https://github.com/gjy3035/Awesome-Crowd-Counting
Awesome Crowd Counting
https://github.com/gjy3035/Awesome-Crowd-Counting
List: Awesome-Crowd-Counting
computer-vision crowd-analysis crowd-counting
Last synced: about 1 year ago
JSON representation
Awesome Crowd Counting
- Host: GitHub
- URL: https://github.com/gjy3035/Awesome-Crowd-Counting
- Owner: gjy3035
- Created: 2018-04-25T09:01:25.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2024-05-21T13:50:26.000Z (about 2 years ago)
- Last Synced: 2024-05-21T15:08:55.106Z (about 2 years ago)
- Topics: computer-vision, crowd-analysis, crowd-counting
- Size: 1.09 MB
- Stars: 2,310
- Watchers: 103
- Forks: 468
- Open Issues: 16
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesomeai - Crowd Counting
- awesome-ai-awesomeness - Crowd Counting
- awesome-ai-awesomeness - Crowd Counting
- awesome-ai-list-guide - Awesome-Crowd-Counting
- Awesome-Visual-Transformer - Awesome-Crowd-Counting
- Awesome-Crowd-Localization - Crowd Counting
- ultimate-awesome - Awesome-Crowd-Counting - Awesome Crowd Counting. (Other Lists / TeX Lists)
- Awesome-Computer-Vision - 21
- awesome-computer-vision-papers - awesome crowd counting
- awesome-artificial-intelligence-research - Awesome Crowd Counting - crowd counting papers and datasets. (Multimodal, Vision-Language, and Generative AI / Computer Vision)
README
# Awesome Crowd Counting[](https://awesome.re)
If you have any problems, suggestions or improvements, please submit the issue or PR.
## Contents
* [Misc](#misc)
* [Datasets](#datasets)
* [Papers](#papers)
* [Leaderboard](#leaderboard)
## Misc
### News
- [2022.09] The VSCrowd Dataset is released.
- [2022.01] The FUDAN-UCC Dataset is released.
- [2021.04] The RGBT-CC Benchmark is released.
- [2020.04] The JHU-CROWD++ Dataset is released.
- [2020.01] The NWPU-Crowd benchmark is released.
### Call for Papers
- [Electronics] Special Issue on: Recent Advances in Pixel-Wise Image Understanding [[Link](https://www.mdpi.com/journal/electronics/special_issues/Pixel-Wise_Image_Understanding)]. Deadline: November 15, 2023.
- [Transportation Research Part C] ~~Special Issue on: Applications of artificial intelligence, computer vision, physics and econometrics modelling methods in pedestrian traffic modelling and crowd safety~~ [[Link](https://www.sciencedirect.com/journal/transportation-research-part-c-emerging-technologies/about/call-for-papers#call-for-papers-applications-of-artificial-intelligence-computer-vision-physics-and-econometrics-modelling-methods-in-pedestrian-traffic-modelling-and-crowd-safety)]. Deadline: April 30th, 2023.
- [IET Image Processing] ~~Special Issue on: Crowd Understanding and Analysis~~ [[Link](https://digital-library.theiet.org/content/journals/iet-ipr/info/spl-issues;jsessionid=rfnb4mhi25p6.x-iet-live-01)] [[PDF](https://digital-library.theiet.org/files/IET_IPR_CFP_CUA.pdf)]
### Challenge
- [[NWPU-Crowd Counting](https://www.crowdbenchmark.com/nwpucrowd.html)] Crowd counting. Deadline: none.
- [[VisDrone 2021](http://aiskyeye.com/challenge_2021/crowd-counting-2/)] ~~Crowd counting. ICCV Workshop. Deadline: **2021.07.15**.~~
- [[VisDrone 2020](http://aiskyeye.com/challenge/crowd-counting/)] ~~Crowd counting. ECCV Workshop. Deadline: **2020.07.15**.~~
### Code
- [[C^3 Framework](https://github.com/gjy3035/C-3-Framework)] An open-source PyTorch code for crowd counting, which is released. 
- [[CCLabeler](https://github.com/Elin24/cclabeler)] A web tool for labeling pedestrians in an image, which is released. 
- [[YOLO-CROWD](https://github.com/zaki1003/YOLO-CROWD)]  a lightweight crowd counting and face detection model that is based on [[YOLO-FaceV2](https://github.com/Krasjet-Yu/YOLO-FaceV2)] 
### Technical blog
- [Chinese Blog] 人群计数论文解读 [[Link](https://zhuanlan.zhihu.com/c_1111215695622352896)]
- [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](https://zhuanlan.zhihu.com/p/65650998)]
- [2019.04] Crowd counting from scratch [[Link](https://github.com/CommissarMa/Crowd_counting_from_scratch)]
- [2017.11] Counting Crowds and Lines with AI [[Link1](https://blog.dimroc.com/2017/11/19/counting-crowds-and-lines/)] [[Link2](https://count.dimroc.com/)] [[Code](https://github.com/dimroc/count)]
### GT generation
- Density Map Generation from Key Points [[Matlab Code](https://github.com/aachenhang/crowdcount-mcnn/tree/master/data_preparation)] [[Python Code](https://github.com/leeyeehoo/CSRNet-pytorch/blob/master/make_dataset.ipynb)] [[Fast Python Code](https://github.com/vlad3996/computing-density-maps)] [[Pytorch CUDA Code](https://github.com/gjy3035/NWPU-Crowd-Sample-Code/blob/master/misc/dot_ops.py)]
### Related Tasks
Crowd Analysis, [Crowd Localization](https://github.com/taohan10200/Awesome-Crowd-Localization), [Video Surveillance](https://github.com/CommissarMa/Awesome-Public-Safety-in-Vision), Dense/Small/Tiny Object Detection
## Datasets
Please refer to [this page](src/Datasets.md).
## 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**](src/Top_Conference-Journal.md)] | [[**Survey**](src/Survey.md)] | [[**Un-/semi-/weakly-/self- Supervised Learning**](src/Un-_Semi-_Weakly-_Self-_supervised_Learning.md)] |
| :---- | :---- | :---- |
| [[**Auxiliary Tasks**](src/Auxiliary_Tasks.md)] | [[**Localization**](src/Localization.md)] | [[**Transfer Learning and Domain Adaptation**](src/Transfer_Learning_and_Domain_Adaptation.md)] |
| [[**Light-weight Models**](src/Light-weight_Model.md)] | [[**Video**](src/Video.md)] | [[**Network Design, Search**](src/Network_Design_and_Search.md)] |
| [[**Perspective Map**](src/Perspective_Map.md)] | [[**Attention**](src/Attention.md)] | [[**Transformer**](src/Transformer.md)] |
### arXiv papers
Note that all unpublished arXiv papers are not included in [the leaderboard of performance](#performance).
- Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark [[paper](https://arxiv.org/abs/2411.13056)]
- Bound Tightening Network for Robust Crowd Counting [[paper](https://arxiv.org/abs/2409.19146)]
- Boosting Adverse Weather Crowd Counting via Multi-queue Contrastive Learning [[paper](https://arxiv.org/abs/2408.05956)]
- VMambaCC: A Visual State Space Model for Crowd Counting [[paper](https://arxiv.org/abs/2405.03978)]
- Fuss-Free Network: A Simplified and Efficient Neural Network for Crowd Counting [[paper](https://arxiv.org/abs/2404.07847)]
- CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification [[paper](https://arxiv.org/abs/2403.09281v1)][[code](https://github.com/Yiming-M/CLIP-EBC)] 
- Robust Unsupervised Crowd Counting and Localization with Adaptive Resolution SAM [[paper](https://arxiv.org/abs/2402.17514)]
- Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling [[paper](https://arxiv.org/abs/2402.15297)]
- Diffusion-based Data Augmentation for Object Counting Problems [[paper](https://arxiv.org/abs/2401.13992)]
- A Lightweight Feature Fusion Architecture For Resource-Constrained Crowd Counting [[paper](https://arxiv.org/abs/2401.05968)]
- Scale-Aware Crowd Count Network with Annotation Error Correction [[paper](https://arxiv.org/abs/2312.16771)]
- SYRAC: Synthesize, Rank, and Count [[paper](https://arxiv.org/abs/2310.01662)]
- Accurate Gigapixel Crowd Counting by Iterative Zooming and Refinement [[paper](https://arxiv.org/abs/2305.09271)]
- CLIP-Count: Towards Text-Guided Zero-Shot Object Counting [[paper](https://arxiv.org/abs/2305.07304)]
- Can SAM Count Anything? An Empirical Study on SAM Counting [[paper](https://arxiv.org/abs/2304.10817)]
- Why Existing Multimodal Crowd Counting Datasets Can Lead to Unfulfilled Expectations in Real-World Applications [[paper](https://arxiv.org/abs/2304.06401)]
- Crowd Counting with Sparse Annotation [[paper](https://arxiv.org/abs/2304.06021)]
- Crowd Counting with Online Knowledge Learning [[paper](https://arxiv.org/abs/2303.10318)]
- LCDnet: A Lightweight Crowd Density Estimation Model for Real-time Video Surveillance [[paper](https://arxiv.org/abs/2302.05374)]
- Mask Focal Loss for dense crowd counting with canonical object detection networks [[paper](https://arxiv.org/abs/2212.11542)]
- CountingMOT: Joint Counting, Detection and Re-Identification for Multiple Object Tracking [[paper](https://arxiv.org/abs/2212.05861)]
- Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects [[paper](https://arxiv.org/abs/2212.02248)]
Earlier ArXiv Papers
- Scale-Aware Crowd Counting Using a Joint Likelihood Density Map and Synthetic Fusion Pyramid Network [[paper](https://arxiv.org/abs/2211.06835)]
- Inception-Based Crowd Counting -- Being Fast while Remaining Accurate [[paper](https://arxiv.org/abs/2210.09796)]
- Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training [[paper](https://arxiv.org/abs/2208.07075)]
- MAFNet: A Multi-Attention Fusion Network for RGB-T Crowd Counting [[paper](https://arxiv.org/abs/2208.06761)]
- Multi-scale Feature Aggregation for Crowd Counting [[paper](https://arxiv.org/abs/2208.05256)]
- Analysis of the Effect of Low-Overhead Lossy Image Compression on the Performance of Visual Crowd Counting for Smart City Applications [[paper](https://arxiv.org/abs/2207.10155)]
- Indirect-Instant Attention Optimization for Crowd Counting in Dense Scenes [[paper](https://arxiv.org/abs/2206.05648)]
- Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd Counting [[paper](https://arxiv.org/abs/2206.05475)]
- Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches [[paper](https://arxiv.org/abs/2204.04653)]
- Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting [[paper](https://arxiv.org/abs/2203.06388)]
- Counting with Adaptive Auxiliary Learning [[paper](https://arxiv.org/abs/2203.04061)][[code](https://github.com/smallmax00/Counting_With_Adaptive_Auxiliary_Learning)]
- CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizability [[paper](https://arxiv.org/abs/2203.03768)]
- S2FPR: Crowd Counting via Self-Supervised Coarse to Fine Feature Pyramid Ranking [[paper](https://arxiv.org/abs/2201.04819)][[code](https://github.com/bridgeqiqi/S2FPR)]
- Scene-Adaptive Attention Network for Crowd Counting [[paper](https://arxiv.org/abs/2112.15509)]
- Object Counting: You Only Need to Look at One [[paper](https://arxiv.org/abs/2112.05993)]
- PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting [[paper](https://arxiv.org/abs/2111.00406)]
- LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds [[paper](https://arxiv.org/abs/2110.04727)]
- CCTrans: Simplifying and Improving Crowd Counting with Transformer [[paper](https://arxiv.org/abs/2109.14483)]
- S4-Crowd: Semi-Supervised Learning with Self-Supervised Regularisation for Crowd Counting [[paper](https://arxiv.org/abs/2108.13969)]
- Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation [[paper](https://arxiv.org/abs/2108.02980)]
- Reducing Spatial Labeling Redundancy for Semi-supervised Crowd Counting [[paper](https://arxiv.org/abs/2108.02970)]
- Multi-Level Attentive Convoluntional Neural Network for Crowd Counting [[paper](https://arxiv.org/abs/2105.11422)]
- Boosting Crowd Counting with Transformers [[paper](https://arxiv.org/abs/2105.10926)]
- Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification [[paper](https://arxiv.org/abs/2105.09684)]
- WheatNet: A Lightweight Convolutional Neural Network for High-throughput Image-based Wheat Head Detection and Counting [[paper](https://arxiv.org/abs/2103.09408)]
- Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting [[paper](https://arxiv.org/abs/2104.13946)]
- Multi-channel Deep Supervision for Crowd Counting [[paper](https://arxiv.org/abs/2103.09553)]
- Enhanced Information Fusion Network for Crowd Counting [[paper](https://arxiv.org/abs/2101.01479)]
- Scale-Aware Network with Regional and Semantic Attentions for Crowd Counting under Cluttered Background [[paper](https://arxiv.org/abs/2101.04279)]
- Learning Independent Instance Maps for Crowd Localization [[paper](https://arxiv.org/abs/2012.04164)] [[code](https://github.com/taohan10200/IIM)]
- A Strong Baseline for Crowd Counting and Unsupervised People Localization [[paper](https://arxiv.org/abs/2011.03725)]
- A Study of Human Gaze Behavior During Visual Crowd Counting [[paper](https://arxiv.org/abs/2009.06502)]
- Bayesian Multi Scale Neural Network for Crowd Counting [[paper](https://arxiv.org/abs/2007.14245)]
- Dense Crowds Detection and Counting with a Lightweight Architecture [[paper](https://arxiv.org/abs/2007.06630)]
- Exploit the potential of Multi-column architecture for Crowd Counting [[paper](https://arxiv.org/abs/2007.05779)][[code](https://github.com/JunhaoCheng/Pyramid_Scale_Network)]
- Recurrent Distillation based Crowd Counting [[paper](https://arxiv.org/abs/2006.07755)]
- Ambient Sound Helps: Audiovisual Crowd Counting in Extreme Conditions [[paper](https://arxiv.org/abs/2005.07097)][[code](https://github.com/qingzwang/AudioVisualCrowdCounting)]
- CNN-based Density Estimation and Crowd Counting: A Survey [[paper](https://arxiv.org/abs/2003.12783)]
- Drone Based RGBT Vehicle Detection and Counting: A Challenge [[paper](https://arxiv.org/abs/2003.02437)]
- Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network [[paper](https://arxiv.org/abs/1912.01811)][[code](https://github.com/VisDrone)]
- Using Depth for Pixel-Wise Detection of Adversarial Attacks in Crowd Counting [[paper](https://arxiv.org/abs/1911.11484)]
- Content-aware Density Map for Crowd Counting and Density Estimation [[paper](https://arxiv.org/abs/1906.07258)]
- Crowd Transformer Network [[paper](https://arxiv.org/abs/1904.02774)]
- W-Net: Reinforced U-Net for Density Map Estimation [[paper](https://arxiv.org/abs/1903.11249)][[code](https://github.com/ZhengPeng7/W-Net-Keras)]
- Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting [[paper](https://arxiv.org/abs/1902.01115)]
- Scale-Aware Attention Network for Crowd Counting [[paper](https://arxiv.org/abs/1901.06026)]
- Crowd Counting with Density Adaption Networks [[paper](https://arxiv.org/abs/1806.10040)]
- Improving Object Counting with Heatmap Regulation [[paper](https://arxiv.org/abs/1803.05494)][[code](https://github.com/littleaich/heatmap-regulation)]
- Structured Inhomogeneous Density Map Learning for Crowd Counting [[paper](https://arxiv.org/abs/1801.06642)]
