressive Search Space Reduction for Human Pose Estimation[Project]

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

十二、图像处理:

·         Distance Transforms of Sampled Functions[Project]

·        The Computer Vision Homepage[Project]

·        Efficient appearance distances between windows[code]

·         Image Exploration algorithm[code]

·         Motion Magnification 运动放大 [Project]

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

·         A Fast Approximation of the Bilateral Filter using a Signal Processing Approach [Project]

                 

十三、一些实用工具:

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

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

·           Fast Artificial Neural Network Library[Project]

十四、人手及指尖检测与识别:

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

·           Hand and Finger Detection using JavaCV[Project]

·           Hand and fingers detection[Code]


十五、场景解释:

·           Nonparametric Scene Parsing via Label Transfer [Project]


十六、光流Optical flow:

·         High accuracy optical flow using a theory for warping [Project]

·         Dense Trajectories Video Description [Project]

·         SIFT Flow: Dense Correspondence across Scenes and its Applications[Project]

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

·         Tracking Cars Using Optical Flow[Project]

·         Secrets of optical flow estimation and their principles[Project]

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

·         Optical Flow Computation[Project]

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

·         A Database and Evaluation Methodology for Optical Flow[Project]

·         optical flow relative[Project]

·         Robust Optical Flow Estimation [Project]

·         optical flow[Project]


十七、图像检索Image Retrieval

·           Semi-Supervised Distance Metric Learning for Collaborative Image Retrieval [Paper][code]


十八、马尔科夫随机场Markov Random Fields:

·         Markov Random Fields for Super-Resolution [Project]

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


十九、运动检测Motion detection:

·         Moving Object Extraction, Using Models or Analysis of Regions [Project]

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

·         A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications [Project]

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

·         ViBe - a powerful technique for background detection and subtraction in video sequences[Project]

·         Background Subtraction Program[Project]

·         Motion Detection Algorithms[Project]

·         Stuttgart Artificial Background Subtraction Dataset[Project]

·         Object Detection, Motion Estimation, and Tracking[Project]

相关文章
|
机器学习/深度学习 编解码 资源调度
2024年3月的计算机视觉论文推荐
从去年开始,针对LLM的研究成为了大家关注的焦点。但是其实针对于计算机视觉的研究领域也在快速的发展。每周都有计算机视觉领域的创新研究,包括图像识别、视觉模型优化、生成对抗网络(gan)、图像分割、视频分析等。
536 0
|
机器学习/深度学习 自然语言处理 算法
2024年4月计算机视觉论文推荐
四月的计算机视觉研究涵盖多个子领域,包括扩散模型和视觉语言模型。在扩散模型中,Tango 2通过直接偏好优化改进了文本到音频生成,而Ctrl-Adapter提出了一种有效且通用的框架,用于在图像和视频扩散模型中添加多样控制。视觉语言模型的论文分析了CLIP模型在有限资源下的优化,并探讨了语言引导对低级视觉任务的鲁棒性。图像生成与编辑领域关注3D感知和高质量图像编辑,而视频理解与生成则涉及实时视频转游戏环境和文本引导的剪贴画动画。
403 0
|
机器学习/深度学习 算法 大数据
【2023年MathorCup高校数学建模挑战赛-大数据竞赛】赛道A:基于计算机视觉的坑洼道路检测和识别 python 代码解析
本文提供了2023年MathorCup高校数学建模挑战赛大数据竞赛赛道A的解决方案,涉及基于计算机视觉的坑洼道路检测和识别任务,包括数据预处理、特征提取、模型建立、训练与评估等步骤的Python代码解析。
505 44
【2023年MathorCup高校数学建模挑战赛-大数据竞赛】赛道A:基于计算机视觉的坑洼道路检测和识别 python 代码解析
|
机器学习/深度学习 算法 TensorFlow
机器学习中的图像处理与计算机视觉
在现代计算机科学中,图像处理和计算机视觉已成为最活跃的研究领域之一,这得益于机器学习和深度学习的发展。本文将深入探讨图像处理与计算机视觉的基础概念、常见应用、关键技术、常用工具,以及在这些领域中的代码示例。通过本篇文章,我们将了解如何从头开始构建一个简单的计算机视觉系统,并探索这些技术背后的原理。
|
机器学习/深度学习 算法 PyTorch
【机器学习】大模型环境下的应用:计算机视觉的探索与实践
【机器学习】大模型环境下的应用:计算机视觉的探索与实践
507 1
|
机器学习/深度学习 PyTorch 算法框架/工具
聊一聊计算机视觉中常用的注意力机制以及Pytorch代码实现
本文介绍了几种常用的计算机视觉注意力机制及其PyTorch实现,包括SENet、CBAM、BAM、ECA-Net、SA-Net、Polarized Self-Attention、Spatial Group-wise Enhance和Coordinate Attention等,每种方法都附有详细的网络结构说明和实验结果分析。通过这些注意力机制的应用,可以有效提升模型在目标检测任务上的性能。此外,作者还提供了实验数据集的基本情况及baseline模型的选择与实验结果,方便读者理解和复现。
1470 0
聊一聊计算机视觉中常用的注意力机制以及Pytorch代码实现
|
计算机视觉 Python
计算机视觉---数字图像代码示例
计算机视觉---数字图像代码示例
299 1
|
编解码 机器人 测试技术
2024年6月计算机视觉论文推荐:扩散模型、视觉语言模型、视频生成等
6月还有一周就要结束了,我们今天来总结2024年6月上半月发表的最重要的论文,重点介绍了计算机视觉领域的最新研究和进展。
799 8
|
机器学习/深度学习 数据采集 算法
隧道裂纹识别:基于计算机视觉与机器学习的应用分享
隧道裂纹的自动检测通过深度学习与计算机视觉技术实现,替代了传统人工检查,提高了检测精度与效率。本文介绍了一套完整的裂纹检测流程,包括图像采集、预处理、裂纹检测与标定、后处理及结果展示,提供了图像处理与深度学习模型的基本代码框架,旨在帮助读者掌握隧道裂纹检测的实际应用方法。
|
人工智能 计算机视觉
AI计算机视觉笔记十五:编写检测的yolov5测试代码
该文为原创文章,如需转载,请注明出处。本文作者在成功运行 `detect.py` 后,因代码难以理解而编写了一个简易测试程序,用于加载YOLOv5模型并检测图像中的对象,特别是“人”类目标。代码实现了从摄像头或图片读取帧、进行颜色转换,并利用YOLOv5进行推理,最后将检测框和置信度绘制在输出图像上,并保存为 `result.jpg`。如果缺少某些模块,可使用 `pip install` 安装。如涉及版权问题或需获取完整代码,请联系作者。

热门文章

最新文章