Object Detection on Mobile Devices
Pelee: A Real-Time Object Detection System on Mobile Devices
- intro: ICLR 2018 workshop track
- intro: based on the SSD
- arxiv: https://arxiv.org/abs/1804.06882
- github: https://github.com/Robert-JunWang/Pelee
Object Detection in 3D
Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks
Complex-YOLO: Real-time 3D Object Detection on Point Clouds
- intro: Valeo Schalter und Sensoren GmbH & Ilmenau University of Technology
- arxiv: https://arxiv.org/abs/1803.06199
Focal Loss in 3D Object Detection
3D Object Detection Using Scale Invariant and Feature Reweighting Networks
- intro: AAAI 2019
- arxiv: https://arxiv.org/abs/1901.02237
3D Backbone Network for 3D Object Detection
Object Detection on RGB-D
Learning Rich Features from RGB-D Images for Object Detection and Segmentation
Differential Geometry Boosts Convolutional Neural Networks for Object Detection
- intro: CVPR 2016
- paper: http://www.cv-foundation.org/openaccess/content_cvpr_2016_workshops/w23/html/Wang_Differential_Geometry_Boosts_CVPR_2016_paper.html
A Self-supervised Learning System for Object Detection using Physics Simulation and Multi-view Pose Estimation
Zero-Shot Object Detection
Zero-Shot Detection
- intro: Australian National University
- keywords: YOLO
- arxiv: https://arxiv.org/abs/1803.07113
Zero-Shot Object Detection
Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts
- intro: Australian National University
- arxiv: https://arxiv.org/abs/1803.06049
Zero-Shot Object Detection by Hybrid Region Embedding
- intro: Middle East Technical University & Hacettepe University
- arxiv: https://arxiv.org/abs/1805.06157
Salient Object Detection
This task involves predicting the salient regions of an image given by human eye fixations.
Best Deep Saliency Detection Models (CVPR 2016 & 2015)
Large-scale optimization of hierarchical features for saliency prediction in natural images
Predicting Eye Fixations using Convolutional Neural Networks
Saliency Detection by Multi-Context Deep Learning
DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection
Shallow and Deep Convolutional Networks for Saliency Prediction
- intro: CVPR 2016
- arxiv: http://arxiv.org/abs/1603.00845
- github: https://github.com/imatge-upc/saliency-2016-cvpr
Recurrent Attentional Networks for Saliency Detection
- intro: CVPR 2016. recurrent attentional convolutional-deconvolution network (RACDNN)
- arxiv: http://arxiv.org/abs/1604.03227
Two-Stream Convolutional Networks for Dynamic Saliency Prediction
Unconstrained Salient Object Detection
Unconstrained Salient Object Detection via Proposal Subset Optimization
- intro: CVPR 2016
- project page: http://cs-people.bu.edu/jmzhang/sod.html
- paper: http://cs-people.bu.edu/jmzhang/SOD/CVPR16SOD_camera_ready.pdf
- github: https://github.com/jimmie33/SOD
- caffe model zoo: https://github.com/BVLC/caffe/wiki/Model-Zoo#cnn-object-proposal-models-for-salient-object-detection
DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection
Salient Object Subitizing
- intro: CVPR 2015
- intro: predicting the existence and the number of salient objects in an image using holistic cues
- project page: http://cs-people.bu.edu/jmzhang/sos.html
- arxiv: http://arxiv.org/abs/1607.07525
- paper: http://cs-people.bu.edu/jmzhang/SOS/SOS_preprint.pdf
- caffe model zoo: https://github.com/BVLC/caffe/wiki/Model-Zoo#cnn-models-for-salient-object-subitizing
Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection
- intro: ACMMM 2016. deeply-supervised recurrent convolutional neural network (DSRCNN)
- arxiv: http://arxiv.org/abs/1608.05177
Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs
- intro: ECCV 2016
- arxiv: http://arxiv.org/abs/1608.05186
Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection
A Deep Multi-Level Network for Saliency Prediction
Visual Saliency Detection Based on Multiscale Deep CNN Features
- intro: IEEE Transactions on Image Processing
- arxiv: http://arxiv.org/abs/1609.02077
A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection
- intro: DSCLRCN
- arxiv: https://arxiv.org/abs/1610.01708
Deeply supervised salient object detection with short connections
- intro: IEEE TPAMI 2018 (IEEE CVPR 2017)
- arxiv: https://arxiv.org/abs/1611.04849
- github(official, Caffe): https://github.com/Andrew-Qibin/DSS
- github(Tensorflow): https://github.com/Joker316701882/Salient-Object-Detection
Weakly Supervised Top-down Salient Object Detection
- intro: Nanyang Technological University
- arxiv: https://arxiv.org/abs/1611.05345
SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
- project page: https://imatge-upc.github.io/saliency-salgan-2017/
- arxiv: https://arxiv.org/abs/1701.01081
Visual Saliency Prediction Using a Mixture of Deep Neural Networks
A Fast and Compact Salient Score Regression Network Based on Fully Convolutional Network
Saliency Detection by Forward and Backward Cues in Deep-CNNs
Supervised Adversarial Networks for Image Saliency Detection
Group-wise Deep Co-saliency Detection
Towards the Success Rate of One: Real-time Unconstrained Salient Object Detection
- intro: University of Maryland College Park & eBay Inc
- arxiv: https://arxiv.org/abs/1708.00079
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
- intro: ICCV 2017
- arixv: https://arxiv.org/abs/1708.02001
Learning Uncertain Convolutional Features for Accurate Saliency Detection
- intro: Accepted as a poster in ICCV 2017
- arxiv: https://arxiv.org/abs/1708.02031
Deep Edge-Aware Saliency Detection
Self-explanatory Deep Salient Object Detection
- intro: National University of Defense Technology, China & National University of Singapore
- arxiv: https://arxiv.org/abs/1708.05595
PiCANet: Learning Pixel-wise Contextual Attention in ConvNets and Its Application in Saliency Detection
DeepFeat: A Bottom Up and Top Down Saliency Model Based on Deep Features of Convolutional Neural Nets
Recurrently Aggregating Deep Features for Salient Object Detection
- intro: AAAI 2018
- paper: https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16775/16281
Deep saliency: What is learnt by a deep network about saliency?