## 2025
### Conference
- OmniCount: Multi-label Object Counting with Semantic-Geometric Priors (**AAAI**)[[paper](https://arxiv.org/abs/2403.05435)][[web](https://mondalanindya.github.io/OmniCount/)]
### 2024
### Conference
- Multi-view People Detection in Large Scenes via Supervised View-wise Contribution Weighting (**AAAI**)[[paper](https://arxiv.org/abs/2405.19943)][[code](https://github.com/zqyq/Multi-view-People-Detection-in-Large-Scenes-via-Supervised-View-wise-Contribution-Weighting)]
- Boosting Semi-supervised Crowd Counting with Scale-based Active Learning (**ACM MM**)[[paper](https://openreview.net/pdf?id=AXvAc3HQFl)]
- Domain-Agnostic Crowd Counting via Uncertainty-Guided Style Diversity Augmentation (**ACM MM**)[[paper](https://openreview.net/attachment?id=nFrcliTxAC&name=pdf)]
- **[ME]** Multi-modal Crowd Counting via Modal Emulation (**BMVC**)[[paper](https://arxiv.org/abs/2407.19491)][[code](https://github.com/Mr-Monday/Multi-modal-Crowd-Counting-via-Modal-Emulation)]
- **[BM]** Multi-modal Crowd Counting via a Broker Modality (**ECCV**)[[paper](https://arxiv.org/abs/2407.07518)][[code](https://github.com/HenryCilence/Broker-Modality-Crowd-Counting)]
- **[CountFormer]** CountFormer: Multi-View Crowd Counting Transformer (**ECCV**)[[paper](https://arxiv.org/abs/2407.02047)]
- **[APGCC]** Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance (**ECCV**)[[paper](https://arxiv.org/abs/2405.10589)][[code](https://github.com/AaronCIH/APGCC)]
- **[OALNet]** Few-shot Class-agnostic Counting with Occlusion Augmentation and Localization (**ISCAS**)[[paper](https://ieeexplore.ieee.org/document/10558069)]
- **[WSCC_TAF]** Weakly-Supervised Crowd Counting with Token Attention and Fusion: A Simple and Effective Baseline (**ICASSP**) [[paper](https://ieeexplore.ieee.org/document/10446636)][[code](https://github.com/WangyiNTU/WSCC_TAF)]
- **[CrowdDiff]** CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models (**CVPR**) [[paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Ranasinghe_CrowdDiff_Multi-hypothesis_Crowd_Density_Estimation_using_Diffusion_Models_CVPR_2024_paper.pdf)][[code](https://github.com/dylran/crowddiff)]
- **[PseCo]** Point, Segment and Count: A Generalized Framework for Object Counting [[paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Huang_Point_Segment_and_Count_A_Generalized_Framework_for_Object_Counting_CVPR_2024_paper.pdf)][[code](https://github.com/Hzzone/PseCo)]
- **[mPrompt]** Regressor-Segmenter Mutual Prompt Learning for Crowd Counting (**CVPR**) [[paper](https://arxiv.org/abs/2312.01711)]
- **[MPCount]** Single Domain Generalization for Crowd Counting (**CVPR**) [[paper](https://arxiv.org/abs/2403.09124)][[code](https://github.com/Shimmer93/MPCount)]
- **[Gramformer]** Gramformer: Learning Crowd Counting via Graph-Modulated Transformer (**AAAI**) [[paper](https://arxiv.org/abs/2401.03870)][[code](https://github.com/LoraLinH/Gramformer)]
- **[SRN]** Glance To Count: Learning To Rank With Anchors for Weakly-Supervised Crowd Counting (**WACV**)[[paper](https://openaccess.thecvf.com/content/WACV2024/papers/Xiong_Glance_To_Count_Learning_To_Rank_With_Anchors_for_Weakly-Supervised_WACV_2024_paper.pdf)][[code](https://github.com/pandaszzzzz/CCRanking)]
- **[SAM]** Training-free Object Counting with Prompts (**WACV**)[[paper](https://openaccess.thecvf.com/content/WACV2024/papers/Shi_Training-Free_Object_Counting_With_Prompts_WACV_2024_paper.pdf)][[code](https://github.com/shizenglin/training-free-object-counter)]
- **[SGA]** Semantic Generative Augmentations for Few-Shot Counting (**WACV**)[[paper](https://openaccess.thecvf.com/content/WACV2024/papers/Doubinsky_Semantic_Generative_Augmentations_for_Few-Shot_Counting_WACV_2024_paper.pdf)]
### Journal
- **[Multimodal-SDA]** A three-stream fusion and self-differential attention network for multi-modal crowd counting (**Pattern Recognition Letters**) [[paper](https://www.sciencedirect.com/science/article/pii/S016786552400134X)]
- Focus for Free in Density-Based Counting (**IJCV**) [[paper](https://arxiv.org/abs/2306.05129)][[code](https://github.com/shizenglin/Counting-with-Focus-for-Free)] (extension of [CFF](#CFF))
- **[MDKNet]** Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting (**T-NNLS**) [[paper](https://arxiv.org/abs/2402.03758)][[code](https://github.com/csguomy/MDKNet)]
- Rethinking Global Context in Crowd Counting (**MIR**) [[paper](https://link.springer.com/article/10.1007/s11633-023-1475-z)]
- **[HPS]** Hybrid Perturbation Strategy for Semi-Supervised Crowd Counting (**TIP**) [[paper](https://arxiv.org/abs/2402.03758)]
- **[LDFNet]** Learning Discriminative Features for Crowd Counting (**TIP**) [[paper](https://arxiv.org/abs/2311.04509)]
- **[HKINet]** Hierarchical Kernel Interaction Network for Remote Sensing Object Counting (**TGRS**) [[paper](https://ieeexplore.ieee.org/abstract/document/10397559)]
- **[MRC-Crowd]** Semi-Supervised Crowd Counting with Contextual Modeling: Facilitating Holistic Understanding of Crowd Scenes (**T-CSVT**) [[paper](https://arxiv.org/abs/2310.10352)][[code](https://github.com/cha15yq/MRC-Crowd)]
- **[GCNet]** GCNet: Probing Self-Similarity Learning for Generalized Counting Network (**Pattern Recognition**) [[paper](https://arxiv.org/abs/2302.05132)]
### 2023
### Conference
- **[Crowd-Hat]** Boosting Detection in Crowd Analysis via Underutilized Output Features (**CVPR**)[[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Boosting_Detection_in_Crowd_Analysis_via_Underutilized_Output_Features_CVPR_2023_paper.pdf)][[code](https://github.com/wskingdom/Crowd-Hat)]
- **[STEERER]** STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning (**ICCV**)[[paper](https://arxiv.org/abs/2308.10468)][[code](https://github.com/taohan10200/STEERER)]
- **[PET]** Point-Query Quadtree for Crowd Counting, Localization, and More (**ICCV**)[[paper](https://arxiv.org/abs/2308.13814)][[code](https://github.com/cxliu0/PET)]
- Striking a Balance: Unsupervised Cross-Domain Crowd Counting via Knowledge Diffusion (**ACM MM**)[[paper](http://aim-nercms.whu.edu.cn/news/list-39.html)]
- **[AWCC-Net]** Counting Crowds in Bad Weather (**ICCV**)[[paper](https://arxiv.org/abs/2306.01209)][[code](https://github.com/awccnet/AWCC-Net)]
- **[CU]** Calibrating Uncertainty for Semi-Supervised Crowd Counting (**ICCV**)[[paper](https://arxiv.org/abs/2308.09887)][[code](https://github.com/superlc1995/Calibrating_count)]
- **[DAOT]** DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting (**ACM MM**)[[paper](https://arxiv.org/abs/2308.05311)]
- **[ZSC]** Zero-shot Object Counting (**CVPR**)[[paper](https://arxiv.org/abs/2303.02001)][[code](https://github.com/cvlab-stonybrook/zero-shot-counting)]
- **[DDC]** Diffuse-Denoise-Count: Accurate Crowd-Counting with Diffusion Models (**CVPR**)[[paper](https://arxiv.org/abs/2303.12790)][[code](https://github.com/dylran/DiffuseDenoiseCount)]
- **[IOCFormer]** Indiscernible Object Counting in Underwater Scenes (**CVPR**)[[paper](http://arxiv.org/abs/2304.11677)][[code](https://github.com/GuoleiSun/Indiscernible-Object-Counting)]
- **[CrowdCLIP]** CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model (**CVPR**)[[paper](https://arxiv.org/abs/2304.04231)]
- **[OT-M]** Optimal Transport Minimization: Crowd Localization on Density Maps for Semi-Supervised Counting (**CVPR**)[[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Optimal_Transport_Minimization_Crowd_Localization_on_Density_Maps_for_Semi-Supervised_CVPR_2023_paper.pdf)][[code](https://github.com/Elin24/OT-M)]
- **[DGCC]** Domain-general Crowd Counting in Unseen Scenarios (**AAAI**)[[paper](https://arxiv.org/abs/2212.02573)] [[code](https://github.com/ZPDu/Domain-general-Crowd-Counting-in-Unseen-Scenarios)]
- **[SAFECount]** Few-Shot Object Counting With Similarity-Aware Feature Enhancement (**WACV**)[[paper](https://arxiv.org/abs/2201.08959)] [[code](https://github.com/zhiyuanyou/SAFECount)]
- **[DMCNet]** Dynamic Mixture of Counter Network for Location-Agnostic Crowd Counting (**WACV**)[[paper](https://openaccess.thecvf.com/content/WACV2023/papers/Wang_Dynamic_Mixture_of_Counter_Network_for_Location-Agnostic_Crowd_Counting_WACV_2023_paper.pdf)]
- **[CACC]** Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation (**ICME**)[[paper](https://arxiv.org/abs/2108.02980v1)]
