Object Detection With Deep Learning: A Review

IEEE Transactions on Neural Networks and Learning Systems - Tập 30 Số 11 - Trang 3212-3232 - 2019
Zhong‐Qiu Zhao, Peng Zheng, Shou-Tao Xu, Xindong Wu

Tóm tắt

Từ khóa


Tài liệu tham khảo

yang, 2017, Face detection through scale-friendly deep convolutional networks, Proc CVPR, 1

wang, 2017, Face R-CNN

10.1109/CVPR.2017.207

huang, 2015, Densebox Unifying landmark localization with end to end object detection

sun, 2017, Face detection using deep learning An improved faster RCNN approach

10.1109/LSP.2016.2603342

10.1007/978-3-319-46487-9_26

10.1109/CVPR.2016.376

kalinovsky, 2016, Compact convolutional neural network cascade for face detection, Proc CEUR Workshop, 375

10.1145/2671188.2749408

10.1109/ICCV.2015.419

10.1109/CVPR.2009.5206848

10.1109/MSP.2012.2205597

mateus, 2016, Efficient and robust pedestrian detection using deep learning for human-aware navigation

chen, 2016, Supervised transformer network for efficient face detection, Proc ECCV, 122

10.1007/978-3-319-10599-4_8

10.1109/FG.2017.82

rumelhart, 1986, Learning representations by back-propagating errors, Nature, 323, 533, 10.1038/323533a0

10.1007/BF02478291

10.1134/S1054661816010065

10.1109/CVPR.2016.234

yang, 2014, Aggregate channel features for multi-view face detection, Proc IJCB, 1

10.1109/CVPR.2015.7299170

10.1109/TPAMI.2015.2448075

10.1109/CVPR.2013.445

10.1007/978-3-319-10593-2_47

markuš, 2013, Object detection with pixel intensity comparisons organized in decision trees

10.1109/TIP.2017.2779856

10.1109/CVPR.2017.166

ranjan, 2016, Hyperface A deep multi-task learning framework for face detection landmark localization pose estimation and gender recognition

10.1109/ICCV.2015.18

liu, 2015, Predicting eye fixations using convolutional neural networks, Proc CVPR, 362

lecun, 2015, Deep learning, Nature, 521, 436, 10.1038/nature14539

jain, 2010, FDDB: A benchmark for face detection in unconstrained settings

10.1109/CVPR.2014.358

10.1109/CVPR.2005.177

10.1007/BF00994018

10.1109/ICIP.2002.1038171

10.1109/TPAMI.2009.167

10.1006/jcss.1997.1504

hinton, 2006, Reducing the dimensionality of data with neural networks, Science, 313, 504, 10.1126/science.1127647

10.1007/s11263-009-0275-4

10.1109/CVPR.2014.222

wadley, 1947, Probit analysis: A statistical treatment of the sigmoid response curve, Ann Entomol Soc Amer, 67, 549

10.1109/CVPR.2017.698

10.1109/CVPR.2016.78

10.1109/CVPR.2013.153

hou, 2016, Deeply supervised salient object detection with short connections[J]

10.1109/ICCV.2013.413

10.1109/CVPR.2013.271

10.1109/TPAMI.2014.2345401

10.1109/TIP.2016.2602079

10.1109/CVPR.2016.71

10.1109/CVPR.2016.399

10.1145/2964284.2967250

10.1016/j.image.2016.05.007

10.1145/2647868.2654948

10.1007/978-3-319-10590-1_38

zhao, 2014, Plant leaf identification via a growing convolution neural network with progressive sample learning, Proc ACCV, 348

10.1109/ICCV.2015.178

10.1109/CVPR.2010.5539957

kavukcuoglu, 2010, Learning convolutional feature hierarchies for visual recognition, Proc NIPS, 1090

10.1109/CVPR.2009.5206545

deng, 2010, Binary coding of speech spectrograms using a deep auto-encoder, Proc INTERSPEECH, 1692, 10.21437/Interspeech.2010-487

10.1145/2964284.2967274

10.1023/B:VISI.0000013087.49260.fb

10.1109/TCYB.2016.2625419

10.1109/TNNLS.2015.2464681

10.1007/s11263-013-0645-9

10.1109/TCSVT.2012.2198090

10.1007/978-3-319-46604-0_1

10.1109/TPAMI.2016.2542816

10.1109/42.500062

wojek, 2012, Pedestrian detection: An evaluation of the state of the art, IEEE Trans Pattern Anal Mach Intell, 34, 743, 10.1109/TPAMI.2011.155

krizhevsky, 2012, ImageNet classification with deep convolutional neural networks, Proc NIPS, 1097

