Awesome Crowd Counting

If you have any problems, suggestions or improvements, please submit the issue or PR.

Misc

News

[2020.04] The JHU-CROWD++ Dataset is released.
[2021.04] The RGBT-CC Benchmark is released.

Call for Papers

[IET Image Processing] Special Issue on: Crowd Understanding and Analysis [Link] [PDF]

Challenge

[VisDrone 2020] ~~Crowd counting. ECCV Workshop. Deadline: 2020.07.15.~~
[NWPU-Crowd Counting] Crowd counting. Deadline: none.

Code

[C^3 Framework] An open-source PyTorch code for crowd counting, which is released.
[CCLabeler] A web tool for labeling pedestrians in an image, which is released.

Technical blog

[Chinese Blog] 人群计数论文解读 [Link]
[2019.05] [Chinese Blog] C^3 Framework系列之一：一个基于PyTorch的开源人群计数框架 [Link]
[2019.04] Crowd counting from scratch [Link]
[2017.11] Counting Crowds and Lines with AI [Link1] [Link2] [Code]

GT generation

Density Map Generation from Key Points [Matlab Code] [Python Code] [Fast Python Code] [Pytorch CUDA Code]

Related Tasks

Crowd Analysis, Crowd Localization, Video Surveillance, Dense/Small/Tiny Object Detection

Datasets

Please refer to this page.

Papers

Considering the increasing number of papers in this field, we roughly summarize some articles and put them into the following categories (they are still listed in this document):

[Top Conference/Journal]	[Survey]	[Un-/semi-/weakly-/self- Supervised Learning]
[Auxiliary Tasks]	[Localization]	[Transfer Learning and Domain Adaptation]
[Light-weight Models]	[Video]	[Network Design, Search]
[Perspective Map]	[Attention]	Todo

arXiv papers

Note that all unpublished arXiv papers are not included in the leaderboard of performance.

Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting [paper]
Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting [paper]
TransCrowd: Weakly-Supervised Crowd Counting with Transformer [paper]
Leveraging Self-Supervision for Cross-Domain Crowd Counting [paper]
Multi-channel Deep Supervision for Crowd Counting [paper]
Focal Inverse Distance Transform Maps for Crowd Localization and Counting in Dense Crowd [paper] [code]
Enhanced Information Fusion Network for Crowd Counting [paper]
Scale-Aware Network with Regional and Semantic Attentions for Crowd Counting under Cluttered Background [paper]
CNN-based Single Image Crowd Counting: Network Design, Loss Function and Supervisory Signal [paper]
Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting [paper]
STNet: Scale Tree Network with Multi-level Auxiliator for Crowd Counting [paper]
Learning Independent Instance Maps for Crowd Localization [paper] [code]
PSCNet: Pyramidal Scale and Global Context Guided Network for Crowd Counting [paper]
Wide-Area Crowd Counting: Multi-View Fusion Networks for Counting in Large Scenes [paper](extension of MVMS)
Counting People by Estimating People Flows [paper][code]

Earlier ArXiv Papers

A Strong Baseline for Crowd Counting and Unsupervised People Localization [paper]
Multi-Resolution Fusion and Multi-scale Input Priors Based Crowd Counting [paper]
Completely Self-Supervised Crowd Counting via Distribution Matching [paper][code]
A Study of Human Gaze Behavior During Visual Crowd Counting [paper]
Bayesian Multi Scale Neural Network for Crowd Counting [paper][code]
DeepCorn: A Semi-Supervised Deep Learning Method for High-Throughput Image-Based Corn Kernel Counting and Yield Estimation [paper]
Dense Crowds Detection and Counting with a Lightweight Architecture [paper]
Exploit the potential of Multi-column architecture for Crowd Counting [paper][code]
Recurrent Distillation based Crowd Counting [paper]
Interlayer and Intralayer Scale Aggregation for Scale-invariant Crowd Counting [paper]
Ambient Sound Helps: Audiovisual Crowd Counting in Extreme Conditions [paper][code]
CNN-based Density Estimation and Crowd Counting: A Survey [paper]
Drone Based RGBT Vehicle Detection and Counting: A Challenge [paper]
PDANet: Pyramid Density-aware Attention Net for Accurate Crowd Counting [paper]
From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting [paper](extension of S-DCNet)
AutoScale: Learning to Scale for Crowd Counting [paper](extension of L2SM)
Domain-adaptive Crowd Counting via Inter-domain Features Segregation and Gaussian-prior Reconstruction [paper]
Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network [paper][code]
Using Depth for Pixel-Wise Detection of Adversarial Attacks in Crowd Counting [paper]
Segmentation Guided Attention Network for Crowd Counting via Curriculum Learning [paper]
Dense Scale Network for Crowd Counting [paper][unofficial code: PyTorch]
Content-aware Density Map for Crowd Counting and Density Estimation [paper]
Crowd Transformer Network [paper]
W-Net: Reinforced U-Net for Density Map Estimation [paper][code]
Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting [paper]
Scale-Aware Attention Network for Crowd Counting [paper]
Crowd Counting with Density Adaption Networks [paper]
Improving Object Counting with Heatmap Regulation [paper][code]
Structured Inhomogeneous Density Map Learning for Crowd Counting [paper]

### 2022

Attention-Guided Collaborative Counting (TIP2022)[paper]
Localization in Crowds with Loosen-structured Pair-of-points Loss (ICVRV2022)

