Object Counting

Object Counting

Towards perspective-free object counting with deep learning

• intro: ECCV 2016. Counting CNN and Hydra CNN
• paper: http://agamenon.tsc.uah.es/Investigacion/gram/publications/eccv2016-onoro.pdf
• github: https://github.com/gramuah/ccnn
• poster: http://www.eccv2016.org/files/posters/P-3B-26.pdf

Using Convolutional Neural Networks to Count Palm Trees in Satellite Images

• arxiv: https://arxiv.org/abs/1701.06462

Count-ception: Counting by Fully Convolutional Redundant Counting

https://arxiv.org/abs/1703.08710

Counting Objects with Faster R-CNN

• blog: https://softwaremill.com/counting-objects-with-faster-rcnn/
• github: https://github.com/softberries/keras-frcnn

Drone-based Object Counting by Spatially Regularized Regional Proposal Network

https://arxiv.org/abs/1707.05972

FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras

• intro: ICCV 2017. CMU & Universidade de Lisboa
• arxiv: https://arxiv.org/abs/1707.09476

Representation Learning by Learning to Count

• intro: ICCV 2017 oral
• arxiv: https://arxiv.org/abs/1708.06734

Leaf Counting with Deep Convolutional and Deconvolutional Networks

• intro: ICCV 2017 Workshop on Computer Vision Problems in Plant Phenotyping
• arxiv: https://arxiv.org/abs/1708.07570

Improving Object Counting with Heatmap Regulation

https://arxiv.org/abs/1803.05494

Learning Short-Cut Connections for Object Counting

• keywords: Gated U-Net (GU-Net)
• arxiv: https://arxiv.org/abs/1805.02919

Object Counting with Small Datasets of Large Images

https://arxiv.org/abs/1805.11123

Counting with Focus for Free

• intro: ICCV 2019
• arxiv: https://arxiv.org/abs/1903.12206
• github: https://github.com/shizenglin/Counting-with-Focus-for-Free

Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting

https://arxiv.org/abs/2012.08149

Object Counting: You Only Need to Look at One

• intro: Xi’an Jiaotong University
• arxiv: https://arxiv.org/abs/2112.05993

Crowd Counting / Crowd Analysis

Large scale crowd analysis based on convolutional neural network

• paper: http://www.sciencedirect.com/science/article/pii/S0031320315001259

Deep People Counting in Extremely Dense Crowds

• intro: ACM 2015
• paper: http://yangliang.github.io/pdf/sp055u.pdf

Crossing-line Crowd Counting with Two-phase Deep Neural Networks

• intro: ECCV 2016
• paper: http://www.ee.cuhk.edu.hk/~rzhao/project/crossline_eccv16/ZhaoLZWeccv16.pdf
• poster: http://www.eccv2016.org/files/posters/P-3C-41.pdf

Cross-scene Crowd Counting via Deep Convolutional Neural Networks

• intro: CVPR 2015
• paper: http://www.ee.cuhk.edu.hk/~xgwang/papers/zhangLWYcvpr15.pdf

Single-Image Crowd Counting via Multi-Column Convolutional Neural Network

• intro: CVPR 2016
• paper: http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Zhang_Single-Image_Crowd_Counting_CVPR_2016_paper.pdf
• paper: http://sist.shanghaitech.edu.cn/office/research/news/CVPR2016/paper/Single-Image%20Crowd%20Counting%20via%20Multi-Column%20Convolutional%20Neural%20Network.pdf
• dataset(pwd: p1rv): http://pan.baidu.com/s/1gfyNBTh
• slides: http://smartdsp.xmu.edu.cn/%E6%B1%87%E6%8A%A5pdf/crowd%20counting%E6%9E%97%E8%B4%A8%E9%94%90.pdf
• github:https://github.com/svishwa/crowdcount-mcnn

CrowdNet: A Deep Convolutional Network for Dense Crowd Counting

• intro: ACM Multimedia (MM) 2016
• arxiv: http://arxiv.org/abs/1608.06197
• github(Caffe): https://github.com/davideverona/deep-crowd-counting_crowdnet

