1. 程式人生 > >各類識別、深度學習 開原始碼及文獻梳理

各類識別、深度學習 開原始碼及文獻梳理

Deep Residual Networks

Deep Residual Learning for Image Recognition 
https://github.com/KaimingHe/deep-residual-networks

Identity Mappings in Deep Residual Networks (by Kaiming He)

arxiv: http://arxiv.org/abs/1603.05027 
github: https://github.com/KaimingHe/resnet-1k-layers

 
github: https://github.com/bazilas/matconvnet-ResNet 
github: https://github.com/FlorianMuellerklein/Identity-Mapping-ResNet-Lasagne

Wide Residual Networks

arxiv: http://arxiv.org/abs/1605.07146 
github: https://github.com/szagoruyko/wide-residual-networks 
github: 

https://github.com/asmith26/wide_resnets_keras

Inception-V4, Inception-Resnet And The Impact Of Residual Connections On Learning (Workshop track - ICLR 2016)

intro: “achieve 3.08% top-5 error on the test set of the ImageNet classification (CLS) challenge” 
arxiv: http://arxiv.org/abs/1602.07261 
paper: 

http://beta.openreview.net/pdf?id=q7kqBkL33f8LEkD3t7X9 
github: https://github.com/lim0606/torch-inception-resnet-v2

Object detection 
Object detection via a multi-region & semantic segmentation-aware CNN model 
https://github.com/gidariss/mrcnn-object-detection

DeepBox: Learning Objectness with Convolutional Networks ICCV2015 
proposal re-ranker 
https://github.com/weichengkuo/DeepBox

Object-Proposal Evaluation Protocol is ‘Gameable’ 好多 Proposal 程式碼 
https://github.com/batra-mlp-lab/object-proposals

Fast R-CNN 
https://github.com/rbgirshick/fast-rcnn

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks 
https://github.com/ShaoqingRen/faster_rcnn MATLAB 
https://github.com/rbgirshick/py-faster-rcnn Python

YOLO : Real-Time Object Detection 
http://pjreddie.com/darknet/yolo/ 
https://github.com/pjreddie/darknet

SSD: Single Shot MultiBox Detector 比Faster R-CNN又快又好啊! 
https://github.com/weiliu89/caffe/tree/ssd

A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection 
https://github.com/zhaoweicai/mscnn

Image Question Answering 
Stacked Attention Networks for Image Question Answering CVPR2016 
https://github.com/zcyang/imageqa-san

Image Question Answering using Convolutional Neural Networ with Dynamic Parameter Prediction CVPR2016

專案網頁 
http://cvlab.postech.ac.kr/research/dppnet/ 
開原始碼 
https://github.com/HyeonwooNoh/DPPnet

**場景識別: 
** 
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust 
Semantic Pixel-Wise Labelling 
https://github.com/alexgkendall/caffe-segnet

Tracking: 
Learning to Track: Online Multi-Object Tracking by Decision Making ICCV2015 
使用 Markov Decision Processes 做跟蹤,速度可能比較慢,效果應該還可以 
https://github.com/yuxng/MDP_Tracking

Fully-Convolutional Siamese Networks for Object Tracking 
http://www.robots.ox.ac.uk/~luca/siamese-fc.html

Car detection: 
Integrating Context and Occlusion for Car Detection by Hierarchical And-or Model ECCV2014 
http://www.stat.ucla.edu/~boli/projects/context_occlusion/context_occlusion.html

Face detection

人臉檢測2015進展:http://www.cvrobot.net/latest-progress-in-face-detection-2015/

Face detection without bells and whistles 
project:http://markusmathias.bitbucket.org/2014_eccv_face_detection/ 
Code:https://bitbucket.org/rodrigob/doppia 
Talk: http://videolectures.net/eccv2014_mathias_face_detection/ (不錯的報告)

From Facial Parts Responses to Face Detection: A Deep Learning Approach ICCV2015 email to get code and model 
http://personal.ie.cuhk.edu.hk/~ys014/projects/Faceness/Faceness.html

A Fast and Accurate Unconstrained Face Detector 2015 PAMI 
簡單 快速 有效 
http://www.cbsr.ia.ac.cn/users/scliao/projects/npdface/

Face Alignment 
Face Alignment by Coarse-to-Fine Shape Searching 
http://mmlab.ie.cuhk.edu.hk/projects/CFSS.html