2021

A Generalized Loss Function for Crowd Counting and Localization (CVPR2021)
Cross-View Cross-Scene Multi-View Crowd Counting (CVPR2021)
[STANet] Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark (CVPR2021) [paper][code]
[SCALNet] Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization (ICMEW) [paper]
[RGBT-CC] Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting (CVPR2021) [paper][code]
[EDIREC-Net] Error-Aware Density Isomorphism Reconstruction for Unsupervised Cross-Domain Crowd Counting (AAAI2021) [paper][code]
[SASNet] To Choose or to Fuse? Scale Selection for Crowd Counting (AAAI2021) [paper][code]
Learning to Count via Unbalanced Optimal Transport (AAAI2021)
[TopoCount] Localization in the Crowd with Topological Constraints (AAAI2021) [paper][code]
[CFANet] Coarse- and Fine-grained Attention Network with Background-aware Loss for Crowd Density Map Estimation (WACV) [paper][code]
[BSCC] Understanding the impact of mistakes on background regions in crowd counting (WACV) [paper]
[CFOCNet] Class-agnostic Few-shot Object Counting (WACV) [paper]
[NLT] Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting (T-NNLS) [paper] [code]]
[MATT] Towards Using Count-level Weak Supervision for Crowd Counting (Pattern Recognition) [paper]
[D2C] Decoupled Two-Stage Crowd Counting and Beyond (TIP) [paper][code]
[TBC] Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets (TIP) [paper]
[FGCC] Fine-Grained Crowd Counting (TIP) [paper]
[PSODC] A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds (TIP) [paper][code]
[EPA] Embedding Perspective Analysis Into Multi-Column Convolutional Neural Network for Crowd Counting (TIP) [paper]
[STDNet] Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation (TMM) [paper]
[AdaCrowd] AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting (TMM) [paper][code]

2020

[MH-METRONET] MH-MetroNet—A Multi-Head CNN for Passenger-Crowd Attendance Estimation (JImaging) [paper][code]
[M-SFANet] Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting (ICPR) [paper][code]
[JHU-CROWD] JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (T-PAMI) [paper](extension of CG-DRCN)
[DM-Count] Distribution Matching for Crowd Counting (NeurIPS) [paper][code]
[MNA] Modeling Noisy Annotations for Crowd Counting (NeurIPS) [paper]
[KDMG] Kernel-based Density Map Generation for Dense Object Counting (T-PAMI) [paper][code]
[NWPU] NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization (T-PAMI) [paper][code]
[PWCU] Pixel-wise Crowd Understanding via Synthetic Data (IJCV) [paper]
[SKT] Efficient Crowd Counting via Structured Knowledge Transfer (ACM MM(oral)) [paper][code]
[DPN] Learning Scales from Points: A Scale-aware Probabilistic Model for Crowd Counting (ACM MM(oral)) [paper]
[RDBT] Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer (ACM MM) [paper]
[PeopleFlow] Estimating People Flows to Better Count Them in Crowded Scenes (ECCV) [paper][code]
[AMSNet] NAS-Count: Counting-by-Density with Neural Architecture Search (ECCV) [paper]
[AMRNet] Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting (ECCV) [paper][code]
[LibraNet] Weighting Counts: Sequential Crowd Counting by Reinforcement Learning (ECCV) [paper][code]
[GP] Learning to Count in the Crowd from Limited Labeled Data (ECCV) [paper]
[IRAST] Semi-supervised Crowd Counting via Self-training on Surrogate Tasks (ECCV) [paper]
[PSSW] Active Crowd Counting with Limited Supervision (ECCV) [paper]
[CCLS] Weakly-Supervised Crowd Counting Learns from Sorting rather than Locations (ECCV) [paper]
[EPF] Estimating People Flows to Better Count them in Crowded Scenes (ECCV) [paper]
A Flow Base Bi-path Network for Cross-scene Video Crowd Understanding in Aerial View (ECCVW) [paper]
[ADSCNet] Adaptive Dilated Network with Self-Correction Supervision for Counting (CVPR) [paper]
[RPNet] Reverse Perspective Network for Perspective-Aware Object Counting (CVPR) [paper] [code]