10.1145/2647868.2654889

yang, 2016, A multi-scale cascade fully convolutional network face detector, Proc ICPR, 633

10.1109/TIP.2015.2487833

10.1109/CVPR.2017.143

oquab, 2014, Weakly supervised object recognition with convolutional neural networks, Proc NIPS, 1

10.1109/CVPR.2014.43

10.1109/ICCV.2015.312

10.1109/CVPRW.2010.5543739

simonyan, 2014, Very Deep Convolutional Networks for Large-scale Image Recognition

10.1109/CVPR.2015.7298594

nair, 2010, Rectified linear units improve restricted Boltzmann machines, Proc ICML, 807

10.1109/CVPR.2016.90

hinton, 2012, Improving Neural Networks by Preventing Co-adaptation of Feature Detectors

dahl, 2010, Phone recognition with the mean-covariance restricted Boltzmann machine, Proc NIPS, 469

sermanet, 2013, Overfeat Integrated Recognition Localization and Detection Using Convolutional Networks

ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, Proc ICML, 448

fu, 2017, Dssd Deconvolutional single shot detector

redmon, 2016, YOLO9000 Better Faster Stronger

liu, 2016, SSD: Single shot multibox detector, Proc ECCV, 21

10.1109/CVPR.2016.260

10.1109/CVPR.2011.5995538

10.1109/CVPR.2013.417

10.1109/ICCV.2017.212

hinton, 2011, Transforming auto-encoders, Proc ICANN, 44

10.1007/s11263-013-0620-5

10.1109/CVPR.2013.465

10.1109/WACV.2017.108

ngiam, 2011, Multimodal deep learning, Proc ICML, 689

10.1007/978-3-319-63309-1_65

10.1145/2733373.2806222

10.1109/TPAMI.2015.2389824

dai, 2016, R-FCN: Object detection via region-based fully convolutional networks, Proc NIPS, 379

10.1109/CVPR.2017.106

10.1109/ICCV.2017.322

10.1109/CVPR.2014.276

10.1109/ICCV.2015.305

10.1109/TPAMI.2014.2300479

10.1109/CVPR.2015.7298784

10.1109/TPAMI.2015.2474388

10.1109/TCYB.2016.2628161

10.1177/0278364913491297

10.1109/ICCV.2015.384

10.1109/ICCV.2015.221

10.1109/CVPR.2016.314

lin, 2014, Microsoft COCO: Common objects in context, Proc ECCV, 740

10.1007/s11263-006-9038-7

10.1109/CVPR.2016.308

10.1109/ICCV.2017.507

10.1109/TPAMI.2016.2577031

10.1109/ICCV.2017.266

xue, 2013, Restructuring of deep neural network acoustic models with singular value decomposition, Proc INTERSPEECH, 2365, 10.21437/Interspeech.2013-552

perronnin, 2010, Improving the Fisher kernel for large-scale image classification, Proc ECCV, 143

10.1109/CVPR.2017.472

jaderberg, 2015, Spatial transformer networks, Proc Adv Neural Inf Process Syst, 2017

10.1109/CVPR.2017.100

10.1109/CVPR.2016.343

10.1007/978-3-319-10602-1_26

10.1109/CVPR.2014.49

10.1007/978-3-319-46448-0_5

10.1109/ICCV.2015.285

10.1007/978-3-319-10602-1_47

10.1109/CVPR.2006.68

10.1109/CVPR.2015.7298621

10.1007/978-3-319-10584-0_23

10.1109/CVPR.2015.7298854

10.5244/C.29.5

10.1109/TPAMI.2014.2359888

10.1109/CVPR.2016.98

10.1109/WACV.2017.109

10.1109/ICCE-Berlin.2016.7684706

10.1007/978-3-319-46475-6_28

10.1109/ICCV.2015.221

10.1109/ICCV.2013.190

10.1007/s11263-013-0664-6

10.1109/WACV.2017.111

10.1109/TCSVT.2017.2648850

10.5244/C.30.73

10.1109/CVPR.2015.7299143

li, 2015, Scale-aware fast R-CNN for pedestrian detection

10.1109/CVPR.2015.7299034

10.1109/TIP.2012.2202676

10.1109/CVPR.2017.557

goodfellow, 2014, Generative adversarial nets, Proc NIPS, 2672

10.24963/ijcai.2017/230

welleck, 2017, Saliency-based sequential image attention with multiset prediction, Proc NIPS, 5173