- intro: 2nd Workshop on Visualisation for Deep Learning in the 34th International Conference On Machine Learning
- arxiv: https://arxiv.org/abs/1801.04261
Contrast-Oriented Deep Neural Networks for Salient Object Detection
- intro: TNNLS
- arxiv: https://arxiv.org/abs/1803.11395
Salient Object Detection by Lossless Feature Reflection
- intro: IJCAI 2018
- arxiv: https://arxiv.org/abs/1802.06527
HyperFusion-Net: Densely Reflective Fusion for Salient Object Detection
Video Saliency Detection
Deep Learning For Video Saliency Detection
Video Salient Object Detection Using Spatiotemporal Deep Features
Predicting Video Saliency with Object-to-Motion CNN and Two-layer Convolutional LSTM
Visual Relationship Detection
Visual Relationship Detection with Language Priors
- intro: ECCV 2016 oral
- paper: https://cs.stanford.edu/people/ranjaykrishna/vrd/vrd.pdf
- github: https://github.com/Prof-Lu-Cewu/Visual-Relationship-Detection
ViP-CNN: A Visual Phrase Reasoning Convolutional Neural Network for Visual Relationship Detection
- intro: Visual Phrase reasoning Convolutional Neural Network (ViP-CNN), Visual Phrase Reasoning Structure (VPRS)
- arxiv: https://arxiv.org/abs/1702.07191
Visual Translation Embedding Network for Visual Relation Detection
Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection
- intro: CVPR 2017 spotlight paper
- arxiv: https://arxiv.org/abs/1703.03054
Detecting Visual Relationships with Deep Relational Networks
- intro: CVPR 2017 oral. The Chinese University of Hong Kong
- arxiv: https://arxiv.org/abs/1704.03114
Identifying Spatial Relations in Images using Convolutional Neural Networks
PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN
- intro: ICCV
- arxiv: https://arxiv.org/abs/1708.01956
Natural Language Guided Visual Relationship Detection
Detecting Visual Relationships Using Box Attention
- intro: Google AI & IST Austria
- arxiv: https://arxiv.org/abs/1807.02136
Google AI Open Images - Visual Relationship Track
- intro: Detect pairs of objects in particular relationships
- kaggle: https://www.kaggle.com/c/google-ai-open-images-visual-relationship-track
Context-Dependent Diffusion Network for Visual Relationship Detection
- intro: 2018 ACM Multimedia Conference
- arxiv: https://arxiv.org/abs/1809.06213
A Problem Reduction Approach for Visual Relationships Detection
- intro: ECCV 2018 Workshop
- arxiv: https://arxiv.org/abs/1809.09828
Face Deteciton
Multi-view Face Detection Using Deep Convolutional Neural Networks
- intro: Yahoo
- arxiv: http://arxiv.org/abs/1502.02766
- github: https://github.com/guoyilin/FaceDetection_CNN
From Facial Parts Responses to Face Detection: A Deep Learning Approach
- intro: ICCV 2015. CUHK
- project page: http://personal.ie.cuhk.edu.hk/~ys014/projects/Faceness/Faceness.html
- arxiv: https://arxiv.org/abs/1509.06451
- paper: http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Yang_From_Facial_Parts_ICCV_2015_paper.pdf
Compact Convolutional Neural Network Cascade for Face Detection
- arxiv: http://arxiv.org/abs/1508.01292
- github: https://github.com/Bkmz21/FD-Evaluation
- github: https://github.com/Bkmz21/CompactCNNCascade
Face Detection with End-to-End Integration of a ConvNet and a 3D Model
- intro: ECCV 2016
- arxiv: https://arxiv.org/abs/1606.00850
- github(MXNet): https://github.com/tfwu/FaceDetection-ConvNet-3D
CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection
- intro: CMU
- arxiv: https://arxiv.org/abs/1606.05413
Towards a Deep Learning Framework for Unconstrained Face Detection
- intro: overlap with CMS-RCNN
- arxiv: https://arxiv.org/abs/1612.05322
Supervised Transformer Network for Efficient Face Detection
UnitBox: An Advanced Object Detection Network
- intro: ACM MM 2016
- keywords: IOULoss
- arxiv: http://arxiv.org/abs/1608.01471
Bootstrapping Face Detection with Hard Negative Examples
- author: 万韶华 @ 小米.