[ASNet] Attention Scaling for Crowd Counting (CVPR) [paper] [code]
[LSC-CNN] Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection (T-PAMI) [paper][code]
[SRF-Net] Scale-Aware Rolling Fusion Network for Crowd Counting (ICME) [paper]
[HSRNet] Crowd Counting via Hierarchical Scale Recalibration Network (ECAI) [paper]
[DeepCount] Deep Density-aware Count Regressor (ECAI) [paper][code]
[SOFA-Net] SOFA-Net: Second-Order and First-order Attention Network for Crowd Counting (BMVC) [paper]
[CWAN] Weakly Supervised Crowd-Wise Attention For Robust Crowd Counting (ICASSP) [paper]
[AGRD] Attention Guided Region Division for Crowd Counting (ICASSP) [paper]
[BBA-NET] BBA-NET: A Bi-Branch Attention Network For Crowd Counting (ICASSP) [paper]
[SMANet] Stochastic Multi-Scale Aggregation Network for Crowd Counting (ICASSP) [paper]
[Stacked-Pool] Stacked Pooling For Boosting Scale Invariance Of Crowd Counting (ICASSP) [paper] [arxiv] [code]
[MSPNET] Multi-supervised Parallel Network for Crowd Counting (ICASSP) [paper]
[ASPDNet] Counting dense objects in remote sensing images (ICASSP) [paper]
[FSC] Focus on Semantic Consistency for Cross-domain Crowd Understanding (ICASSP) [paper]
[C-CNN] A Real-Time Deep Network for Crowd Counting (ICASSP) [arxiv][ieee]
[HyGnn] Hybrid Graph Neural Networks for Crowd Counting (AAAI) [paper]
[DUBNet] Crowd Counting with Decomposed Uncertainty (AAAI) [paper]
[SDANet] Shallow Feature based Dense Attention Network for Crowd Counting (AAAI) [paper]
[3DCC] 3D Crowd Counting via Multi-View Fusion with 3D Gaussian Kernels (AAAI) [paper][Project]
[FSSA] Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning (WACV) [paper][code]
[CC-Mod] Plug-and-Play Rescaling Based Crowd Counting in Static Images (WACV) [paper]
[CTN] Uncertainty Estimation and Sample Selection for Crowd Counting (ACCV) [paper]
[CLPNet] Cross-Level Parallel Network for Crowd Counting (TII) [paper]
[HA-CCN] HA-CCN: Hierarchical Attention-based Crowd Counting Network (TIP) [paper]
[PaDNet] PaDNet: Pan-Density Crowd Counting (TIP) [paper]
[CRNet] Crowd Counting via Cross-stage Refinement Networks (TIP) [paper][code]
[BNFDD] Background Noise Filtering and Distribution Dividing for Crowd Counting (TIP) [paper]
[FADA] Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance (TCYB) [paper]
[MS-GAN] Adversarial Learning for Multiscale Crowd Counting Under Complex Scenes (TCYB) [paper]
[DCL] Density-aware Curriculum Learning for Crowd Counting (TCYB) [paper][code]
[ZoomCount] ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images (T-CSVT) [paper]
[Deem] Scale-Aware Crowd Counting via Depth-Embedded Convolutional Neural Networks (T-CSVT) [paper]
[DensityCNN] Density-Aware Multi-Task Learning for Crowd Counting (TMM) [paper]
[DENet] DENet: A Universal Network for Counting Crowd with Varying Densities and Scales (TMM) [paper][code]
[FMLF] Crowd Density Estimation Using Fusion of Multi-Layer Features (TITS) [paper]
[MLSTN] Multi-level feature fusion based Locality-Constrained Spatial Transformer network for video crowd counting (Neurocomputing) [paper](extension of LSTN)
[SRN+PS] Scale-Recursive Network with point supervision for crowd scene analysis (Neurocomputing) [paper]
[ASDF] Counting crowds with varying densities via adaptive scenario discovery framework (Neurocomputing) [paper](extension of ASD)
[CAT-CNN] Crowd counting with crowd attention convolutional neural network (Neurocomputing) [paper]
[RRP] Relevant Region Prediction for Crowd Counting (Neurocomputing) [paper]
[SCAN] Crowd Counting via Scale-Communicative Aggregation Networks (Neurocomputing) [paper](extension of MVSAN)
[MobileCount] MobileCount: An Efficient Encoder-Decoder Framework for Real-Time Crowd Counting (Neurocomputing) [conference paper] [journal paper] [code]
[TAN] Fast Video Crowd Counting with a Temporal Aware Network (Neurocomputing) [paper]
[ikNN] Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling (VISAPP) [paper]

