开源的深度学习论文
转 https://blog.csdn.net/qq_28413479/article/details/78048862
人群分析
Novel Dataset for Fine-grained Abnormal Behavior Understanding in Crowd
人群异常行为数据库:https://github.com/hosseinm/med Panic,Fight,Congestion,Obstacle ,Neutral
Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
https://www.microsoft.com/en-us/research/publication/deep-spatio-temporal-residual-networks-for-citywide-crowd-flows-prediction/
https://github.com/lucktroy/DeepST/tree/master/scripts/papers/AAAI17
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition ECCV2016
https://github.com/yjxiong/temporal-segment-networks
Towards Good Practices for Very Deep Two-stream ConvNets
http://yjxiong.me/others/action_recog/
https://github.com/yjxiong/caffe
基于单张RGB图像的 3D 人体姿态估计
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image CVPR2017
http://www0.cs.ucl.ac.uk/staff/D.Tome/papers/LiftingFromTheDeep.html
https://github.com/DenisTome/Lifting-from-the-Deep-release
视频中的时空特征
Learning Spatiotemporal Features with 3D Convolutional Networks ICCV 2015
http://vlg.cs.dartmouth.edu/c3d/
https://github.com/facebook/C3D
Measuring Crowd Collectiveness
CVPR2013
http://mmlab.ie.cuhk.edu.hk/projects/collectiveness/
https://github.com/metalbubble/collectiveness
Scene-Independent Group Profiling in Crowd CVPR2014
http://www.ee.cuhk.edu.hk/~jshao/CUHKcrowd.html
https://github.com/amiltonwong/crowd_group_profile
Deeply Learned Attributes for Crowded Scene Understanding CVPR2015
http://www.ee.cuhk.edu.hk/~jshao/WWWCrowdDataset.html
https://github.com/amandajshao/www_deep_crowd
Slicing Convolutional Neural Network for Crowd Video Understanding CVPR2016
http://www.ee.cuhk.edu.hk/~jshao/SCNN.html
Caffe code: https://github.com/amandajshao/Slicing-CNN
End-to-end people detection in crowded scenes CVPR2016
https://github.com/Russell91/ReInspect
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network CVPR2016
https://github.com/svishwa/crowdcount-mcnn
https://github.com/leeyeehoo/Reduplication-of-Single-Image-Crowd-Counting-via-MCNN-on-UCF-Dataset
Switching Convolutional Neural Network for Crowd Counting CVPR2017
https://github.com/val-iisc/crowd-counting-scnn
视频合成
Generating Videos with Scene Dynamics NIPS2016
http://carlvondrick.com/tinyvideo/
Torch7 https://github.com/cvondrick/videogan
Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
https://coxlab.github.io/prednet/
Keras https://github.com/coxlab/prednet
Flexible Spatio-Temporal Networks for Video Prediction CVPR2017
视频中的运动模式学习
Learning Motion Patterns in Videos CVPR2017
http://thoth.inrialpes.fr/research/mpnet
图像语义匹配
SCNet: Learning Semantic Correspondence ICCV2017
Matlab code: https://github.com/k-han/SCNet
特征匹配
GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence CVPR2017
c++ code: https://github.com/JiawangBian/GMS-Feature-Matcher
目标检测 — 加速候选区域提取
DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling ICCV2017
https://github.com/lachlants/denet
【Dlib 19.5车辆检测】《Vehicle Detection with Dlib 19.5》
http://blog.dlib.net/2017/08/vehicle-detection-with-dlib-195_27.html
基于语义的视频快进,不丢失感兴趣物体的快进
Fast-Forward Video Based on Semantic Extraction
GitHub: https://github.com/verlab/SemanticFastForward_ICIP_2016
残差网络超快训练
Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates
https://github.com/lnsmith54/super-convergence
深度边缘检测
Richer Convolutional Features for Edge Detection CVPR2017
https://github.com/yun-liu/rcf
目标检测
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection ECCV2016
https://github.com/zhaoweicai/mscnn
目标检测
RON: Reverse Connection with Objectness Prior Networks for Object Detection CVPR2017
https://github.com/taokong/RON
同时检测和分割,类似 Mask R-CNN
BlitzNet: A Real-Time Deep Network for Scene Understanding ICCV2017
https://github.com/dvornikita/blitznet
网络裁剪加速
Learning Efficient Convolutional Networks through Network Slimming ICCV2017
https://github.com/liuzhuang13/slimming
CNN网络通道裁剪加速
Channel Pruning for Accelerating Very Deep Neural Networks ICCV2017
https://github.com/yihui-he/channel-pruning
pytorch tutorial
https://github.com/soravux/pytorch_tutorial
目标候选区域分割
FastMask: Segment Multi-scale Object Candidates in One Shot CVPR2017
https://github.com/voidrank/FastMask
新的池化方法
S3Pool: Pooling with Stochastic Spatial Sampling CVPR2017
https://github.com/Shuangfei/s3pool
CNN 图像检索
Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations CVPR2017
https://github.com/ahmetius/diffusion-retrieval
基于查表的CNN网络模型
LCNN: Lookup-based Convolutional Neural Network CVPR2017
https://github.com/hessamb/lcnn
人脸检测
Recurrent Scale Approximation for Object Detection in CNN ICCV2017
https://github.com/sciencefans/RSA-for-object-detection
数据扩张 Image Augmentation tool
Augmentor: An Image Augmentation Library for Machine Learning
GitHub: https://github.com/mdbloice/Augmentor
人脸识别
SphereFace: Deep Hypersphere Embedding for Face Recognition CVPR2017
https://github.com/wy1iu/sphereface
语义分割
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation CVPRW 2017
Theano/Lasagne code Implementation
https://github.com/0bserver07/One-Hundred-Layers-Tiramisu
语义分割
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes CVPR2017
https://github.com/TobyPDE/FRRN
目标检测
DSOD: Learning Deeply Supervised Object Detectors from Scratch ICCV2017
https://github.com/szq0214/DSOD
语义分割:
Awesome Semantic Segmentation
https://github.com/mrgloom/awesome-semantic-segmentation
Semantic Segmentation Algorithms Implemented in PyTorch 这个很好!