- intro: Faster R-CNN, hard negative mining. state-of-the-art on the FDDB dataset
- arxiv: http://arxiv.org/abs/1608.02236
Grid Loss: Detecting Occluded Faces
- intro: ECCV 2016
- arxiv: https://arxiv.org/abs/1609.00129
- paper: http://lrs.icg.tugraz.at/pubs/opitz_eccv_16.pdf
- poster: http://www.eccv2016.org/files/posters/P-2A-34.pdf
A Multi-Scale Cascade Fully Convolutional Network Face Detector
- intro: ICPR 2016
- arxiv: http://arxiv.org/abs/1609.03536
MTCNN
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks
- project page: https://kpzhang93.github.io/MTCNN_face_detection_alignment/index.html
- arxiv: https://arxiv.org/abs/1604.02878
- github(official, Matlab): https://github.com/kpzhang93/MTCNN_face_detection_alignment
- github: https://github.com/pangyupo/mxnet_mtcnn_face_detection
- github: https://github.com/DaFuCoding/MTCNN_Caffe
- github(MXNet): https://github.com/Seanlinx/mtcnn
- github: https://github.com/Pi-DeepLearning/RaspberryPi-FaceDetection-MTCNN-Caffe-With-Motion
- github(Caffe): https://github.com/foreverYoungGitHub/MTCNN
- github: https://github.com/CongWeilin/mtcnn-caffe
- github(OpenCV+OpenBlas): https://github.com/AlphaQi/MTCNN-light
- github(Tensorflow+golang): https://github.com/jdeng/goface
Face Detection using Deep Learning: An Improved Faster RCNN Approach
- intro: DeepIR Inc
- arxiv: https://arxiv.org/abs/1701.08289
Faceness-Net: Face Detection through Deep Facial Part Responses
- intro: An extended version of ICCV 2015 paper
- arxiv: https://arxiv.org/abs/1701.08393
Multi-Path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained “Hard Faces”
- intro: CVPR 2017. MP-RCNN, MP-RPN
- arxiv: https://arxiv.org/abs/1703.09145
End-To-End Face Detection and Recognition
Face R-CNN
Face Detection through Scale-Friendly Deep Convolutional Networks
Scale-Aware Face Detection
- intro: CVPR 2017. SenseTime & Tsinghua University
- arxiv: https://arxiv.org/abs/1706.09876
Detecting Faces Using Inside Cascaded Contextual CNN
- intro: CVPR 2017. Tencent AI Lab & SenseTime
- paper: http://ai.tencent.com/ailab/media/publications/Detecting_Faces_Using_Inside_Cascaded_Contextual_CNN.pdf
Multi-Branch Fully Convolutional Network for Face Detection
SSH: Single Stage Headless Face Detector
- intro: ICCV 2017. University of Maryland
- arxiv: https://arxiv.org/abs/1708.03979
- github(official, Caffe): https://github.com/mahyarnajibi/SSH
Dockerface: an easy to install and use Faster R-CNN face detector in a Docker container
FaceBoxes: A CPU Real-time Face Detector with High Accuracy
- intro: IJCB 2017
- keywords: Rapidly Digested Convolutional Layers (RDCL), Multiple Scale Convolutional Layers (MSCL)
- intro: the proposed detector runs at 20 FPS on a single CPU core and 125 FPS using a GPU for VGA-resolution images
- arxiv: https://arxiv.org/abs/1708.05234
- github(official): https://github.com/sfzhang15/FaceBoxes
- github(Caffe): https://github.com/zeusees/FaceBoxes
S3FD: Single Shot Scale-invariant Face Detector
- intro: ICCV 2017. Chinese Academy of Sciences
- intro: can run at 36 FPS on a Nvidia Titan X (Pascal) for VGA-resolution images
- arxiv: https://arxiv.org/abs/1708.05237
- github(Caffe, official): https://github.com/sfzhang15/SFD
- github: https://github.com//clcarwin/SFD_pytorch
Detecting Faces Using Region-based Fully Convolutional Networks
AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection
Face Attention Network: An effective Face Detector for the Occluded Faces
Feature Agglomeration Networks for Single Stage Face Detection
Face Detection Using Improved Faster RCNN
- intro: Huawei Cloud BU
- arxiv: https://arxiv.org/abs/1802.02142
PyramidBox: A Context-assisted Single Shot Face Detector
- intro: Baidu, Inc
- arxiv: https://arxiv.org/abs/1803.07737
A Fast Face Detection Method via Convolutional Neural Network
- intro: Neurocomputing
- arxiv: https://arxiv.org/abs/1803.10103
Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy
- intro: CVPR 2018. Beihang University & CUHK & Sensetime
- arxiv: https://arxiv.org/abs/1804.05197
Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks
- intro: CVPR 2018
- arxiv: https://arxiv.org/abs/1804.06039
- github: https://github.com/Jack-CV/PCN
SFace: An Efficient Network for Face Detection in Large Scale Variations
- intro: Beihang University & Megvii Inc. (Face++)
- arxiv: https://arxiv.org/abs/1804.06559