2019

[D-ConvNet] Nonlinear Regression via Deep Negative Correlation Learning (T-PAMI) [paper](extension of D-ConvNet)[Project]
Generalizing semi-supervised generative adversarial networks to regression using feature contrasting (CVIU)[paper]
[CG-DRCN] Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method (ICCV)[paper]
[ADMG] Adaptive Density Map Generation for Crowd Counting (ICCV)[paper]
[DSSINet] Crowd Counting with Deep Structured Scale Integration Network (ICCV) [paper][code]
[RANet] Relational Attention Network for Crowd Counting (ICCV)[paper]
[ANF] Attentional Neural Fields for Crowd Counting (ICCV)[paper]
[SPANet] Learning Spatial Awareness to Improve Crowd Counting (ICCV(oral)) [paper]
[MBTTBF] Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting (ICCV) [paper]
[CFF] Counting with Focus for Free (ICCV) [paper][code]
[L2SM] Learn to Scale: Generating Multipolar Normalized Density Map for Crowd Counting (ICCV) [paper]
[S-DCNet] From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer (ICCV) [paper][code]
[BL] Bayesian Loss for Crowd Count Estimation with Point Supervision (ICCV(oral)) [paper][code]
[PGCNet] Perspective-Guided Convolution Networks for Crowd Counting (ICCV) [paper][code]
[SACANet] Crowd Counting on Images with Scale Variation and Isolated Clusters (ICCVW) [paper]
[McML] Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting (ACM MM) [paper]
[DADNet] DADNet: Dilated-Attention-Deformable ConvNet for Crowd Counting (ACM MM) [paper]
[MRNet] Crowd Counting via Multi-layer Regression (ACM MM) [paper]
[MRCNet] MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground Imagery (BMVCW)[paper]
[E3D] Enhanced 3D convolutional networks for crowd counting (BMVC) [paper]
[OSSS] One-Shot Scene-Specific Crowd Counting (BMVC) [paper]
[RAZ-Net] Recurrent Attentive Zooming for Joint Crowd Counting and Precise Localization (CVPR) [paper]
[RDNet] Density Map Regression Guided Detection Network for RGB-D Crowd Counting and Localization (CVPR) [paper][code]
[RRSP] Residual Regression with Semantic Prior for Crowd Counting (CVPR) [paper][code]
[MVMS] Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs (CVPR) [paper] [Project] [Dataset&Code]
[AT-CFCN] Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting (CVPR) [paper]
[TEDnet] Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks (CVPR) [paper]
[CAN] Context-Aware Crowd Counting (CVPR) [paper] [code]
[PACNN] Revisiting Perspective Information for Efficient Crowd Counting (CVPR)[paper]
[PSDDN] Point in, Box out: Beyond Counting Persons in Crowds (CVPR(oral))[paper]
[ADCrowdNet] ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding (CVPR) [paper]
[CCWld, SFCN] Learning from Synthetic Data for Crowd Counting in the Wild (CVPR) [paper] [Project] [arxiv]
[DG-GAN] Dense Crowd Counting Convolutional Neural Networks with Minimal Data using Semi-Supervised Dual-Goal Generative Adversarial Networks (CVPRW)[paper]
[GSP] Global Sum Pooling: A Generalization Trick for Object Counting with Small Datasets of Large Images (CVPRW)[paper]
[SL2R] Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank (T-PAMI) [paper](extension of L2R)
[IA-DNN] Inverse Attention Guided Deep Crowd Counting Network (AVSS Best Paper) [paper]
[MTCNet] MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation (AVSS) [paper]
[CODA] CODA: Counting Objects via Scale-aware Adversarial Density Adaption (ICME) [paper][code]
[LSTN] Locality-Constrained Spatial Transformer Network for Video Crowd Counting (ICME(oral)) [paper]
[DRD] Dynamic Region Division for Adaptive Learning Pedestrian Counting (ICME) [paper]
[MVSAN] Crowd Counting via Multi-View Scale Aggregation Networks (ICME) [paper]
[ASD] Adaptive Scenario Discovery for Crowd Counting (ICASSP) [paper]
[SAAN] Crowd Counting Using Scale-Aware Attention Networks (WACV) [paper]
[SPN] Scale Pyramid Network for Crowd Counting (WACV) [paper]
[GWTA-CCNN] Almost Unsupervised Learning for Dense Crowd Counting (AAAI) [paper]
[GPC] Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation (IROS) [paper]
[PCC-Net] PCC Net: Perspective Crowd Counting via Spatial Convolutional Network (T-CSVT) [paper] [code]
[CLPC] Cross-Line Pedestrian Counting Based on Spatially-Consistent Two-Stage Local Crowd Density Estimation and Accumulation (T-CSVT) [paper]
[MAN] Mask-aware networks for crowd counting (T-CSVT) [paper]
[CCLL] Crowd Counting With Limited Labeling Through Submodular Frame Selection (T-ITS) [paper]
[ACSPNet] Atrous convolutions spatial pyramid network for crowd counting and density estimation (Neurocomputing) [paper]
[DDCN] Removing background interference for crowd counting via de-background detail convolutional network (Neurocomputing) [paper]
[MRA-CNN] Multi-resolution attention convolutional neural network for crowd counting (Neurocomputing) [paper]
[ACM-CNN] Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs (Neurocomputing) [paper]
[SDA-MCNN] Counting crowds using a scale-distribution-aware network and adaptive human-shaped kernel (Neurocomputing) [paper]
[SCAR] SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting (Neurocomputing) [paper][code]
[GMLCNN] Learning Multi-Level Density Maps for Crowd Counting (TNNLS) [paper]
[LDL] Indoor Crowd Counting by Mixture of Gaussians Label Distribution Learning (TIP) [paper]
[AM-CNN] Attention to Head Locations for Crowd Counting (ICIG) [paper]

2018

[SANet] Scale Aggregation Network for Accurate and Efficient Crowd Counting (ECCV) [paper]
[ic-CNN] Iterative Crowd Counting (ECCV) [paper]
[CL] Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds (ECCV) [paper]
[LCFCN] Where are the Blobs: Counting by Localization with Point Supervision (ECCV) [paper] [code]
[CSR] CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes (CVPR) [paper] [code]
[L2R] Leveraging Unlabeled Data for Crowd Counting by Learning to Rank (CVPR) [paper] [code]
[ACSCP] Crowd Counting via Adversarial Cross-Scale Consistency Pursuit (CVPR) [paper] [unofficial code: PyTorch]
[DecideNet] DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density (CVPR) [paper]
[AMDCN] An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting (CVPRW) [paper] [code]
[D-ConvNet] Crowd Counting with Deep Negative Correlation Learning (CVPR) [paper] [code]
[IG-CNN] Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN (CVPR) [paper]
[SCNet] In Defense of Single-column Networks for Crowd Counting (BMVC) [paper]
[AFP] Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid (BMVC) [paper]
[DRSAN] Crowd Counting using Deep Recurrent Spatial-Aware Network (IJCAI) [paper]
[TDF-CNN] Top-Down Feedback for Crowd Counting Convolutional Neural Network (AAAI) [paper]
[CAC] Class-Agnostic Counting (ACCV) [paper] [code]
[A-CCNN] A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting (ICIP) [paper]
Crowd Counting with Fully Convolutional Neural Network (ICIP) [paper]
[MS-GAN] Multi-scale Generative Adversarial Networks for Crowd Counting (ICPR) [paper]
[DR-ResNet] A Deeply-Recursive Convolutional Network for Crowd Counting (ICASSP) [paper]
[GAN-MTR] Crowd Counting With Minimal Data Using Generative Adversarial Networks For Multiple Target Regression (WACV) [paper]
[SaCNN] Crowd counting via scale-adaptive convolutional neural network (WACV) [paper] [code]
[Improved SaCNN] Improved Crowd Counting Method Based on Scale-Adaptive Convolutional Neural Network (IEEE Access) [paper]
[DA-Net] DA-Net: Learning the Fine-Grained Density Distribution With Deformation Aggregation Network (IEEE Access) [paper][code]
[BSAD] Body Structure Aware Deep Crowd Counting (TIP) [paper]
[NetVLAD] Multiscale Multitask Deep NetVLAD for Crowd Counting (TII) [paper] [code]
[W-VLAD] Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps (T-CSVT) [paper]