- **[MSSRM]** Super-Resolution Information Enhancement For Crowd Counting (**ICASSP**)[[paper](https://arxiv.org/abs/2303.06925)] [[code](https://github.com/PRIS-CV/MSSRM)]
- **[CHS-Net]** Cross-head Supervision for Crowd Counting with Noisy Annotations (**ICASSP**)[[paper](https://arxiv.org/abs/2303.09245)] [[code](https://github.com/RaccoonDML/CHSNet)]
- **[Self-ONN]** DroneNet: Crowd Density Estimation using Self-ONNs for Drones (**CCNC**)[[paper](https://arxiv.org/abs/2211.07137)]
### Journal
- **[MDC]** Reducing Spatial Labeling Redundancy for Active Semi-supervised Crowd Counting (**T-PAMI**) [[paper](https://arxiv.org/abs/2108.02970)]
- **[AGK]** Counting manatee aggregations using deep neural networks and Anisotropic Gaussian Kernel (**Scientific Reports-Nature**) [[paper](https://www.nature.com/articles/s41598-023-45507-3.epdf)] [[code](https://github.com/yeyimilk/deep-learning-for-manatee-counting)]
- **[GCFL]** Generalized Characteristic Function Loss for Crowd Analysis in the Frequency Domain (**T-PAMI**) [[paper]()]
- **[PESSNet]** A Perspective-Embedded Scale-Selection Network for Crowd Counting in Public Transportation (**T-ITS**) [[paper](https://ieeexplore.ieee.org/document/10311097)]
- **[MRL]** Semi-Supervised Crowd Counting via Multiple Representation Learning (**TIP**) [[paper](https://ieeexplore.ieee.org/document/10251149)]
- **[CDENet]** Confusion Region Mining for Crowd Counting (**T-NNLS**) [[paper](https://ieeexplore.ieee.org/document/10253468)]
- **[FLCC]** Federated Learning for Crowd Counting in Smart Surveillance Systems (**IEEE IoTJ**) [[paper](https://ieeexplore.ieee.org/document/10221866)]
- **[MGANet]** Crowd Counting Based on Multiscale Spatial Guided Perception Aggregation Network (**T-NNLS**) [[paper](https://ieeexplore.ieee.org/document/10227827)]
- **[HMoDE]** Redesigning Multi-Scale Neural Network for Crowd Counting (**TIP**) [[paper](https://arxiv.org/abs/2208.02894)][[code](https://github.com/ZPDu/Redesigning-Multi-Scale-Neural-Network-for-Crowd-Counting)]
- **[SS-DCNet]** From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting (**IJCV**) [[paper](https://link.springer.com/article/10.1007/s11263-023-01782-1)](extension of [S-DCNet](#S-DCNet))
- **[SSL-FT]** Self-Supervised Learning with Data-Efficient Supervised Fine-Tuning for Crowd Counting (**TMM**) [[paper](https://ieeexplore.ieee.org/document/10057013)]
- **[FRVCC]** Frame-Recurrent Video Crowd Counting (**T-CSVT**) [[paper](https://ieeexplore.ieee.org/document/10057072)]
- **[FLCB]** Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting (**FITEE**) [[paper](https://link.springer.com/article/10.1631/FITEE.2200380)]
- **[MTCP]** Multi-Task Credible Pseudo-Label Learning for Semi-supervised Crowd Counting (**T-NNLS**) [[paper]()] [[code](https://github.com/ljq2000/MTCP)]
- **[STGN]** Spatial-Temporal Graph Network for Video Crowd Counting (**T-CSVT**) [[paper](https://ieeexplore.ieee.org/document/9810269)][[code](https://github.com/wuzhe71/STGN)]
- **[PML_Loss]** Progressive Multi-resolution Loss for Crowd Counting (**T-CSVT**) [[paper](https://ieeexplore.ieee.org/abstract/document/10256036/)][[code](https://github.com/streamer-AP/PML_Loss)]
- **[EoCo]** A Unified Object Counting Network with Object Occupation Prior (**T-CSVT**) [[paper](https://ieeexplore.ieee.org/abstract/document/10172099)][[code](https://github.com/Tanyjiang/EOCO)]
- **[CmCaF]** RGB-D Crowd Counting With Cross-Modal Cycle-Attention Fusion and Fine-Coarse Supervision (**TII**) [[paper](https://ieeexplore.ieee.org/document/9765786)]
- **[STC-Crowd]** Semi-supervised Crowd Counting with Spatial Temporal Consistency and Pseudo-label Filter (**T-CSVT**)[[paper](https://ieeexplore.ieee.org/document/10032602)]
- **[LMSFFNet]** A Lightweight Multiscale Feature Fusion Network for Remote Sensing Object Counting (**TGRS**) [[paper](https://ieeexplore.ieee.org/document/10021616)]
- **[DDMD]** Deformable Density Estimation via Adaptive Representation (**TIP**) [[paper](https://ieeexplore.ieee.org/document/10036469)]
- **[UCCF]** A unified RGB-T crowd counting learning framework (**Image and Vision Computing**) [[arxiv](https://arxiv.org/abs/2202.03843)] [[paper](https://linkinghub.elsevier.com/retrieve/pii/S0262885623000057)]
- **[DASECount]** DASECount: Domain-Agnostic Sample-Efficient Wireless Indoor Crowd Counting via Few-shot Learning (**IEEE IOT**) [[paper](https://arxiv.org/abs/2211.10040)]
- **[CrowdMLP]** CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP (**Pattern Recognition**) [[paper](https://arxiv.org/abs/2203.08219)]
- **[MTSS]** Multi-task semi-supervised crowd counting via global to local self-correction (**Pattern Recognition**) [[paper](https://www.sciencedirect.com/science/article/abs/pii/S0031320323002066)]
### 2022
### Conference
- **[CTFNet]** Faster, Lighter, Robuster: A Weakly-Supervised Crowd Analysis Enhancement Network and A Generic Feature Extraction Framework (**CVPR**)[[paper](https://openaccess.thecvf.com/content/CVPR2022W/L3D-IVU/html/Wu_Faster_Lighter_Robuster_A_Weakly-Supervised_Crowd_Analysis_Enhancement_Network_and_CVPRW_2022_paper.html)]
- **[CSS-CCNN]** Completely Self-Supervised Crowd Counting via Distribution Matching (**ECCV**) [[paper](https://arxiv.org/abs/2009.06420)][[code](https://github.com/val-iisc/css-ccnn)]
- **[TSFADet]** Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection (**ECCV**) [[paper](https://arxiv.org/abs/2209.13801)]
- **[CSCA]** Spatio-channel Attention Blocks for Cross-modal Crowd Counting (**ACCV**) [[paper](https://arxiv.org/abs/2210.10392)] [[code](https://github.com/VCLLab/CSCA)]
- **[CUT]** Segmentation Assisted U-shaped Multi-scale Transformer for Crowd Counting (**BMVC**) [[paper](https://www.researchgate.net/publication/364030579_Segmentation_Assisted_U-shaped_Multi-scale_Transformer_for_Crowd_Counting)]
- **[MSDTrans]** RGB-T Multi-Modal Crowd Counting Based on Transformer (**BMVC**)[[paper](https://arxiv.org/abs/2301.03033)] [[code](https://github.com/liuzywen/RGBTCC)]
- **[LoViTCrowd]** Improving Local Features with Relevant Spatial Information by Vision Transformer for Crowd Counting (**BMVC**) [[paper](https://bmvc2022.mpi-inf.mpg.de/0729.pdf)] [[code](https://github.com/nguyen1312/LoViTCrowd)]
- **[SPDCN]** Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting (**BMVC**) [[paper](https://bmvc2022.mpi-inf.mpg.de/0313.pdf)]
- **[PAP]** Harnessing Perceptual Adversarial Patches for Crowd Counting (**ACM CCS**) [[paper](https://arxiv.org/abs/2109.07986)] [[code](https://github.com/shunchang-liu/PAP-Pytorch)]
- **[CLTR]** An End-to-End Transformer Model for Crowd Localization (**ECCV**) [[paper](https://arxiv.org/abs/2202.13065)] [[code](https://github.com/dk-liang/CLTR)][[project](https://dk-liang.github.io/CLTR/)]
- **[CF-MVCC]** Calibration-free Multi-view Crowd Counting (**ECCV**) [[paper](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136690224.pdf)]
- **[DC]** Discrete-Constrained Regression for Local Counting Models (**ECCV**) [[paper](https://arxiv.org/abs/2207.09865)]
- **[DMBA]** Backdoor Attacks on Crowd Counting (**ACM MM**) [[paper](https://arxiv.org/abs/2205.11398)][[code](https://github.com/Nathangitlab/Backdoor-Attacks-on-Crowd-Counting)]
- **[DACount]** Semi-supervised-Crowd-Counting-via-Density-Agency (**ACM MM**) [[paper](https://arxiv.org/abs/2209.02955)][[code](https://github.com/LoraLinH/Semi-supervised-Crowd-Counting-via-Density-Agency)]
- **[ChfL]** Crowd Counting in the Frequency Domain (**CVPR**) [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Shu_Crowd_Counting_in_the_Frequency_Domain_CVPR_2022_paper.pdf)][[code](https://github.com/wbshu/Crowd_Counting_in_the_Frequency_Domain)]
- **[GauNet]** Rethinking Spatial Invariance of Convolutional Networks for Object Counting (**CVPR**) [[paper](https://arxiv.org/abs/2206.05253)][[code](https://github.com/zhiqic/Rethinking-Counting)]
- **[DR.VIC]** DR.VIC: Decomposition and Reasoning for Video Individual Counting (**CVPR**) [[paper](https://crabwq.github.io/pdf/2022%20DR.VIC.pdf)][[code](https://github.com/taohan10200/DRNet)]
- **[CDCC]** Leveraging Self-Supervision for Cross-Domain Crowd Counting (**CVPR**) [[paper](https://arxiv.org/abs/2103.16291)][[code](https://github.com/weizheliu/Cross-Domain-Crowd-Counting)]
- **[MAN]** Boosting Crowd Counting via Multifaceted Attention (**CVPR**) [[paper](https://arxiv.org/abs/2203.02636)][[code](https://github.com/LoraLinH/Boosting-Crowd-Counting-via-Multifaceted-Attention)]