Survey of Face Detection on Low-quality Images
Anchor Cascade for Efficient Face Detection
- intro: The University of Sydney
- arxiv: https://arxiv.org/abs/1805.03363
Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization
- intro: IEEE MMSP
- arxiv: https://arxiv.org/abs/1805.12302
Selective Refinement Network for High Performance Face Detection
DSFD: Dual Shot Face Detector
Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
FA-RPN: Floating Region Proposals for Face Detection
Robust and High Performance Face Detector
https://arxiv.org/abs/1901.02350
DAFE-FD: Density Aware Feature Enrichment for Face Detection
Improved Selective Refinement Network for Face Detection
- intro: Chinese Academy of Sciences & JD AI Research
- arxiv: https://arxiv.org/abs/1901.06651
Revisiting a single-stage method for face detection
Detect Small Faces
Finding Tiny Faces
- intro: CVPR 2017. CMU
- project page: http://www.cs.cmu.edu/~peiyunh/tiny/index.html
- arxiv: https://arxiv.org/abs/1612.04402
- github(official, Matlab): https://github.com/peiyunh/tiny
- github(inference-only): https://github.com/chinakook/hr101_mxnet
- github: https://github.com/cydonia999/Tiny_Faces_in_Tensorflow
Detecting and counting tiny faces
- intro: ENS Paris-Saclay. ExtendedTinyFaces
- intro: Detecting and counting small objects - Analysis, review and application to counting
- arxiv: https://arxiv.org/abs/1801.06504
- github: https://github.com/alexattia/ExtendedTinyFaces
Seeing Small Faces from Robust Anchor’s Perspective
- intro: CVPR 2018
- arxiv: https://arxiv.org/abs/1802.09058
Face-MagNet: Magnifying Feature Maps to Detect Small Faces
- intro: WACV 2018
- keywords: Face Magnifier Network (Face-MageNet)
- arxiv: https://arxiv.org/abs/1803.05258
- github: https://github.com/po0ya/face-magnet
Robust Face Detection via Learning Small Faces on Hard Images
- intro: Johns Hopkins University & Stanford University
- arxiv: https://arxiv.org/abs/1811.11662
- github: https://github.com/bairdzhang/smallhardface
SFA: Small Faces Attention Face Detector
- intro: Jilin University
- arxiv: https://arxiv.org/abs/1812.08402
Person Head Detection
Context-aware CNNs for person head detection
- intro: ICCV 2015
- project page: http://www.di.ens.fr/willow/research/headdetection/
- arxiv: http://arxiv.org/abs/1511.07917
- github: https://github.com/aosokin/cnn_head_detection
Detecting Heads using Feature Refine Net and Cascaded Multi-scale Architecture
A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications
FCHD: A fast and accurate head detector
- arxiv: https://arxiv.org/abs/1809.08766
- github(PyTorch, official): https://github.com/aditya-vora/FCHD-Fully-Convolutional-Head-Detector
Pedestrian Detection / People Detection
Pedestrian Detection aided by Deep Learning Semantic Tasks
- intro: CVPR 2015
- project page: http://mmlab.ie.cuhk.edu.hk/projects/TA-CNN/
- arxiv: http://arxiv.org/abs/1412.0069
Deep Learning Strong Parts for Pedestrian Detection
- intro: ICCV 2015. CUHK. DeepParts
- intro: Achieving 11.89% average miss rate on Caltech Pedestrian Dataset
- paper: http://personal.ie.cuhk.edu.hk/~pluo/pdf/tianLWTiccv15.pdf
Taking a Deeper Look at Pedestrians
- intro: CVPR 2015
- arxiv: https://arxiv.org/abs/1501.05790
Convolutional Channel Features
- intro: ICCV 2015
- arxiv: https://arxiv.org/abs/1504.07339
- github: https://github.com/byangderek/CCF
End-to-end people detection in crowded scenes
- arxiv: http://arxiv.org/abs/1506.04878
- github: https://github.com/Russell91/reinspect
- ipn: http://nbviewer.ipython.org/github/Russell91/ReInspect/blob/master/evaluation_reinspect.ipynb
- youtube: https://www.youtube.com/watch?v=QeWl0h3kQ24
Learning Complexity-Aware Cascades for Deep Pedestrian Detection
- intro: ICCV 2015
- arxiv: https://arxiv.org/abs/1507.05348
Deep convolutional neural networks for pedestrian detection
Scale-aware Fast R-CNN for Pedestrian Detection
New algorithm improves speed and accuracy of pedestrian detection
Pushing the Limits of Deep CNNs for Pedestrian Detection
- intro: “set a new record on the Caltech pedestrian dataset, lowering the log-average miss rate from 11.7% to 8.9%”
- arxiv: http://arxiv.org/abs/1603.04525
A Real-Time Deep Learning Pedestrian Detector for Robot Navigation
A Real-Time Pedestrian Detector using Deep Learning for Human-Aware Navigation
Is Faster R-CNN Doing Well for Pedestrian Detection?