2017

[ACNN] Incorporating Side Information by Adaptive Convolution (NIPS) [paper][Project]
[CP-CNN] Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs (ICCV) [paper]
[ConvLSTM] Spatiotemporal Modeling for Crowd Counting in Videos (ICCV) [paper]
[CMTL] CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting (AVSS) [paper] [code]
[ResnetCrowd] ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification (AVSS) [paper]
[Switching CNN] Switching Convolutional Neural Network for Crowd Counting (CVPR) [paper] [code]
[DAL-SVR] Boosting deep attribute learning via support vector regression for fast moving crowd counting (PR Letters) [paper]
[MSCNN] Multi-scale Convolution Neural Networks for Crowd Counting (ICIP) [paper] [code]
[FCNCC] Fully Convolutional Crowd Counting On Highly Congested Scenes (VISAPP) [paper]
[CNN-MRF] Image Crowd Counting Using Convolutional Neural Network and Markov Random Field (JACII) [paper] [code]

2016

[Hydra-CNN] Towards perspective-free object counting with deep learning (ECCV) [paper] [code]
[CNN-Boosting] Learning to Count with CNN Boosting (ECCV) [paper]
[Crossing-line] Crossing-line Crowd Counting with Two-phase Deep Neural Networks (ECCV) [paper]
[GP] Gaussian Process Density Counting from Weak Supervision (ECCV) [paper]
[CrowdNet] CrowdNet: A Deep Convolutional Network for Dense Crowd Counting (ACMMM) [paper] [code]
[MCNN] Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (CVPR) [paper] [unofficial code: TensorFlow PyTorch]
[Shang 2016] End-to-end crowd counting via joint learning local and global count (ICIP) [paper]
[DE-VOC] Fast visual object counting via example-based density estimation (ICIP) [paper]
[RPF] Crowd Density Estimation based on Rich Features and Random Projection Forest (WACV) [paper]
[CS-SLR] Cost-sensitive sparse linear regression for crowd counting with imbalanced training data (ICME) [paper]
[Faster-OHEM-KCF] Deep People Counting with Faster R-CNN and Correlation Tracking (ICME) [paper]

2015

[COUNT Forest] COUNT Forest: CO-voting Uncertain Number of Targets using Random Forest for Crowd Density Estimation (ICCV) [paper]
[Bayesian] Bayesian Model Adaptation for Crowd Counts (ICCV) [paper]
[Zhang 2015] Cross-scene Crowd Counting via Deep Convolutional Neural Networks (CVPR) [paper] [code]
[Wang 2015] Deep People Counting in Extremely Dense Crowds (ACMMM) [paper]
[FU 2015] Fast crowd density estimation with convolutional neural networks (Artificial Intelligence) [paper]

2014

[Arteta 2014] Interactive Object Counting (ECCV) [paper]

2013

[Idrees 2013] Multi-Source Multi-Scale Counting in Extremely Dense Crowd Images (CVPR) [paper]
[Ma 2013] Crossing the Line: Crowd Counting by Integer Programming with Local Features (CVPR) [paper]
[Chen 2013] Cumulative Attribute Space for Age and Crowd Density Estimation (CVPR) [paper]
[SSR] From Semi-Supervised to Transfer Counting of Crowds (ICCV) [paper]

2012

[Chen 2012] Feature mining for localised crowd counting (BMVC) [paper]

2011

[Rodriguez 2011] Density-aware person detection and tracking in crowds (ICCV) [paper]

2010

[Lempitsky 2010] Learning To Count Objects in Images (NeurIPS) [paper]

2008

[Chan 2008] Privacy preserving crowd monitoring: Counting people without people models or tracking (CVPR) [paper]

Leaderboard

The section is being continually updated. Note that some values have superscript, which indicates their source.

NWPU

Year-Conference/Journal	Methods	Val-MAE	Val-MSE	Test-MAE	Test-MSE	Test-NAE	Backbone
2016--CVPR	MCNN	218.5	700.6	232.5	714.6	1.063	FS
2018--CVPR	CSRNet	104.8	433.4	121.3	387.8	0.604	VGG-16
2019--CSVT	PCC-Net	100.7	573.1	112.3	457.0	0.251	VGG-16
2019--CVPR	CAN	93.5	489.9	106.3	386.5	0.295	VGG-16
2019--NC	SCAR	81.5	397.9	110.0	495.3	0.288	VGG-16
2019--ICCV	BL	93.6	470.3	105.4	454.2	0.203	VGG-19
2019--CVPR	SFCN	95.4	608.3	105.4	424.1	0.254	ResNet-101
2020--NeurIPS	DM-Count	70.5	357.6	88.4	388.6	0.169	VGG-19