- **[BLA]** Bi-level Alignment for Cross-Domain Crowd Counting (**CVPR**) [[paper](https://arxiv.org/abs/2205.05844)][[code](https://github.com/Yankeegsj/BLA)]
- **[BMNet]** Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting (**CVPR**)[[paper](https://arxiv.org/abs/2203.08354)][[code](https://github.com/flyinglynx/Bilinear-Matching-Network)]
- Fine-Grained Counting with Crowd-Sourced Supervision (**CVPRW**) [[paper](https://arxiv.org/abs/2205.11398)]
- **[CrowdFormer]** CrowdFormer: An Overlap Patching Vision Transformer for Top-Down Crowd Counting (**IJCAI**)[[paper](https://www.ijcai.org/proceedings/2022/0215.pdf)]
- **[WSCNN]** Single Image Object Counting and Localizing using Active-Learning (**WACV**) [[paper](https://openaccess.thecvf.com/content/WACV2022/papers/Huberman-Spiegelglas_Single_Image_Object_Counting_and_Localizing_Using_Active-Learning_WACV_2022_paper.pdf)]
- **[IS-Count]** IS-Count: Large-Scale Object Counting from Satellite Images with Covariate-Based Importance Sampling (**AAAI**) [[paper](https://arxiv.org/abs/2112.09126)][[code](https://github.com/sustainlab-group/IS-Count)]
- **[STAN]** A Spatio-Temporal Attentive Network for Video-Based Crowd Counting (**ISCC**) [[paper](https://arxiv.org/abs/2208.11339)]
- **[LARL]** Label-Aware Ranked Loss for robust People Counting using Automotive in-cabin Radar (**ICASSP**) [[paper](https://arxiv.org/abs/2110.05876v2)]
- **[ESA-Net]** Enhancing and Dissecting Crowd Counting By Synthetic Data (**ICASSP**) [[paper](https://arxiv.org/abs/2201.08992)]
- **[MPS]** Multiscale Crowd Counting and Localization By Multitask Point Supervision (**ICASSP**) [[paper](https://arxiv.org/abs/2202.09942)][[code](https://github.com/RCVLab-AiimLab/crowd_counting)]
- **[TAFNet]** TAFNet: A Three-Stream Adaptive Fusion Network for RGB-T Crowd Counting (**ISCAS**) [[paper](https://arxiv.org/abs/2202.08517)][[code](https://github.com/TANGHAIHAN/TAFNet)]
- **[HDNet]** HDNet: A Hierarchically Decoupled Network for Crowd Counting (**ICME**) [[paper](https://arxiv.org/abs/2212.05722)]
- **[SSDA]** Self-supervised Domain Adaptation in Crowd Counting (**ICIP**) [[paper](https://arxiv.org/abs/2206.03431)]
- **[FusionCount]** FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion (**ICIP**) [[paper](https://arxiv.org/abs/2202.13660)][[code](https://github.com/YimingMa/FusionCount)]
### Journal
- **[PSGCNet]** PSGCNet: A Pyramidal Scale and Global Context Guided Network for Dense Object Counting in Remote Sensing Images (**TGRS**) [[paper](https://ieeexplore.ieee.org/abstract/document/9720990)][[code](https://github.com/gaoguangshuai/psgcnet)]
- **[MVMS]** Wide-Area Crowd Counting: Multi-View Fusion Networks for Counting in Large Scenes (**IJCV**) [[paper](https://arxiv.org/abs/2012.00946)](extension of [MVMS](#MVMS))
- **[DEFNet]** DEFNet: Dual-Branch Enhanced Feature Fusion Network for RGB-T Crowd Counting (**TITS**) [[paper](https://ieeexplore.ieee.org/abstract/document/9889192)][[code](https://github.com/panyi95/DEFNet)]
- **[CLRNet]** CLRNet: A Cross Locality Relation Network for Crowd Counting in Videos (**T-NNLS**) [[paper](https://ieeexplore.ieee.org/document/9913683)]
- **[AGCCM]** Attention-guided Collaborative Counting (**TIP**) [[paper](https://ieeexplore.ieee.org/document/9906560)]
- **[GNA]** Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark (**TIP**) [[paper](https://ieeexplore.ieee.org/abstract/document/9893023/)][[code](https://github.com/HopLee6/VSCrowd-Dataset)]
- **[LibraNet+DQN]** Counting Crowd by Weighing Counts: A Sequential Decision-Making Perspective (**T-NNLS**) [[paper](https://ieeexplore.ieee.org/document/9887967/)][[code](https://git.io/libranet)](extension of [LibraNet](#LibraNet))
- **[FIDTM]** Focal Inverse Distance Transform Maps for Crowd Localization (**TMM**)[[paper](https://ieeexplore.ieee.org/document/9875106)] [[code](https://github.com/dk-liang/FIDTM)] [[project](https://dk-liang.github.io/FIDTM/)]
- **[NDConv]** An Improved Normed-Deformable Convolution for Crowd Counting (**SPL**) [[paper](https://arxiv.org/abs/2206.08084)]
- **[RAN]** Region-Aware Network: Model Human’s Top-Down Visual Perception Mechanism for Crowd Counting (**Neural Networks**) [[paper](https://arxiv.org/abs/2106.12163)]
- **[HANet]** Hybrid attention network based on progressive embedding scale-context for crowd counting (**Information Sciences**) [[paper](https://arxiv.org/abs/2106.02324)]
- **[TransCrowd]** TransCrowd: Weakly-Supervised Crowd Counting with Transformer (**Science China Information Sciences**) [[paper](https://arxiv.org/abs/2104.09116)] [[code](https://github.com/dk-liang/TransCrowd)]
- **[STNet]** STNet: Scale Tree Network with Multi-level Auxiliator for Crowd Counting (**TMM**) [[paper](https://ieeexplore.ieee.org/document/9681311)]
- **[SGANet]** Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss (**TITS**) [[paper](https://ieeexplore.ieee.org/document/9678116)]
- **[CTASNet]** Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation (**T-CSVT**) [[paper](https://ieeexplore.ieee.org/document/9899467)]
- **[SSR-HEF]** SSR-HEF: Crowd Counting with Multi-Scale Semantic Refining and Hard Example Focusing (**TII**) [[paper](https://arxiv.org/abs/2204.07406)]
- **[ECCNAS]** ECCNAS: Efficient Crowd Counting Neural Architecture Search (**TOMM**) [[paper](https://dl.acm.org/doi/abs/10.1145/3465455)]
- **[SSCC]** Scene-specific crowd counting using synthetic training images (**Pattern Recognition**) [[paper](https://www.sciencedirect.com/science/article/pii/S0031320321006609)]
- **[SL-ViT]** Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead (**Neural Networks**) [[paper](https://arxiv.org/abs/2105.09121)]
- **[DCST]** Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer (**Neurocomputing**) [[paper](https://arxiv.org/abs/2108.00584)]
- A survey on deep learning-based single image crowd counting: Network design, loss function and supervisory signal (**Neurocomputing**) [[paper](https://arxiv.org/abs/2012.15685)]
### 2021
### Conference
- **[GNet]** Gaussian map predictions for 3D surface feature localisation and counting (**BMVC**) [[paper](https://www.bmvc2021-virtualconference.com/assets/papers/1417.pdf)]
- **[PFSNet]** Robust Crowd Counting via Image Enhancement and Dynamic Feature Selection (**BMVC**) [[paper](https://www.bmvc2021-virtualconference.com/assets/papers/1387.pdf)]
- **[URC]** Crowd Counting With Partial Annotations in an Image (**ICCV**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Xu_Crowd_Counting_With_Partial_Annotations_in_an_Image_ICCV_2021_paper.pdf)]
- **[MFDC]** Exploiting Sample Correlation for Crowd Counting With Multi-Expert Network (**ICCV**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Liu_Exploiting_Sample_Correlation_for_Crowd_Counting_With_Multi-Expert_Network_ICCV_2021_paper.pdf)]
- **[SDNet]** Towards A Universal Model for Cross-Dataset Crowd Counting (**ICCV**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Ma_Towards_a_Universal_Model_for_Cross-Dataset_Crowd_Counting_ICCV_2021_paper.pdf)]
- **[P2PNet]** Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework (**ICCV(Oral)**) [[paper](https://arxiv.org/abs/2107.12746)][[code](https://github.com/TencentYoutuResearch/CrowdCounting-P2PNet)]
- **[UEPNet]** Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting (**ICCV**) [[paper](https://arxiv.org/abs/2107.12619)][[code](https://github.com/TencentYoutuResearch/CrowdCounting-UEPNet)]
- **[SUA]** Spatial Uncertainty-Aware Semi-Supervised Crowd Counting (**ICCV**) [[paper](https://arxiv.org/abs/2107.13271)][[code](https://github.com/smallmax00/SUA_crowd_counting)]
- **[DKPNet]** Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting (**ICCV**) [[paper](https://arxiv.org/abs/2108.08023)][[code](https://github.com/Zhaoyi-Yan/DKPNet)]
- **[CC-AV]** Audio-Visual Transformer Based Crowd Counting (**ICCVW**) [[paper](https://arxiv.org/abs/2109.01926)]
- **[BinLoss]** Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting (**ACM MM**) [[paper](https://arxiv.org/abs/2108.08784)][[code](https://github.com/atmacvit/bincrowd)]
- **[C2MoT]** Dynamic Momentum Adaptation for Zero-Shot Cross-Domain Crowd Counting (**ACM MM**) [[paper](https://dl.acm.org/doi/pdf/10.1145/3474085.3475230)][[code](https://github.com/jimmy-dq/C2MOT)]
