各类识别、深度学习-开源代码文献梳理

可以看看这个 http://blog.csdn.net/workerwu/article/details/46537849

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 代码
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-rcnnPython

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

项目网页
http://cvlab.postech.ac.kr/research/dppnet/
开源代码
https://github.com/HyeonwooNoh/DPPnet

**场景识别:
**
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 做跟踪,速度可能比较慢,效果应该还可以
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

人脸检测2015进展: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/ (不错的报告)

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
简单 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/ 没有特征提取代码

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 代码 :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/

杂项
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

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

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

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

开源车牌识别代码
支持美国和欧洲车牌
http://www.openalpr.com

文字识别
https://github.com/MichalBusta/FASText
FASText: Efficient Unconstrained Scene Text Detector

  • 0
    点赞
  • 8
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
深度学习-语音识别是一种利用神经网络模型进行语音识别的技术。Python语言在深度学习领域有广泛应用,并提供了多个相关框架,如TensorFlow和PyTorch,便于实现语音识别任务。 在进行深度学习-语音识别实战时,首先需要准备语音数据集。可以使用已有的公数据集,也可以自己收集。常用的数据集包括LibriSpeech、TIMIT和Aurora4等。 接下来,需要将语音数据集进行预处理。预处理步骤包括数据清洗、标签处理和特征提取。数据清洗可以剔除噪音和异常数据,标签处理主要是将语音数据与对应的文字标签进行对齐,特征提取则是将语音信号转换为机器学习算法可以处理的数值特征,常用的特征提取方法有Mel频谱特征和MFCC等。 然后,需要选择合适的神经网络模型进行语音识别。常用的模型包括基于卷积神经网络(CNN)和循环神经网络(RNN)的混合模型。模型的选择要根据数据集的规模和任务需求进行。 在实际实现中,可以利用Python的深度学习框架(如TensorFlow和PyTorch)来构建和训练神经网络模型。框架提供了高级的API和函数,可以方便地定义模型结构、进行参数优化和模型评估。 训练完成后,可以使用训练好的模型进行语音识别。使用Python进行语音识别时,可以使用语音信号进行预测,并得到相应的文本结果。 总之,深度学习-语音识别实战是一个复杂的任务,但借助Python的强大生态系统和深度学习框架,可以更高效地进行模型训练和识别任务的实现。

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值