ShanghaiTech Part A

Year-Conference/Journal	Methods	MAE	MSE	PSNR	SSIM	Params	Pre-trained Model
2016--CVPR	MCNN	110.2	173.2	21.4^CSR	0.52^CSR	0.13M^SANet	None
2017--AVSS	CMTL	101.3	152.4	-	-	-	None
2017--CVPR	Switching CNN	90.4	135.0	-	-	15.11M^SANet	VGG-16
2017--ICIP	MSCNN	83.8	127.4	-	-	-	-
2017--ICCV	CP-CNN	73.6	106.4	21.72^CP-CNN	0.72^CP-CNN	68.4M^SANet	-
2018--AAAI	TDF-CNN	97.5	145.1	-	-	-	-
2018--WACV	SaCNN	86.8	139.2	-	-	-	-
2018--CVPR	ACSCP	75.7	102.7	-	-	5.1M	None
2018--CVPR	D-ConvNet-v1	73.5	112.3	-	-	-	VGG-16
2018--CVPR	IG-CNN	72.5	118.2	-	-	-	VGG-16
2018--CVPR	L2R (Multi-task, Query-by-example)	72.0	106.6	-	-	-	VGG-16
2018--CVPR	L2R (Multi-task, Keyword)	73.6	112.0	-	-	-	VGG-16
2019--CVPRW	GSP (one stage, efficient)	70.7	103.6	-	-	-	VGG-16
2018--IJCAI	DRSAN	69.3	96.4	-	-	-	-
2018--ECCV	ic-CNN (one stage)	69.8	117.3	-	-	-	-
2018--ECCV	ic-CNN (two stages)	68.5	116.2	-	-	-	-
2018--CVPR	CSRNet	68.2	115.0	23.79	0.76	16.26M^SANet	VGG-16
2018--ECCV	SANet	67.0	104.5	-	-	0.91M	None
2019--AAAI	GWTA-CCNN	154.7	229.4	-	-	-	-
2019--ICASSP	ASD	65.6	98.0	-	-	-	-
2019--ICCV	CFF	65.2	109.4	25.4	0.78	-	-
2019--CVPR	SFCN	64.8	107.5	-	-	-	-
2020--AAAI	DUBNet	64.6	106.8	-	-	-	-
2019--ICCV	SPN+L2SM	64.2	98.4	-	-	-	-
2019--CVPR	TEDnet	64.2	109.1	25.88	0.83	1.63M	-
2019--CVPR	ADCrowdNet(AMG-bAttn-DME)	63.2	98.9	24.48	0.88	-	-
2019--CVPR	PACNN	66.3	106.4	-	-	-	-
2019--CVPR	PACNN+CSRNet	62.4	102.0	-	-	-	-
2019--CVPR	CAN	62.3	100.0	-	-	-	VGG-16
2019--TIP	HA-CCN	62.9	94.9	-	-	-	-
2019--ICCV	BL	62.8	101.8	-	-	-	-
2019--WACV	SPN	61.7	99.5	-	-	-	-
2019--ICCV	DSSINet	60.63	96.04	-	-	-	-
2019--ICCV	MBTTBF-SCFB	60.2	94.1	-	-	-	-
2019--ICCV	RANet	59.4	102.0	-	-	-	-
2019--ICCV	SPANet+SANet	59.4	92.5	-	-	-	-
2019--TIP	PaDNet	59.2	98.1	-	-	-	-
2019--ICCV	S-DCNet	58.3	95.0	-	-	-	-
2020--ICPR	M-SFANet+M-SegNet	57.55	94.48	-	-	-	-
2019--ICCV	PGCNet	57.0	86.0	-	-	-	-
2020--ECCV	AMSNet	56.7	93.4	-	-	-	-
2020--CVPR	ADSCNet	55.4	97.7	-	-	-	-
2021--AAAI	SASNet	53.59	88.38	-	-	-	-
2022--TIP	AGCCM	52.75	85.5	-	-	-	-
2022--ICVRV	LSPL	50.41	81.9	-	-	-	-

ShanghaiTech Part B

Year-Conference/Journal	Methods	MAE	MSE
2016--CVPR	MCNN	26.4	41.3
2017--ICIP	MSCNN	17.7	30.2
2017--AVSS	CMTL	20.0	31.1
2017--CVPR	Switching CNN	21.6	33.4
2017--ICCV	CP-CNN	20.1	30.1
2018--TIP	BSAD	20.2	35.6
2018--WACV	SaCNN	16.2	25.8
2018--CVPR	ACSCP	17.2	27.4
2018--CVPR	CSRNet	10.6	16.0
2018--CVPR	IG-CNN	13.6	21.1
2018--CVPR	D-ConvNet-v1	18.7	26.0
2018--CVPR	DecideNet	21.53	31.98
2018--CVPR	DecideNet + R3	20.75	29.42
2018--CVPR	L2R (Multi-task, Query-by-example)	14.4	23.8
2018--CVPR	L2R (Multi-task, Keyword)	13.7	21.4
2018--IJCAI	DRSAN	11.1	18.2
2018--AAAI	TDF-CNN	20.7	32.8
2018--ECCV	ic-CNN (one stage)	10.4	16.7
2018--ECCV	ic-CNN (two stages)	10.7	16.0
2019--CVPRW	GSP (one stage, efficient)	9.1	15.9
2018--ECCV	SANet	8.4	13.6
2019--WACV	SPN	9.4	14.4
2019--ICCV	PGCNet	8.8	13.7
2019--ICASSP	ASD	8.5	13.7
2019--CVPR	TEDnet	8.2	12.8
2019--TIP	HA-CCN	8.1	13.4
2019--TIP	PaDNet	8.1	12.2
2019--ICCV	RANet	7.9	12.9
2019--CVPR	CAN	7.8	12.2
2019--CVPR	ADCrowdNet(AMG-attn-DME)	7.7	12.9
2020--AAAI	DUBNet	7.7	12.5
2019--CVPR	ADCrowdNet(AMG-DME)	7.6	13.9
2019--CVPR	SFCN	7.6	13.0
2019--CVPR	PACNN	8.9	13.5
2019--CVPR	PACNN+CSRNet	7.6	11.8
2019--ICCV	BL	7.7	12.7
2019--ICCV	CFF	7.2	12.2
2019--ICCV	SPN+L2SM	7.2	11.1
2019--ICCV	DSSINet	6.85	10.34
2019--ICCV	S-DCNet	6.7	10.7
2019--ICCV	SPANet+SANet	6.5	9.9
2020--CVPR	ADSCNet	6.4	11.3
2020--ICPR	M-SFANet+M-SegNet	6.32	10.06
2021--AAAI	SASNet	6.35	9.9
2021--AAAI	AGCCM	5.98	9.72
2021--AAAI	LSPL	5.96	9.78