- **[ASNet]** Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network (**ACM MM**) [[paper](https://arxiv.org/abs/2107.12858)]
- **[APAM]** Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting (**ACM MM**) [[paper](https://arxiv.org/abs/2104.10868)][[code](https://github.com/harrywuhust2022/Adv-Crowd-analysis)]
- **[S3]** Direct Measure Matching for Crowd Counting (**IJCAI**) [[paper](https://www.ijcai.org/proceedings/2021/0116.pdf)]
- **[BM-Count]** Bipartite Matching for Crowd Counting with Point Supervision (**IJCAI**) [[paper](https://www.ijcai.org/proceedings/2021/0119.pdf)]
- **[GLoss]** A Generalized Loss Function for Crowd Counting and Localization (**CVPR**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Wan_A_Generalized_Loss_Function_for_Crowd_Counting_and_Localization_CVPR_2021_paper.pdf)]
- **[CVCS]** Cross-View Cross-Scene Multi-View Crowd Counting (**CVPR**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhang_Cross-View_Cross-Scene_Multi-View_Crowd_Counting_CVPR_2021_paper.pdf)]
- **[STANet]** Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark (**CVPR**) [[paper](https://arxiv.org/abs/2105.02440)][[code](https://github.com/VisDrone/DroneCrowd)]
- **[RGBT-CC]** Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting (**CVPR**) [[paper](https://arxiv.org/abs/2012.04529)][[code](https://github.com/chen-judge/RGBTCrowdCounting)][[Project](http://lingboliu.com/RGBT_Crowd_Counting.html#)]
- **[EDIREC-Net]** Error-Aware Density Isomorphism Reconstruction for Unsupervised Cross-Domain Crowd Counting (**AAAI**) [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/16245)][[code](https://github.com/GehenHe/EDIREC-Net)]
- **[SASNet]** To Choose or to Fuse? Scale Selection for Crowd Counting (**AAAI**) [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/16360)][[code](https://github.com/TencentYoutuResearch/CrowdCounting-SASNet)]
- **[UOT]** Learning to Count via Unbalanced Optimal Transport (**AAAI**) [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/16332)]
- **[TopoCount]** Localization in the Crowd with Topological Constraints (**AAAI**) [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/16170)][[code](https://github.com/ShahiraAbousamra/TopoCount)]
- **[CFANet]** Coarse- and Fine-grained Attention Network with Background-aware Loss for Crowd Density Map Estimation (**WACV**) [[paper](https://arxiv.org/abs/2011.03721)][[code](https://github.com/rongliangzi/MARUNet)]
- **[BSCC]** Understanding the impact of mistakes on background regions in crowd counting (**WACV**) [[paper](https://arxiv.org/abs/2003.13759)]
- **[CFOCNet]** Class-agnostic Few-shot Object Counting (**WACV**) [[paper](https://winstonhsu.info/wp-content/uploads/2020/11/yang21class-agnostic.pdf)][[code](https://github.com/SinicaGroup/Class-agnostic-Few-shot-Object-Counting)]
- **[SCALNet]** Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization (**ICMEW**) [[paper](https://arxiv.org/abs/2104.12505)][[code](https://github.com/WangyiNTU/SCALNet)]
- **[DSNet]** Dense Scale Network for Crowd Counting (**ICMR**) [[paper](https://arxiv.org/abs/1906.09707)][unofficial code: [PyTorch](https://github.com/rongliangzi/Dense-Scale-Network-for-Crowd-Counting)]
- **[FCVF]** Learning Factorized Cross-View Fusion for Multi-View Crowd Counting (**ICME**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9428284)]
- **[IDK]** Leveraging Intra-Domain Knowledge to Strengthen Cross-Domain Crowd Counting (**ICME**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9428159)]
- **[CRANet]** CRANet: Cascade Residual Attention Network for Crowd Counting (**ICME**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9428236)]
### Journal
- **[DPDNet]** Locating and Counting Heads in Crowds With a Depth Prior (**T-PAMI**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9601215)] [[code](https://github.com/svip-lab/Locating_Counting_with_a_Depth_Prior)]
- **[EPF]** Counting People by Estimating People Flows (**TPAMI**) [[paper](https://arxiv.org/abs/2012.00452)][[code](https://github.com/weizheliu/People-Flows)]
- **[LA-Batch]** Locality-Aware Crowd Counting (**TPAMI**) [[paper](https://www.computer.org/csdl/journal/tp/5555/01/09346018/1qV39sNsjWU)]
- **[AutoScale]** AutoScale: Learning to Scale for Crowd Counting (**IJCV**) [[paper](https://link.springer.com/article/10.1007/s11263-021-01542-z)] (extension of [L2SM](#L2SM))[[code](https://github.com/dk-liang/AutoScale)]
- **[DSACA]** Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting (**SPL**) [[paper](https://ieeexplore.ieee.org/abstract/document/9479708)] [[code](https://github.com/PRIS-CV/DSACA)]
- **[NLT]** Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting (**T-NNLS**) [[paper](https://arxiv.org/abs/2004.02133)] [[code]](https://github.com/taohan10200/NLT)]
- **[DACC]** Domain-Adaptive Crowd Counting via High-Quality Image Translation and Density Reconstruction (**T-NNLS**) [[paper](https://arxiv.org/abs/1912.03677)]
- **[MATT]** Towards Using Count-level Weak Supervision for Crowd Counting (**Pattern Recognition**) [[paper](https://arxiv.org/abs/2003.00164)]
- **[D2C]** Decoupled Two-Stage Crowd Counting and Beyond (**TIP**) [[paper](https://ieeexplore.ieee.org/document/9347700)][[code](https://github.com/hustaia/Decoupled_Two-Stage_Counting)]
- **[TBC]** Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets (**TIP**) [[paper](https://ieeexplore.ieee.org/document/9298464)]
- **[FGCC]** Fine-Grained Crowd Counting (**TIP**) [[paper](https://arxiv.org/abs/2007.06146)]
- **[PSODC]** A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds (**TIP**) [[paper](https://arxiv.org/abs/2007.12831)][[code](https://github.com/WangyiNTU/Point-supervised-crowd-detection)]
- **[EPA]** Embedding Perspective Analysis Into Multi-Column Convolutional Neural Network for Crowd Counting (**TIP**) [[paper](https://ieeexplore.ieee.org/document/9293174)]
- **[PFDNet]** Crowd Counting via Perspective-Guided Fractional-Dilation Convolution (**TMM**) [[paper](https://ieeexplore.ieee.org/document/9468694)](extension of [PGCNet](#PGCNet))
- **[STDNet]** Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation (**TMM**) [[paper](https://arxiv.org/abs/2101.12439)]
- **[AdaCrowd]** AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting (**TMM**) [[paper](https://arxiv.org/abs/2010.12141)][[code](https://github.com/maheshkkumar/adacrowd)]
- **[DCANet]** Towards Learning Multi-domain Crowd Counting (**T-CSVT**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9658506)] [[code](https://github.com/Zhaoyi-Yan/DCANet)]
- **[PDANet]** PDANet: Pyramid Density-aware Attention Net for Accurate Crowd Counting (**Neurocomputing**) [[paper](https://arxiv.org/abs/2001.05643)]
- **[ScSiNet]** Interlayer and Intralayer Scale Aggregation for Scale-invariant Crowd Counting (**Neurocomputing**) [[paper](https://arxiv.org/abs/2005.11943)]
- **[PRM]** Towards More Effective PRM-based Crowd Counting via A Multi-resolution Fusion and Attention Network (**Neurocomputing**) [[paper](https://arxiv.org/abs/2112.09664)]
- **[DeepCorn]** DeepCorn: A Semi-Supervised Deep Learning Method for High-Throughput Image-Based Corn Kernel Counting and Yield Estimation (**Knowledge-Based Systems**) [[paper](https://arxiv.org/abs/2007.10521)]
### 2020
### Conference
- **[DM-Count]** Distribution Matching for Crowd Counting (**NeurIPS**) [[paper](https://arxiv.org/abs/2009.13077)][[code](https://github.com/cvlab-stonybrook/DM-Count)]
- **[MNA]** Modeling Noisy Annotations for Crowd Counting (**NeurIPS**) [[paper](http://visal.cs.cityu.edu.hk/static/pubs/conf/nips2020-noisycc-web.pdf)]
- **[SKT]** Efficient Crowd Counting via Structured Knowledge Transfer (**ACM MM(oral)**) [[paper](https://arxiv.org/abs/2003.10120)][[code](https://github.com/HCPLab-SYSU/SKT)]
- **[DPN]** Learning Scales from Points: A Scale-aware Probabilistic Model for Crowd Counting (**ACM MM(oral)**) [[paper](https://dl.acm.org/doi/10.1145/3394171.3413642)]
- **[RDBT]** Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer (**ACM MM**) [[paper](https://arxiv.org/abs/2008.05383)]
- **[VisDrone-CC2020]** VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results (**ECCV**) [[paper](https://arxiv.org/abs/2107.08766)]
- **[EPF]** Estimating People Flows to Better Count Them in Crowded Scenes (**ECCV**) [[paper](https://arxiv.org/abs/1911.10782)][[code](https://github.com/weizheliu/People-Flows)]