High-Fidelity Pose and Expression Normalization for Face Recognition 
in the Wild 
http://www.cbsr.ia.ac.cn/users/xiangyuzhu/projects/HPEN/main.htm

Face Recognition 
Deep face recognition 
http://www.robots.ox.ac.uk/~vgg/software/vgg_face/

Do We Really Need to Collect Millions of Faces for Effective Face Recognition? 
http://www.openu.ac.il/home/hassner/projects/augmented_faces/

Person Re-identification :

Person Re-identification Results 
http://www.ssig.dcc.ufmg.br/reid-results/#ref35VIPER

Learning a Discriminative Null Space for Person Re-identification 
code http://www.eecs.qmul.ac.uk/~lz/

Query-Adaptive Late Fusion for Image Search and Person Re-identification 
CVPR2015 
http://www.liangzheng.com.cn/Project/project_fusion.html

Efficient Person Re-identification by Hybrid Spatiogram and Covariance Descriptor CVPR2015 Workshops 
https://github.com/Myles-ZMY/HSCD

Person Re-Identification by Iterative Re-Weighted Sparse Ranking PAMI 2015 
http://www.micc.unifi.it/masi/code/isr-re-id/ 沒有特徵提取程式碼

Person re-identification by Local Maximal Occurrence representation and metric learning CVPR2015 
http://www.cbsr.ia.ac.cn/users/scliao/projects/lomo_xqda/

Head detection 
Context-aware CNNs for person head detection 
Matlab code & dataset avaiable 
http://www.di.ens.fr/willow/research/headdetection/

Pedestrian detection

Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning PAMI 2015 
Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features ECCV2014 
https://github.com/chhshen/pedestrian-detection

Is Faster R-CNN Doing Well for Pedestrian Detection 
Matlab 程式碼 :https://github.com/zhangliliang/RPN_BF/tree/RPN-pedestrian

Deep Learning 
Deeply Learned Attributes for Crowded Scene Understanding 
https://github.com/amandajshao/www_deep_crowd 
http://www.ee.cuhk.edu.hk/~jshao/WWWCrowdDataset.html

Quantized Convolutional Neural Networks for Mobile Devices 
https://github.com/jiaxiang-wu/quantized-cnn

Human Pose Estimation 
DeepPose: Human Pose Estimation via Deep Neural Networks, CVPR2014 
https://github.com/mitmul/deeppose not official implementation

Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations NIPS 2014 
http://www.stat.ucla.edu/~xianjie.chen/projects/pose_estimation/pose_estimation.html

Learning Human Pose Estimation Features with Convolutional Networks 
https://github.com/stencilman/deep_nets_iclr04

Flowing ConvNets for Human Pose Estimation in Videos 
http://www.robots.ox.ac.uk/~vgg/software/cnn_heatmap/

雜項 
Unsupervised Learning of Visual Representations using Videos 很有前途啊! 
https://github.com/xiaolonw/caffe-video_triplet

Learning Deep Representations of Fine-Grained Visual Descriptions 
https://github.com/reedscot/cvpr2016

Fast Detection of Curved Edges at Low SNR 
http://www.wisdom.weizmann.ac.il/~yehonato/projectPage.html

Unsupervised Processing of Vehicle Appearance for Automatic Understanding in Traffic Surveillance

code: https://medusa.fit.vutbr.cz/traffic/research-topics/fine-grained-vehicle-recognition/unsupervised-processing-of-vehicle-appearance-for-automatic-understanding-in-traffic-surveillance/

Image Retrieval 
Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks 
https://github.com/kevinlin311tw/cvpr16-deepbit

Deep Supervised Hashing for Fast Image Retrieval 
https://github.com/lhmRyan/deep-supervised-hashing-DSH

Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification 
https://github.com/ruixuejianfei/BitScalableDeepHash

資料庫 
MPII Human Pose Dataset 
http://human-pose.mpi-inf.mpg.de/#overview

WIDER FACE: A Face Detection Benchmark 資料庫
http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/

DPM 
將voc-release4.0.1 Linux 轉到windows 
http://blog.csdn.net/masibuaa/article/details/17577195

開源車牌識別程式碼 
支援美國和歐洲車牌 
http://www.openalpr.com

文字識別 
https://github.com/MichalBusta/FASText 
FASText: Efficient Unconstrained Scene Text Detector