https://github.com/meetshah1995/pytorch-semseg
Learning Deconvolution Network for Semantic Segmentation
https://github.com/HyeonwooNoh/DeconvNet
Fully Convolutional Instance-aware Semantic Segmentation
https://github.com/daijifeng001/TA-FCN
Fully Convolutional Networks for Semantic Segmentation
https://github.com/shelhamer/fcn.berkeleyvision.org
PixelNet: Representation of the pixels, by the pixels, and for the pixels
https://github.com/aayushbansal/PixelNet
http://www.cs.cmu.edu/~aayushb/pixelNet/
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
https://hszhao.github.io/projects/icnet/
https://github.com/hszhao/ICNet
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Semantic Pixel-Wise Labelling
https://arxiv.org/pdf/1511.00561.pdf PAMI-2017
https://github.com/alexgkendall/caffe-segnet
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
https://bitbucket.org/aquariusjay/deeplab-public-ver2/overview
DeconvNet : Learning Deconvolution Network for Semantic Segmentation ICCV2015
https://github.com/HyeonwooNoh/DeconvNet
http://cvlab.postech.ac.kr/research/deconvnet/
Pyramid Scene Parsing Network CVPR2017
https://github.com/hszhao/PSPNet
Fully Convolutional Instance-aware Semantic Segmentation CVPR2017
https://github.com/msracver/FCIS
ParseNet: Looking Wider to See Better
https://github.com/weiliu89/caffe/tree/fcn
深度网络模型:
Deep Residual Learning for Image Recognition
https://github.com/KaimingHe/deep-residual-networks
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks
for Real-Time Object Detection for Autonomous Driving
https://github.com/BichenWuUCB/squeezeDet
Coordinating Filters for Faster Deep Neural Networks
https://arxiv.org/abs/1703.09746
https://github.com/wenwei202/caffe/tree/sfm
Network Dissection:
Quantifying Interpretability of Deep Visual Representations
CVPR2017
https://github.com/CSAILVision/NetDissect
人脸识别
C++ 代码: https://github.com/seetaface/SeetaFaceEngine
A Discriminative Feature Learning Approach for Deep Face Recognition
code: https://github.com/ydwen/caffe-face
目标检测:
PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
https://github.com/sanghoon/pva-faster-rcnn
R-FCN: Object Detection via Region-based Fully Convolutional Networks
https://github.com/daijifeng001/r-fcn
A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection CVPR 2017
Caffe code : https://github.com/xiaolonw/adversarial-frcnn
Improving Object Detection With One Line of Code
https://github.com/bharatsingh430/soft-nms
行人检测:
Is Faster R-CNN Doing Well for Pedestrian Detection? ECCV2016
https://github.com/zhangliliang/RPN_BF/tree/RPN-pedestrian
人体姿态估计:
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields CVPR2017
https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation
Convolutional Pose Machines CVPR2016
https://github.com/shihenw/convolutional-pose-machines-release
深度图片风格迁移
Deep Photo Style Transfer
https://github.com/luanfujun/deep-photo-styletransfer
检测
Accurate Single Stage Detector Using Recurrent Rolling Convolution
https://github.com/xiaohaoChen/rrc_detection
人脸修复
Generative Face Completion
https://github.com/Yijunmaverick/GenerativeFaceCompletion
Failures of Gradient-Based Deep Learning
https://github.com/shakedshammah/failures_of_DL
深度视频去模糊
Deep Video Deblurring
https://github.com/shuochsu/DeepVideoDeblurring
深度去噪
Learning Deep CNN Denoiser Prior for Image Restoration
https://github.com/cszn/ircnn
人脸超分辨
Face Super-Resolution Through Wasserstein GANs
https://github.com/MandyZChen/srez
https://github.com/YuguangTong/improved_wgan_training