深度学习有开源代码的文献

 

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

视频结构化分析平台 
https://github.com/AKSHAYUBHAT/DeepVideoAnalytics