- intro: ECCV 2016
- arxiv: http://arxiv.org/abs/1607.07032
- github: https://github.com/zhangliliang/RPN_BF/tree/RPN-pedestrian
Unsupervised Deep Domain Adaptation for Pedestrian Detection
- intro: ECCV Workshop 2016
- arxiv: https://arxiv.org/abs/1802.03269
Reduced Memory Region Based Deep Convolutional Neural Network Detection
- intro: IEEE 2016 ICCE-Berlin
- arxiv: http://arxiv.org/abs/1609.02500
Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection
Detecting People in Artwork with CNNs
- intro: ECCV 2016 Workshops
- arxiv: https://arxiv.org/abs/1610.08871
Multispectral Deep Neural Networks for Pedestrian Detection
- intro: BMVC 2016 oral
- arxiv: https://arxiv.org/abs/1611.02644
Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection
Deep Multi-camera People Detection
Expecting the Unexpected: Training Detectors for Unusual Pedestrians with Adversarial Imposters
- intro: CVPR 2017
- project page: http://ml.cs.tsinghua.edu.cn:5000/publications/synunity/
- arxiv: https://arxiv.org/abs/1703.06283
- github(Tensorflow): https://github.com/huangshiyu13/RPNplus
What Can Help Pedestrian Detection?
- intro: CVPR 2017. Tsinghua University & Peking University & Megvii Inc.
- keywords: Faster R-CNN, HyperLearner
- arxiv: https://arxiv.org/abs/1705.02757
- paper: http://openaccess.thecvf.com/content_cvpr_2017/papers/Mao_What_Can_Help_CVPR_2017_paper.pdf
Illuminating Pedestrians via Simultaneous Detection & Segmentation
Rotational Rectification Network for Robust Pedestrian Detection
- intro: CMU & Volvo Construction
- arxiv: https://arxiv.org/abs/1706.08917
STD-PD: Generating Synthetic Training Data for Pedestrian Detection in Unannotated Videos
- intro: The University of North Carolina at Chapel Hill
- arxiv: https://arxiv.org/abs/1707.09100
Too Far to See? Not Really! — Pedestrian Detection with Scale-aware Localization Policy
Repulsion Loss: Detecting Pedestrians in a Crowd
Aggregated Channels Network for Real-Time Pedestrian Detection
Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection
- intro: State Key Lab of CAD&CG, Zhejiang University
- arxiv: https://arxiv.org/abs/1803.05347
Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection
Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
PCN: Part and Context Information for Pedestrian Detection with CNNs
- intro: British Machine Vision Conference(BMVC) 2017
- arxiv: https://arxiv.org/abs/1804.04483
Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation
- intro: ECCV 2018. Hikvision Research Institute
- arxiv: https://arxiv.org/abs/1807.01438
Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
- intro: ECCV 2018
- arxiv: https://arxiv.org/abs/1807.08407
Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation
- intro: BMVC 2018
- arxiv: https://arxiv.org/abs/1808.04818
Pedestrian Detection with Autoregressive Network Phases
- intro: Michigan State University
- arxiv: https://arxiv.org/abs/1812.00440
The Cross-Modality Disparity Problem in Multispectral Pedestrian Detection
-arxiv: https://arxiv.org/abs/1901.02645
Vehicle Detection
DAVE: A Unified Framework for Fast Vehicle Detection and Annotation
- intro: ECCV 2016
- arxiv: http://arxiv.org/abs/1607.04564
Evolving Boxes for fast Vehicle Detection
Fine-Grained Car Detection for Visual Census Estimation
- intro: AAAI 2016
- arxiv: https://arxiv.org/abs/1709.02480
SINet: A Scale-insensitive Convolutional Neural Network for Fast Vehicle Detection
- intro: IEEE Transactions on Intelligent Transportation Systems (T-ITS)
- arxiv: https://arxiv.org/abs/1804.00433
Label and Sample: Efficient Training of Vehicle Object Detector from Sparsely Labeled Data
- intro: UC Berkeley
- arxiv: https://arxiv.org/abs/1808.08603
Domain Randomization for Scene-Specific Car Detection and Pose Estimation
ShuffleDet: Real-Time Vehicle Detection Network in On-board Embedded UAV Imagery
- intro: ECCV 2018, UAVision 2018
- arxiv: https://arxiv.org/abs/1811.06318
Traffic-Sign Detection
Traffic-Sign Detection and Classification in the Wild
- intro: CVPR 2016
- project page(code+dataset): http://cg.cs.tsinghua.edu.cn/traffic-sign/
- paper: http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Zhu_Traffic-Sign_Detection_and_CVPR_2016_paper.pdf
- code & model: http://cg.cs.tsinghua.edu.cn/traffic-sign/data_model_code/newdata0411.zip
Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data
- intro: CVPR 2017 workshop
- paper: http://openaccess.thecvf.com/content_cvpr_2017_workshops/w9/papers/Jensen_Evaluating_State-Of-The-Art_Object_CVPR_2017_paper.pdf
Detecting Small Signs from Large Images