- **[AMSNet]** NAS-Count: Counting-by-Density with Neural Architecture Search (**ECCV**) [[paper](https://arxiv.org/abs/2003.00217)]
- **[AMRNet]** Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting (**ECCV**) [[paper](https://arxiv.org/abs/2005.05776)][[code](https://github.com/xiyang1012/Local-Crowd-Counting)]
- **[LibraNet]** Weighting Counts: Sequential Crowd Counting by Reinforcement Learning (**ECCV**) [[paper](https://arxiv.org/abs/2007.08260)][[code](https://github.com/poppinace/libranet)]
- **[GP]** Learning to Count in the Crowd from Limited Labeled Data (**ECCV**) [[paper](https://arxiv.org/abs/2007.03195)]
- **[IRAST]** Semi-supervised Crowd Counting via Self-training on Surrogate Tasks (**ECCV**) [[paper](https://arxiv.org/abs/2007.03207)]
- **[PSSW]** Active Crowd Counting with Limited Supervision (**ECCV**) [[paper](https://arxiv.org/abs/2007.06334)]
- **[CCLS]** Weakly-Supervised Crowd Counting Learns from Sorting rather than Locations (**ECCV**) [[paper](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123530001.pdf)]
- **[Bi-pathNet]** A Flow Base Bi-path Network for Cross-scene Video Crowd Understanding in Aerial View (**ECCVW**) [[paper](https://arxiv.org/abs/2009.13723)]
- **[ADSCNet]** Adaptive Dilated Network with Self-Correction Supervision for Counting (**CVPR**) [[paper](http://openaccess.thecvf.com/content_CVPR_2020/papers/Bai_Adaptive_Dilated_Network_With_Self-Correction_Supervision_for_Counting_CVPR_2020_paper.pdf)]
- **[RPNet]** Reverse Perspective Network for Perspective-Aware Object Counting (**CVPR**) [[paper](http://openaccess.thecvf.com/content_CVPR_2020/papers/Yang_Reverse_Perspective_Network_for_Perspective-Aware_Object_Counting_CVPR_2020_paper.pdf)] [[code](https://github.com/CrowdCounting)]
- **[ASNet]** Attention Scaling for Crowd Counting (**CVPR**) [[paper](http://openaccess.thecvf.com/content_CVPR_2020/papers/Jiang_Attention_Scaling_for_Crowd_Counting_CVPR_2020_paper.pdf)] [[code](https://github.com/laridzhang/ASNet)]
- **[SRF-Net]** Scale-Aware Rolling Fusion Network for Crowd Counting (**ICME**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9102854)]
- **[EDC]** Learning Error-Driven Curriculum for Crowd Counting (**ICPR**) [[paper](https://arxiv.org/pdf/2007.09676.pdf)][[code](https://github.com/FDU-VTS/TutorNet_Crowd_Counting)]
- **[PRM]** Multi-Resolution Fusion and Multi-scale Input Priors Based Crowd Counting (**ICPR**) [[paper](https://arxiv.org/abs/2010.01664)]
- **[M-SFANet]** Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting (**ICPR**) [[paper](https://arxiv.org/abs/2003.05586)][[code](https://github.com/Pongpisit-Thanasutives/Variations-of-SFANet-for-Crowd-Counting)]
- **[HSRNet]** Crowd Counting via Hierarchical Scale Recalibration Network (**ECAI**) [[paper](https://arxiv.org/abs/2003.03545)]
- **[DeepCount]** Deep Density-aware Count Regressor (**ECAI**) [[paper](https://arxiv.org/abs/1908.03314)][[code](https://github.com/GeorgeChenZJ/deepcount)]
- **[SOFA-Net]** SOFA-Net: Second-Order and First-order Attention Network for Crowd Counting (**BMVC**) [[paper](https://arxiv.org/abs/2008.03723)]
- **[CWAN]** Weakly Supervised Crowd-Wise Attention For Robust Crowd Counting (**ICASSP**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9054258)]
- **[AGRD]** Attention Guided Region Division for Crowd Counting (**ICASSP**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9053761)]
- **[BBA-NET]** BBA-NET: A Bi-Branch Attention Network For Crowd Counting (**ICASSP**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9053955)]
- **[SMANet]** Stochastic Multi-Scale Aggregation Network for Crowd Counting (**ICASSP**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9054238)]
- **[Stacked-Pool]** Stacked Pooling For Boosting Scale Invariance Of Crowd Counting (**ICASSP**) [[paper](https://siyuhuang.github.io/papers/ICASSP-2020-STACKED%20POOLING%20FOR%20BOOSTING%20SCALE%20INVARIANCE%20OF%20CROWD%20COUNTING.pdf)] [[arxiv](https://arxiv.org/abs/1808.07456)] [[code](https://github.com/siyuhuang/crowdcount-stackpool)]
- **[MSPNET]** Multi-supervised Parallel Network for Crowd Counting (**ICASSP**) [[paper](https://crabwq.github.io/pdf/2020%20MSPNET%20Multi-supervised%20Parallel%20Network%20for%20Crowd%20Counting.pdf)]
- **[ASPDNet]** Counting dense objects in remote sensing images (**ICASSP**) [[paper](https://arxiv.org/abs/2002.05928)]
- **[FSC]** Focus on Semantic Consistency for Cross-domain Crowd Understanding (**ICASSP**) [[paper](https://arxiv.org/abs/2002.08623)]
- **[C-CNN]** A Real-Time Deep Network for Crowd Counting (**ICASSP**) [[arxiv](https://arxiv.org/abs/2002.06515)][[ieee](https://ieeexplore.ieee.org/abstract/document/9053780/)]
- **[HyGnn]** Hybrid Graph Neural Networks for Crowd Counting (**AAAI**) [[paper](https://arxiv.org/abs/2002.00092)]
- **[DUBNet]** Crowd Counting with Decomposed Uncertainty (**AAAI**) [[paper](https://arxiv.org/abs/1903.07427)]
- **[SDANet]** Shallow Feature based Dense Attention Network for Crowd Counting (**AAAI**) [[paper](http://wrap.warwick.ac.uk/130173/1/WRAP-shallow-feature-dense-attention-crowd-counting-Han-2019.pdf)]
- **[3DCC]** 3D Crowd Counting via Multi-View Fusion with 3D Gaussian Kernels (**AAAI**) [[paper](https://arxiv.org/abs/2003.08162)][[Project](http://visal.cs.cityu.edu.hk/research/aaai20-3d-counting/)]
- **[FSSA]** Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning (**WACV**) [[paper](https://arxiv.org/abs/2002.00264)][[code](https://github.com/maheshkkumar/fscc)] 
- **[CC-Mod]** Plug-and-Play Rescaling Based Crowd Counting in Static Images (**WACV**) [[paper](https://arxiv.org/abs/2001.01786)]
- **[CTN]** Uncertainty Estimation and Sample Selection for Crowd Counting (**ACCV**) [[paper](https://arxiv.org/abs/2009.14411)]
- **[ikNN]** Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling (**VISAPP**) [[paper](https://arxiv.org/abs/1902.05379)]
### Journal
- **[NWPU]** NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization (**T-PAMI**) [[paper](https://arxiv.org/abs/2001.03360)][[code](https://gjy3035.github.io/NWPU-Crowd-Sample-Code/)]
- **[KDMG]** Kernel-based Density Map Generation for Dense Object Counting (**T-PAMI**) [[paper](https://ieeexplore.ieee.org/document/9189836)][[code](https://github.com/jia-wan/KDMG_Counting)]
- **[JHU-CROWD]** JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (**T-PAMI**) [[paper](https://arxiv.org/abs/2004.03597)](extension of [CG-DRCN](#CG-DRCN))
- **[LSC-CNN]** Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection (**T-PAMI**) [[paper](https://arxiv.org/abs/1906.07538)][[code](https://github.com/val-iisc/lsc-cnn)]
- **[PWCU]** Pixel-wise Crowd Understanding via Synthetic Data (**IJCV**) [[paper](https://arxiv.org/abs/2007.16032)]
- **[CRNet]** Crowd Counting via Cross-stage Refinement Networks (**TIP**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9096602)][[code](https://github.com/lytgftyf/Crowd-Counting-via-Cross-stage-Refinement-Networks)] 
- **[BNFDD]** Background Noise Filtering and Distribution Dividing for Crowd Counting (**TIP**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9161353)]
- **[FADA]** Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance (**TCYB**) [[paper](https://arxiv.org/abs/1912.03672)]
- **[MS-GAN]** Adversarial Learning for Multiscale Crowd Counting Under Complex Scenes (**TCYB**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8949751)]
- **[DCL]** Density-aware Curriculum Learning for Crowd Counting (**TCYB**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9275392)][[code](https://github.com/Elin24/DCL-CrowdCounting)]
- **[ZoomCount]** ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images (**T-CSVT**) [[paper](https://arxiv.org/abs/2002.12256)]
- **[DensityCNN]** Density-Aware Multi-Task Learning for Crowd Counting (**TMM**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9037113)]
- **[DENet]** DENet: A Universal Network for Counting Crowd with Varying Densities and Scales (**TMM**) [[paper](https://arxiv.org/abs/1904.08056)][[code](https://github.com/liuleiBUAA/DENet)]
- **[CLPNet]** Cross-Level Parallel Network for Crowd Counting (**TII**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8798674)]
- **[FMLF]** Crowd Density Estimation Using Fusion of Multi-Layer Features (**TITS**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9063540)]