UCF-QNRF

Year-Conference/Journal	Method	C-MAE	C-NAE	C-MSE	DM-MAE	DM-MSE	DM-HI	L- Av. Precision	L-Av. Recall	L-AUC
2013--CVPR	Idrees 2013^CL	315	0.63	508	-	-	-	-	-	-
2016--CVPR	MCNN^CL	277	0.55	426	0.006670	0.0223	0.5354	59.93%	63.50%	0.591
2017--AVSS	CMTL^CL	252	0.54	514	0.005932	0.0244	0.5024	-	-	-
2017--CVPR	Switching CNN^CL	228	0.44	445	0.005673	0.0263	0.5301	-	-	-
2018--ECCV	CL	132	0.26	191	0.00044	0.0017	0.9131	75.8%	59.75%	0.714
2019--TIP	HA-CCN	118.1	-	180.4	-	-	-	-	-	-
2019--CVPR	TEDnet	113	-	188	-	-	-	-	-	-
2019--ICCV	RANet	111	-	190	-	-	-	-	-	-
2019--CVPR	CAN	107	-	183	-	-	-	-	-	-
2020--AAAI	DUBNet	105.6	-	180.5	-	-	-	-	-	-
2019--ICCV	SPN+L2SM	104.7	-	173.6	-	-	-	-	-	-
2019--ICCV	S-DCNet	104.4	-	176.1	-	-	-	-	-	-
2019--CVPR	SFCN	102.0	-	171.4	-	-	-	-	-	-
2019--ICCV	DSSINet	99.1	-	159.2	-	-	-	-	-	-
2019--ICCV	MBTTBF-SCFB	97.5	-	165.2	-	-	-	-	-	-
2019--TIP	PaDNet	96.5	-	170.2	-	-	-	-	-	-
2019--ICCV	BL	88.7	-	154.8	-	-	-	-	-	-
2020--ICPR	M-SFANet	85.6	-	151.23	-	-	-	-	-	-
2021--AAAI	SASNet	85.2	-	147.3	-	-	-	-	-	-
2020--CVPR	ADSCNet	71.3	-	132.5	-	-	-	-	-	-

UCF_CC_50

Year-Conference/Journal	Methods	MAE	MSE
2013--CVPR	Idrees 2013	468.0	590.3
2015--CVPR	Zhang 2015	467.0	498.5
2016--ACM MM	CrowdNet	452.5	-
2016--CVPR	MCNN	377.6	509.1
2016--ECCV	CNN-Boosting	364.4	-
2016--ECCV	Hydra-CNN	333.73	425.26
2016--ICIP	Shang 2016	270.3	-
2017--ICIP	MSCNN	363.7	468.4
2017--AVSS	CMTL	322.8	397.9
2017--CVPR	Switching CNN	318.1	439.2
2017--ICCV	CP-CNN	298.8	320.9
2017--ICCV	ConvLSTM-nt	284.5	297.1
2018--TIP	BSAD	409.5	563.7
2018--AAAI	TDF-CNN	354.7	491.4
2018--WACV	SaCNN	314.9	424.8
2018--CVPR	IG-CNN	291.4	349.4
2018--CVPR	ACSCP	291.0	404.6
2018--CVPR	L2R (Multi-task, Query-by-example)	291.5	397.6
2018--CVPR	L2R (Multi-task, Keyword)	279.6	388.9
2018--CVPR	D-ConvNet-v1	288.4	404.7
2018--CVPR	CSRNet	266.1	397.5
2018--ECCV	ic-CNN (two stages)	260.9	365.5
2018--ECCV	SANet	258.4	334.9
2018--IJCAI	DRSAN	219.2	250.2
2019--AAAI	GWTA-CCNN	433.7	583.3
2019--WACV	SPN	259.2	335.9
2019--CVPR	ADCrowdNet(DME)	257.1	363.5
2019--TIP	HA-CCN	256.2	348.4
2019--CVPR	TEDnet	249.4	354.5
2019--CVPR	PACNN	267.9	357.8
2020--AAAI	DUBNet	243.8	329.3
2019--CVPR	PACNN+CSRNet	241.7	320.7
2019--ICCV	RANet	239.8	319.4
2019--ICCV	MBTTBF-SCFB	233.1	300.9
2019--ICCV	BL	229.3	308.2
2019--ICCV	DSSINet	216.9	302.4
2019--CVPR	SFCN	214.2	318.2
2019--CVPR	CAN	212.2	243.7
2019--ICCV	S-DCNet	204.2	301.3
2019--ICASSP	ASD	196.2	270.9
2019--ICCV	SPN+L2SM	188.4	315.3
2019--TIP	PaDNet	185.8	278.3
2020--ICPR	M-SFANet	162.33	276.76
2021--AAAI	SASNet	161.4	234.46