- intro: IEEE Conference on Information Reuse and Integration (IRI) 2017 oral
- arxiv: https://arxiv.org/abs/1706.08574
Localized Traffic Sign Detection with Multi-scale Deconvolution Networks
Detecting Traffic Lights by Single Shot Detection
- intro: ITSC 2018
- arxiv: https://arxiv.org/abs/1805.02523
A Hierarchical Deep Architecture and Mini-Batch Selection Method For Joint Traffic Sign and Light Detection
- intro: IEEE 15th Conference on Computer and Robot Vision
- arxiv: https://arxiv.org/abs/1806.07987
- demo: https://www.youtube.com/watch?v=_YmogPzBXOw&feature=youtu.be
Skeleton Detection
Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs
DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images
SRN: Side-output Residual Network for Object Symmetry Detection in the Wild
- intro: CVPR 2017
- arxiv: https://arxiv.org/abs/1703.02243
- github: https://github.com/KevinKecc/SRN
Hi-Fi: Hierarchical Feature Integration for Skeleton Detection
Fruit Detection
Deep Fruit Detection in Orchards
Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards
- intro: The Journal of Field Robotics in May 2016
- project page: http://confluence.acfr.usyd.edu.au/display/AGPub/
- arxiv: https://arxiv.org/abs/1610.08120
Shadow Detection
Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network
A+D-Net: Shadow Detection with Adversarial Shadow Attenuation
Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
Direction-aware Spatial Context Features for Shadow Detection
- intro: CVPR 2018
- arxiv: https://arxiv.org/abs/1712.04142
Direction-aware Spatial Context Features for Shadow Detection and Removal
- intro: The Chinese University of Hong Kong & The Hong Kong Polytechnic University
- arxiv: https://arxiv.org/abs/1805.04635
Others Detection
Deep Deformation Network for Object Landmark Localization
Fashion Landmark Detection in the Wild
- intro: ECCV 2016
- project page: http://personal.ie.cuhk.edu.hk/~lz013/projects/FashionLandmarks.html
- arxiv: http://arxiv.org/abs/1608.03049
- github(Caffe): https://github.com/liuziwei7/fashion-landmarks
Deep Learning for Fast and Accurate Fashion Item Detection
- intro: Kuznech Inc.
- intro: MultiBox and Fast R-CNN
- paper: https://kddfashion2016.mybluemix.net/kddfashion_finalSubmissions/Deep Learning for Fast and Accurate Fashion Item Detection.pdf
OSMDeepOD - OSM and Deep Learning based Object Detection from Aerial Imagery (formerly known as “OSM-Crosswalk-Detection”)
Selfie Detection by Synergy-Constraint Based Convolutional Neural Network
- intro: IEEE SITIS 2016
- arxiv: https://arxiv.org/abs/1611.04357
Associative Embedding:End-to-End Learning for Joint Detection and Grouping
Deep Cuboid Detection: Beyond 2D Bounding Boxes
- intro: CMU & Magic Leap
- arxiv: https://arxiv.org/abs/1611.10010
Automatic Model Based Dataset Generation for Fast and Accurate Crop and Weeds Detection
Deep Learning Logo Detection with Data Expansion by Synthesising Context
Scalable Deep Learning Logo Detection
Pixel-wise Ear Detection with Convolutional Encoder-Decoder Networks
Automatic Handgun Detection Alarm in Videos Using Deep Learning
- arxiv: https://arxiv.org/abs/1702.05147
- results: https://github.com/SihamTabik/Pistol-Detection-in-Videos
Objects as context for part detection
Using Deep Networks for Drone Detection
- intro: AVSS 2017
- arxiv: https://arxiv.org/abs/1706.05726
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
- intro: ICCV 2017
- arxiv: https://arxiv.org/abs/1708.01642
Target Driven Instance Detection
DeepVoting: An Explainable Framework for Semantic Part Detection under Partial Occlusion
VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition
- intro: ICCV 2017
- arxiv: https://arxiv.org/abs/1710.06288
- github: https://github.com/SeokjuLee/VPGNet
Grab, Pay and Eat: Semantic Food Detection for Smart Restaurants
ReMotENet: Efficient Relevant Motion Event Detection for Large-scale Home Surveillance Videos
- intro: WACV 2018
- arxiv: https://arxiv.org/abs/1801.02031
Deep Learning Object Detection Methods for Ecological Camera Trap Data
- intro: Conference of Computer and Robot Vision. University of Guelph
- arxiv: https://arxiv.org/abs/1803.10842
EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection
Towards End-to-End Lane Detection: an Instance Segmentation Approach
- arxiv: https://arxiv.org/abs/1802.05591
- github: https://github.com/MaybeShewill-CV/lanenet-lane-detection
iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection
- intro: BMVC 2018
- project page: https://gaochen315.github.io/iCAN/
- arxiv: https://arxiv.org/abs/1808.10437