10.1109/CVPR.2017.779

sukhbaatar, 2015, End-to-end memory networks, Proc NIPS, 2440

dabkowski, 2017, Real time image saliency for black box classifiers, Proc NIPS, 6967

10.1109/CVPR.2016.650

10.1007/978-3-319-10599-4_28

10.1109/ICCV.2017.465

10.1109/CVPR.2017.380

chen, 2015, 3D object proposals for accurate object class detection, Proc NIPS, 424

romero, 2015, FitNets: Hints for thin deep nets, Proc ICLR, 1

hinton, 2015, Distilling the knowledge in a neural network, Comput Sci, 14, 38

10.1109/CVPR.2017.776

10.1109/CVPR.2017.351

10.1109/CVPR.2017.27

10.1109/CVPR.2016.256

10.1109/TIP.2011.2164420

10.1145/1141911.1141965

10.1109/ICCV.2017.89

10.1016/j.patcog.2009.04.021

10.1109/TPAMI.2016.2547384

liu, 2011, Learning to detect a salient object, IEEE Trans Pattern Anal Mach Intell, 33, 353, 10.1109/TPAMI.2010.70

10.1109/ICCV.2015.164

kümmerer, 2014, Deep gaze I Boosting saliency prediction with feature maps trained on ImageNet

10.1109/CVPR.2015.7298965

gao, 2009, Discriminant saliency, the detection of suspicious coincidences, and applications to visual recognition, IEEE Trans Pattern Anal Mach Intell, 31, 989, 10.1109/TPAMI.2009.27

10.1109/CVPR.2017.101

10.1109/CVPR.2015.7298938

10.1109/ICCV.2015.38

10.1109/CVPR.2015.7298731

cholakkal, 2016, Backtracking spatial pyramid pooling (SPP)-based image classifier for weakly supervised top-down salient object detection

bak, 2016, Spatio-temporal saliency networks for dynamic saliency prediction

10.1007/s11263-015-0822-0

10.1109/TIP.2016.2579306

10.1007/978-3-319-46484-8_49

10.1109/CVPR.2016.58

10.1109/34.655648

wang, 2016, Edge preserving and multi-scale contextual neural network for salient object detection

10.1109/TPAMI.2009.167

10.1109/ICPR.2016.7900174

10.1007/978-3-319-46478-7_22

moysset, 2016, Learning to detect and localize many objects from few examples

10.1109/CVPR.2015.7298977

zhu, 2015, segDeepM: Exploiting segmentation and context in deep neural networks for object detection, Proc CVPR, 4703

10.1007/978-3-319-46493-0_22

li, 2016, Multi-stage object detection with group recursive learning

yim, 2015, Rotating your face using multi-task deep neural network, Proc CVPR, 676

10.1109/CVPR.2015.7299188

10.1109/78.650093

10.5244/C.30.15

10.1109/ICCV.2015.135

10.1109/CVPR.2017.691

10.1109/TNNLS.2016.2545298

10.1109/TNNLS.2018.2815435

khan, 2018, Cost-sensitive learning of deep feature representations from imbalanced data, IEEE Trans Neural Netw Learn Syst, 29, 3573, 10.1109/TNNLS.2017.2732482

10.1109/TNNLS.2012.2183645

10.1109/CVPR.2014.81

10.1109/ICCV.2015.169

szegedy, 2013, Deep neural networks for object detection, Proc NIPS, 1

ren, 2015, Faster R-CNN: Towards real-time object detection with region proposal networks, Proc NIPS, 91

shang, 2016, Understanding and improving convolutional neural networks via concatenated rectified linear units, Proc ICML, 1

10.1109/CVPR.2016.91

10.1023/B:VISI.0000029664.99615.94

pinheiro, 2015, Learning to segment object candidates, Proc NIPS, 1990

10.1109/TPAMI.2016.2601099

10.1109/CVPR.2016.89

hong, 2016, Pvanet Lightweight deep neural networks for real-time object detection

10.1109/CVPR.2016.100

szegedy, 2014, Scalable high-quality object detection

everingham, 2011, The pascal visual object classes challenge 2012 (voc2012) results (2012)

zeiler, 2014, Visualizing and understanding convolutional networks, Proc ECCV, 818

10.1109/CVPR.2017.634