WorldExpo'10

Year-Conference/Journal	Method	S1	S2	S3	S4	S5	Avg.
2015--CVPR	Zhang 2015	9.8	14.1	14.3	22.2	3.7	12.9
2016--CVPR	MCNN	3.4	20.6	12.9	13.0	8.1	11.6
2017--ICIP	MSCNN	7.8	15.4	14.9	11.8	5.8	11.7
2017--ICCV	ConvLSTM-nt	8.6	16.9	14.6	15.4	4.0	11.9
2017--ICCV	ConvLSTM	7.1	15.2	15.2	13.9	3.5	10.9
2017--ICCV	Bidirectional ConvLSTM	6.8	14.5	14.9	13.5	3.1	10.6
2017--CVPR	Switching CNN	4.4	15.7	10.0	11.0	5.9	9.4
2017--ICCV	CP-CNN	2.9	14.7	10.5	10.4	5.8	8.86
2018--AAAI	TDF-CNN	2.7	23.4	10.7	17.6	3.3	11.5
2018--CVPR	IG-CNN	2.6	16.1	10.15	20.2	7.6	11.3
2018--TIP	BSAD	4.1	21.7	11.9	11.0	3.5	10.5
2018--ECCV	ic-CNN	17.0	12.3	9.2	8.1	4.7	10.3
2018--CVPR	DecideNet	2.0	13.14	8.9	17.4	4.75	9.23
2018--CVPR	D-ConvNet-v1	1.9	12.1	20.7	8.3	2.6	9.1
2018--CVPR	CSRNet	2.9	11.5	8.6	16.6	3.4	8.6
2018--WACV	SaCNN	2.6	13.5	10.6	12.5	3.3	8.5
2018--ECCV	SANet	2.6	13.2	9.0	13.3	3.0	8.2
2018--IJCAI	DRSAN	2.6	11.8	10.3	10.4	3.7	7.76
2018--CVPR	ACSCP	2.8	14.05	9.6	8.1	2.9	7.5
2019--ICCV	PGCNet	2.5	12.7	8.4	13.7	3.2	8.1
2019--CVPR	TEDnet	2.3	10.1	11.3	13.8	2.6	8.0
2019--CVPR	PACNN	2.3	12.5	9.1	11.2	3.8	7.8
2019--CVPR	ADCrowdNet(AMG-bAttn-DME)	1.7	14.4	11.5	7.9	3.0	7.7
2019--CVPR	ADCrowdNet(AMG-attn-DME)	1.6	13.2	8.7	10.6	2.6	7.3
2019--CVPR	CAN	2.9	12.0	10.0	7.9	4.3	7.4
2019--CVPR	CAN(ECAN)	2.4	9.4	8.8	11.2	4.0	7.2
2019--ICCV	DSSINet	1.57	9.51	9.46	10.35	2.49	6.67
2020--ICPR	M-SFANet	1.88	13.24	10.07	7.5	3.87	7.32
2020--CVPR	ASNet	2.22	10.11	8.89	7.14	4.84	6.64
2021--AAAI	SASNet	1.134	13.24	7.68	7.61	2.07	5.71

UCSD

Year-Conference/Journal	Method	MAE	MSE
2015--CVPR	Zhang 2015	1.60	3.31
2016--ECCV	Hydra-CNN	1.65	-
2016--ECCV	CNN-Boosting	1.10	-
2016--CVPR	MCNN	1.07	1.35
2017--ICCV	ConvLSTM-nt	1.73	3.52
2017--CVPR	Switching CNN	1.62	2.10
2017--ICCV	ConvLSTM	1.30	1.79
2017--ICCV	Bidirectional ConvLSTM	1.13	1.43
2018--CVPR	CSRNet	1.16	1.47
2018--CVPR	ACSCP	1.04	1.35
2018--ECCV	SANet	1.02	1.29
2018--TIP	BSAD	1.00	1.40
2019--WACV	SPN	1.03	1.32
2019--ICCV	SPANet+SANet	1.00	1.28
2019--CVPR	ADCrowdNet(DME)	0.98	1.25
2019--BMVC	E3D	0.93	1.17
2019--CVPR	PACNN	0.89	1.18
2019--TIP	PaDNet	0.85	1.06

Mall

Year-Conference/Journal	Method	MAE	MSE
2012--BMVC	Chen 2012	3.15	15.7
2016--ECCV	CNN-Boosting	2.01	-
2017--ICCV	ConvLSTM-nt	2.53	11.2
2017--ICCV	ConvLSTM	2.24	8.5
2017--ICCV	Bidirectional ConvLSTM	2.10	7.6
2018--CVPR	DecideNet	1.52	1.90
2018--IJCAI	DRSAN	1.72	2.1
2019--BMVC	E3D	1.64	2.13
2019--WACV	SAAN	1.28	1.68

Name		Name	Last commit message	Last commit date
Latest commit History 522 Commits
src		src
README.md		README.md

LaiPiXiong/Awesome-Crowd-Counting

Folders and files

Latest commit

History

Repository files navigation