Crowd Counting by Adapting Convolutional Neural Networks with Side Information

• arxiv: https://arxiv.org/abs/1611.06748

Fully Convolutional Crowd Counting On Highly Congested Scenes

• intro: VISAPP 2017
• arxiv: https://arxiv.org/abs/1612.00220

Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction

• intro: AAAI 2017
• project page: https://www.microsoft.com/en-us/research/publication/deep-spatio-temporal-residual-networks-for-citywide-crowd-flows-prediction/
• paper: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/11/ST-ResNet-AAAI17-Zhang.pdf
• github: https://github.com/lucktroy/DeepST/tree/master/scripts/papers/AAAI17
• ppt: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/11/DeepST-crowd-prediction.pptx
• system: http://urbanflow.sigkdd.com.cn/

Multi-scale Convolutional Neural Networks for Crowd Counting

• arxiv: https://arxiv.org/abs/1702.02359

Mixture of Counting CNNs: Adaptive Integration of CNNs Specialized to Specific Appearance for Crowd Counting

https://arxiv.org/abs/1703.09393

Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks - Counting, Detection, and Tracking

https://arxiv.org/abs/1705.10118

ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification

• intro: AVSS 2017
• arxiv: https://arxiv.org/abs/1705.10698

Image Crowd Counting Using Convolutional Neural Network and Markov Random Field

• intro: CVPR 2017
• arxiv: https://arxiv.org/abs/1706.03725

A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation

https://arxiv.org/abs/1707.01202

Spatiotemporal Modeling for Crowd Counting in Videos

• intro: ICCV 2017
• arxiv: https://arxiv.org/abs/1707.07890

CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting

• intro: AVSS 2017 (14th International Conference on Advanced Video and Signal Based Surveillance)
• arxiv: https://arxiv.org/abs/1707.09605

Switching Convolutional Neural Network for Crowd Counting

• intro: CVPR 2017. Indian Institute of Science
• project page: http://val.serc.iisc.ernet.in/crowdcnn/
• arxiv: https://arxiv.org/abs/1708.00199
• github: https://github.com/val-iisc/crowd-counting-scnn

Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs

• intro: ICCV 2017
• arxiv: https://arxiv.org/abs/1708.00953

Deep Spatial Regression Model for Image Crowd Counting

https://arxiv.org/abs/1710.09757

Crowd counting via scale-adaptive convolutional neural network

• intro: WACV 2-18. Tencent Youtu Lab
• arxiv: https://arxiv.org/abs/1711.04433
• github: https://github.com/miao0913/SaCNN-CrowdCounting-Tencent_Youtu

DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation

• intro: CVPR 2018
• arxiv: https://arxiv.org/abs/1712.06679

Structured Inhomogeneous Density Map Learning for Crowd Counting

https://arxiv.org/abs/1801.06642

Understanding Human Behaviors in Crowds by Imitating the Decision-Making Process

• intro: AAAI 2018
• arxiv: https://arxiv.org/abs/1801.08391

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

• intro: CVPR 2018
• arxiv: https://arxiv.org/abs/1803.03095

Crowd Counting via Adversarial Cross-Scale Consistency Pursuit

• intro: CVPR 2018
• paper: http://openaccess.thecvf.com/content_cvpr_2018/papers/Shen_Crowd_Counting_via_CVPR_2018_paper.pdf
• github: https://github.com/Ling-Bao/ACSCP_cGAN

Crowd Counting with Deep Negative Correlation Learning

• intro: CVPR 2018
• paper: http://openaccess.thecvf.com/content_cvpr_2018/papers/Shi_Crowd_Counting_With_CVPR_2018_paper.pdf
• github: https://github.com/shizenglin/Deep-NCL

An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting

• intro: CVPR 2018 Workshop On Visual Understanding of Humans in Crowd Scene
• arxiv: https://arxiv.org/abs/1804.07821