- github: https://github.com/vt-vl-lab/iCAN
Densely Supervised Grasp Detector (DSGD)
Object Proposal
DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers
Scale-aware Pixel-wise Object Proposal Networks
- intro: IEEE Transactions on Image Processing
- arxiv: http://arxiv.org/abs/1601.04798
Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization
- intro: BMVC 2016. AttractioNet
- arxiv: https://arxiv.org/abs/1606.04446
- github: https://github.com/gidariss/AttractioNet
Learning to Segment Object Proposals via Recursive Neural Networks
Learning Detection with Diverse Proposals
- intro: CVPR 2017
- keywords: differentiable Determinantal Point Process (DPP) layer, Learning Detection with Diverse Proposals (LDDP)
- arxiv: https://arxiv.org/abs/1704.03533
ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
- keywords: product detection
- arxiv: https://arxiv.org/abs/1704.06752
Improving Small Object Proposals for Company Logo Detection
- intro: ICMR 2017
- arxiv: https://arxiv.org/abs/1704.08881
Open Logo Detection Challenge
- intro: BMVC 2018
- keywords: QMUL-OpenLogo
- project page: https://qmul-openlogo.github.io/
- arxiv: https://arxiv.org/abs/1807.01964
AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects
- intro: ACCV 2018 oral
- arxiv: https://arxiv.org/abs/1811.08728
- github: https://github.com/chwilms/AttentionMask
Localization
Beyond Bounding Boxes: Precise Localization of Objects in Images
- intro: PhD Thesis
- homepage: http://www.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-193.html
- phd-thesis: http://www.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-193.pdf
- github(“SDS using hypercolumns”): https://github.com/bharath272/sds
Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
Weakly Supervised Object Localization Using Size Estimates
Active Object Localization with Deep Reinforcement Learning
- intro: ICCV 2015
- keywords: Markov Decision Process
- arxiv: https://arxiv.org/abs/1511.06015
Localizing objects using referring expressions
- intro: ECCV 2016
- keywords: LSTM, multiple instance learning (MIL)
- paper: http://www.umiacs.umd.edu/~varun/files/refexp-ECCV16.pdf
- github: https://github.com/varun-nagaraja/referring-expressions
LocNet: Improving Localization Accuracy for Object Detection
- intro: CVPR 2016 oral
- arxiv: http://arxiv.org/abs/1511.07763
- github: https://github.com/gidariss/LocNet
Learning Deep Features for Discriminative Localization
- homepage: http://cnnlocalization.csail.mit.edu/
- arxiv: http://arxiv.org/abs/1512.04150
- github(Tensorflow): https://github.com/jazzsaxmafia/Weakly_detector
- github: https://github.com/metalbubble/CAM
- github: https://github.com/tdeboissiere/VGG16CAM-keras
ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
- intro: ECCV 2016
- project page: http://www.di.ens.fr/willow/research/contextlocnet/
- arxiv: http://arxiv.org/abs/1609.04331
- github: https://github.com/vadimkantorov/contextlocnet
Ensemble of Part Detectors for Simultaneous Classification and Localization
STNet: Selective Tuning of Convolutional Networks for Object Localization
Soft Proposal Networks for Weakly Supervised Object Localization
- intro: ICCV 2017
- arxiv: https://arxiv.org/abs/1709.01829
Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN
- intro: ACM MM 2017
- arxiv: https://arxiv.org/abs/1709.08295
Tutorials / Talks
Convolutional Feature Maps: Elements of efficient (and accurate) CNN-based object detection
Towards Good Practices for Recognition & Detection
- intro: Hikvision Research Institute. Supervised Data Augmentation (SDA)
- slides: http://image-net.org/challenges/talks/2016/Hikvision_at_ImageNet_2016.pdf
Work in progress: Improving object detection and instance segmentation for small objects
Object Detection with Deep Learning: A Review
Projects
Detectron
- intro: FAIR’s research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
- github: https://github.com/facebookresearch/Detectron
TensorBox: a simple framework for training neural networks to detect objects in images
- intro: “The basic model implements the simple and robust GoogLeNet-OverFeat algorithm. We additionally provide an implementation of the ReInspect algorithm”
- github: https://github.com/Russell91/TensorBox
Object detection in torch: Implementation of some object detection frameworks in torch
Using DIGITS to train an Object Detection network
FCN-MultiBox Detector
- intro: Full convolution MultiBox Detector (like SSD) implemented in Torch.
- github: https://github.com/teaonly/FMD.torch
KittiBox: A car detection model implemented in Tensorflow.
- keywords: MultiNet
- intro: KittiBox is a collection of scripts to train out model FastBox on the Kitti Object Detection Dataset
- github: https://github.com/MarvinTeichmann/KittiBox
Deformable Convolutional Networks + MST + Soft-NMS
How to Build a Real-time Hand-Detector using Neural Networks (SSD) on Tensorflow
- blog: https://towardsdatascience.com/how-to-build-a-real-time-hand-detector-using-neural-networks-ssd-on-tensorflow-d6bac0e4b2ce
- github: https://github.com//victordibia/handtracking
Metrics for object detection
- intro: Most popular metrics used to evaluate object detection algorithms
- github: https://github.com/rafaelpadilla/Object-Detection-Metrics
MobileNetv2-SSDLite
- intro: Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.
- github: https://github.com/chuanqi305/MobileNetv2-SSDLite
Leaderboard
Detection Results: VOC2012
- intro: Competition “comp4” (train on additional data)
- homepage: http://host.robots.ox.ac.uk:8080/leaderboard/displaylb.php?challengeid=11&compid=4
Tools
BeaverDam: Video annotation tool for deep learning training labels
https://github.com/antingshen/BeaverDam
Blogs
Convolutional Neural Networks for Object Detection
http://rnd.azoft.com/convolutional-neural-networks-object-detection/
Introducing automatic object detection to visual search (Pinterest)
- keywords: Faster R-CNN
- blog: https://engineering.pinterest.com/blog/introducing-automatic-object-detection-visual-search
- demo: https://engineering.pinterest.com/sites/engineering/files/Visual Search V1 - Video.mp4
- review: https://news.developer.nvidia.com/pinterest-introduces-the-future-of-visual-search/?mkt_tok=eyJpIjoiTnpaa01UWXpPRE0xTURFMiIsInQiOiJJRjcybjkwTmtmallORUhLOFFFODBDclFqUlB3SWlRVXJXb1MrQ013TDRIMGxLQWlBczFIeWg0TFRUdnN2UHY2ZWFiXC9QQVwvQzBHM3B0UzBZblpOSmUyU1FcLzNPWXI4cml2VERwTTJsOFwvOEk9In0%3D
Deep Learning for Object Detection with DIGITS
Analyzing The Papers Behind Facebook’s Computer Vision Approach
- keywords: DeepMask, SharpMask, MultiPathNet
- blog: https://adeshpande3.github.io/adeshpande3.github.io/Analyzing-the-Papers-Behind-Facebook’s-Computer-Vision-Approach/
Easily Create High Quality Object Detectors with Deep Learning
- intro: dlib v19.2
- blog: http://blog.dlib.net/2016/10/easily-create-high-quality-object.html
How to Train a Deep-Learned Object Detection Model in the Microsoft Cognitive Toolkit
- blog: https://blogs.technet.microsoft.com/machinelearning/2016/10/25/how-to-train-a-deep-learned-object-detection-model-in-cntk/
- github: https://github.com/Microsoft/CNTK/tree/master/Examples/Image/Detection/FastRCNN
Object Detection in Satellite Imagery, a Low Overhead Approach
- part 1: https://medium.com/the-downlinq/object-detection-in-satellite-imagery-a-low-overhead-approach-part-i-cbd96154a1b7#.2csh4iwx9
- part 2: https://medium.com/the-downlinq/object-detection-in-satellite-imagery-a-low-overhead-approach-part-ii-893f40122f92#.f9b7dgf64
You Only Look Twice — Multi-Scale Object Detection in Satellite Imagery With Convolutional Neural Networks
- part 1: https://medium.com/the-downlinq/you-only-look-twice-multi-scale-object-detection-in-satellite-imagery-with-convolutional-neural-38dad1cf7571#.fmmi2o3of
- part 2: https://medium.com/the-downlinq/you-only-look-twice-multi-scale-object-detection-in-satellite-imagery-with-convolutional-neural-34f72f659588#.nwzarsz1t
Faster R-CNN Pedestrian and Car Detection
- blog: https://bigsnarf.wordpress.com/2016/11/07/faster-r-cnn-pedestrian-and-car-detection/
- ipn: https://gist.github.com/bigsnarfdude/2f7b2144065f6056892a98495644d3e0#file-demo_faster_rcnn_notebook-ipynb
- github: https://github.com/bigsnarfdude/Faster-RCNN_TF
Small U-Net for vehicle detection
Region of interest pooling explained
- blog: https://deepsense.io/region-of-interest-pooling-explained/
- github: https://github.com/deepsense-io/roi-pooling
Supercharge your Computer Vision models with the TensorFlow Object Detection API
- blog: https://research.googleblog.com/2017/06/supercharge-your-computer-vision-models.html
- github: https://github.com/tensorflow/models/tree/master/object_detection
Understanding SSD MultiBox — Real-Time Object Detection In Deep Learning
One-shot object detection
http://machinethink.net/blog/object-detection/
An overview of object detection: one-stage methods
https://www.jeremyjordan.me/object-detection-one-stage/
deep learning object detection
- intro: A paper list of object detection using deep learning.
- github: https://github.com/hoya012/deep_learning_object_detection