A Deeply-Recursive Convolutional Network for Crowd Counting

• intro: Xiamen University
• arxiv: https://arxiv.org/abs/1805.05633

Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid

https://arxiv.org/abs/1805.06115

Attention to Head Locations for Crowd Counting

https://arxiv.org/abs/1806.10287

Crowd Counting with Density Adaption Networks

https://arxiv.org/abs/1806.10040

Perspective-Aware CNN For Crowd Counting

https://arxiv.org/abs/1807.01989

Crowd Counting using Deep Recurrent Spatial-Aware Network

• intro: IJCAI 2018
• arxiv: https://arxiv.org/abs/1807.00601

Top-Down Feedback for Crowd Counting Convolutional Neural Network

https://arxiv.org/abs/1807.08881

Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds

• intro: ECCV 2018
• arxiv: https://arxiv.org/abs/1808.01050

Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance

• arxiv: https://arxiv.org/abs/1808.07456
• github: https://github.com/siyuhuang/crowdcount-stackpool

In Defense of Single-column Networks for Crowd Counting

https://arxiv.org/abs/1808.06133

Attentive Crowd Flow Machines

• intro: ACM MM, full paper
• arxiv: https://arxiv.org/abs/1809.00101

Context-Aware Crowd Counting

• intro: CVPR 2019
• arxiv: https://arxiv.org/abs/1811.10452
• github: https://github.com/weizheliu/Context-Aware-Crowd-Counting

ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding

https://arxiv.org/abs/1811.11968

Learning from Synthetic Data for Crowd Counting in the Wild

• intro: CVPR 2019
• project page: https://gjy3035.github.io/GCC-CL/
• arxiv: https://arxiv.org/abs/1903.03303

Point in, Box out: Beyond Counting Persons in Crowds

• intro: CVPR 2019
• arxiv: https://arxiv.org/abs/1904.01333

Crowd Transformer Network

https://arxiv.org/abs/1904.02774

DENet: A Universal Network for Counting Crowd with Varying Densities and Scales

https://arxiv.org/abs/1904.08056

PCC Net: Perspective Crowd Counting via Spatial Convolutional Network

• intro: IEEE T-CSVT
• arxiv: https://arxiv.org/abs/1905.10085
• github: https://github.com/gjy3035/PCC-Net

Dense Scale Network for Crowd Counting

https://arxiv.org/abs/1906.09707

Inverse Attention Guided Deep Crowd Counting Network

• intro: AVSS 2019
• arxiv: https://arxiv.org/abs/1907.01193

Locality-constrained Spatial Transformer Network for Video Crowd Counting

• intro: ICME 2019 Oral
• arxiv: https://arxiv.org/abs/1907.07911

HA-CCN: Hierarchical Attention-based Crowd Counting Network

• intro: TIP 2019
• arxiv: https://arxiv.org/abs/1907.10255

Learn to Scale: Generating Multipolar Normalized Density Map for Crowd Counting

• intro: ICCV 2019
• arxiv: https://arxiv.org/abs/1907.12428**

Deep Density-aware Count Regressor

https://arxiv.org/abs/1908.03314

Bayesian Loss for Crowd Count Estimation with Point Supervision

• intro: ICCV 2019 oral
• arxiv: https://arxiv.org/abs/1908.03684
• github: https://github.com/ZhihengCV/Bayesian-Crowd-Counting

Crowd Counting with Deep Structured Scale Integration Network

• intro: ICCV 2019
• arxiv: https://arxiv.org/abs/1908.08692

Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting

• intro: ICCV 2019
• arxiv: https://arxiv.org/abs/1908.10937

Awesome Crowd Counting

https://github.com/gjy3035/Awesome-Crowd-Counting

Learning Spatial Awareness to Improve Crowd Counting

• intro: ICCV 2019 oral
• intro: Southwest Jiaotong University & Carnegie Mellon University & Microsoft Research
• keywords: SPatial Awareness Network (SPANet), Maximum Excess over Pixels (MEP) loss
• arxiv: https://arxiv.org/abs/1909.07057

Perspective-Guided Convolution Networks for Crowd Counting

• intro: ICCV 2019
• arxiv: https://arxiv.org/abs/1909.06966
• github: https://github.com/Zhaoyi-Yan/PGCNet

Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method

• intro: ICCV 2019
• arxiv: https://arxiv.org/abs/1910.12384

Feature-aware Adaptation and Structured Density Alignment for Crowd Counting in Video Surveillance

https://arxiv.org/abs/1912.03672

AutoScale: Learning to Scale for Crowd Counting

https://arxiv.org/abs/1912.09632