- **[MLSTN]** Multi-level feature fusion based Locality-Constrained Spatial Transformer network for video crowd counting (**Neurocomputing**) [[paper](https://www.sciencedirect.com/science/article/pii/S0925231220301454)](extension of [LSTN](#LSTN))
- **[SRN+PS]** Scale-Recursive Network with point supervision for crowd scene analysis (**Neurocomputing**) [[paper](https://www.sciencedirect.com/science/article/abs/pii/S0925231219317795)]
- **[ASDF]** Counting crowds with varying densities via adaptive scenario discovery framework (**Neurocomputing**) [[paper](https://www.sciencedirect.com/science/article/pii/S0925231220302356)](extension of [ASD](#ASD))
- **[CAT-CNN]** Crowd counting with crowd attention convolutional neural network (**Neurocomputing**) [[paper](https://www.sciencedirect.com/science/article/pii/S0925231219316662)]
- **[RRP]** Relevant Region Prediction for Crowd Counting (**Neurocomputing**) [[paper](https://arxiv.org/abs/2005.09816)]
- **[SCAN]** Crowd Counting via Scale-Communicative Aggregation Networks (**Neurocomputing**) [[paper](https://www.sciencedirect.com/science/article/abs/pii/S0925231220308778)](extension of [MVSAN](#MVSAN))
- **[MobileCount]** MobileCount: An Efficient Encoder-Decoder Framework for Real-Time Crowd Counting (**Neurocomputing**) [[conference paper](https://link.springer.com/chapter/10.1007/978-3-030-31723-2_50)] [[journal paper](https://www.sciencedirect.com/science/article/pii/S0925231220308912)] [[code](https://github.com/SelinaFelton/MobileCount)]
- **[TAN]** Fast Video Crowd Counting with a Temporal Aware Network (**Neurocomputing**) [[paper](https://arxiv.org/abs/1907.02198)]
- **[MH-METRONET]** MH-MetroNet—A Multi-Head CNN for Passenger-Crowd Attendance Estimation (**JImaging**) [[paper](https://www.mdpi.com/759202)][[code]( https://bitbucket.org/isasi-lecce/mh-metronet/src/master/)]
### 2019
### Conference
- **[CG-DRCN]** Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method (**ICCV**)[[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Sindagi_Pushing_the_Frontiers_of_Unconstrained_Crowd_Counting_New_Dataset_and_ICCV_2019_paper.pdf)]
- **[ADMG]** Adaptive Density Map Generation for Crowd Counting (**ICCV**)[[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Wan_Adaptive_Density_Map_Generation_for_Crowd_Counting_ICCV_2019_paper.pdf)]
- **[DSSINet]** Crowd Counting with Deep Structured Scale Integration Network (**ICCV**) [[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Crowd_Counting_With_Deep_Structured_Scale_Integration_Network_ICCV_2019_paper.pdf)][[code](https://github.com/Legion56/Counting-ICCV-DSSINet)] 
- **[RANet]** Relational Attention Network for Crowd Counting (**ICCV**)[[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Relational_Attention_Network_for_Crowd_Counting_ICCV_2019_paper.pdf)]
- **[ANF]** Attentional Neural Fields for Crowd Counting (**ICCV**)[[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Attentional_Neural_Fields_for_Crowd_Counting_ICCV_2019_paper.pdf)]
- **[SPANet]** Learning Spatial Awareness to Improve Crowd Counting (**ICCV(oral)**) [[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Cheng_Learning_Spatial_Awareness_to_Improve_Crowd_Counting_ICCV_2019_paper.pdf)]
- **[MBTTBF]** Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting (**ICCV**) [[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Sindagi_Multi-Level_Bottom-Top_and_Top-Bottom_Feature_Fusion_for_Crowd_Counting_ICCV_2019_paper.pdf)]
- **[CFF]** Counting with Focus for Free (**ICCV**) [[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Shi_Counting_With_Focus_for_Free_ICCV_2019_paper.pdf)][[code](https://github.com/shizenglin/Counting-with-Focus-for-Free)] 
- **[L2SM]** Learn to Scale: Generating Multipolar Normalized Density Map for Crowd Counting (**ICCV**) [[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Xu_Learn_to_Scale_Generating_Multipolar_Normalized_Density_Maps_for_Crowd_ICCV_2019_paper.pdf)]
- **[S-DCNet]** From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer (**ICCV**) [[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Xiong_From_Open_Set_to_Closed_Set_Counting_Objects_by_Spatial_ICCV_2019_paper.pdf)][[code](https://github.com/xhp-hust-2018-2011/S-DCNet)]
- **[BL]** Bayesian Loss for Crowd Count Estimation with Point Supervision (**ICCV(oral)**) [[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Ma_Bayesian_Loss_for_Crowd_Count_Estimation_With_Point_Supervision_ICCV_2019_paper.pdf)][[code](https://github.com/ZhihengCV/Bayesian-Crowd-Counting)] 
- **[PGCNet]** Perspective-Guided Convolution Networks for Crowd Counting (**ICCV**) [[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Yan_Perspective-Guided_Convolution_Networks_for_Crowd_Counting_ICCV_2019_paper.pdf)][[code](https://github.com/Zhaoyi-Yan/PGCNet)]
- **[SACANet]** Crowd Counting on Images with Scale Variation and Isolated Clusters (**ICCVW**) [[paper](https://arxiv.org/abs/1909.03839)]
- **[McML]** Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting (**ACM MM**) [[paper](https://dl.acm.org/citation.cfm?doid=3343031.3350898)]
- **[DADNet]** DADNet: Dilated-Attention-Deformable ConvNet for Crowd Counting (**ACM MM**) [[paper](https://dl.acm.org/citation.cfm?doid=3343031.3350881)]
- **[MRNet]** Crowd Counting via Multi-layer Regression (**ACM MM**) [[paper](https://dl.acm.org/citation.cfm?doid=3343031.3350914)]
- **[MRCNet]** MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground Imagery (**BMVCW**)[[paper](https://arxiv.org/abs/1909.12743)]
- **[E3D]** Enhanced 3D convolutional networks for crowd counting (**BMVC**) [[paper](https://arxiv.org/abs/1908.04121)]
- **[OSSS]** One-Shot Scene-Specific Crowd Counting (**BMVC**) [[paper](https://bmvc2019.org/wp-content/uploads/papers/0209-paper.pdf)]
- **[RAZ-Net]** Recurrent Attentive Zooming for Joint Crowd Counting and Precise Localization (**CVPR**) [[paper](http://www.muyadong.com/paper/cvpr19_0484.pdf)]
- **[RDNet]** Density Map Regression Guided Detection Network for RGB-D Crowd Counting and Localization (**CVPR**) [[paper](http://openaccess.thecvf.com/content_CVPR_2019/papers/Lian_Density_Map_Regression_Guided_Detection_Network_for_RGB-D_Crowd_Counting_CVPR_2019_paper.pdf)][[code](https://github.com/svip-lab/RGBD-Counting)] 
- **[RRSP]** Residual Regression with Semantic Prior for Crowd Counting (**CVPR**) [[paper](http://openaccess.thecvf.com/content_CVPR_2019/papers/Wan_Residual_Regression_With_Semantic_Prior_for_Crowd_Counting_CVPR_2019_paper.pdf)][[code](https://github.com/jia-wan/ResidualRegression-pytorch)] 
- **[MVMS]** Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs (**CVPR**) [[paper](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Wide-Area_Crowd_Counting_via_Ground-Plane_Density_Maps_and_Multi-View_Fusion_CVPR_2019_paper.pdf)] [[Project](http://visal.cs.cityu.edu.hk/research/cvpr2019wacc/)] [[Dataset&Code](http://visal.cs.cityu.edu.hk/research/citystreet/)]
- **[AT-CFCN]** Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting (**CVPR**) [[paper](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhao_Leveraging_Heterogeneous_Auxiliary_Tasks_to_Assist_Crowd_Counting_CVPR_2019_paper.pdf)]
- **[TEDnet]** Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks (**CVPR**) [[paper](https://arxiv.org/abs/1903.00853)]
- **[CAN]** Context-Aware Crowd Counting (**CVPR**) [[paper](https://arxiv.org/pdf/1811.10452.pdf)] [[code](https://github.com/weizheliu/Context-Aware-Crowd-Counting)]
- **[PACNN]** Revisiting Perspective Information for Efficient Crowd Counting (**CVPR**)[[paper](https://arxiv.org/abs/1807.01989v3)]
- **[PSDDN]** Point in, Box out: Beyond Counting Persons in Crowds (**CVPR(oral)**)[[paper](https://arxiv.org/abs/1904.01333)]
- **[ADCrowdNet]** ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding (**CVPR**) [[paper](https://arxiv.org/abs/1811.11968)]
- **[CCWld, SFCN]** Learning from Synthetic Data for Crowd Counting in the Wild (**CVPR**) [[paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Learning_From_Synthetic_Data_for_Crowd_Counting_in_the_Wild_CVPR_2019_paper.pdf)] [[Project](https://gjy3035.github.io/GCC-CL/)] [[arxiv](https://arxiv.org/abs/1903.03303)] 
- **[DG-GAN]** Dense Crowd Counting Convolutional Neural Networks with Minimal Data using Semi-Supervised Dual-Goal Generative Adversarial Networks (**CVPRW**)[[paper](http://openaccess.thecvf.com/content_CVPRW_2019/papers/Weakly%20Supervised%20Learning%20for%20Real-World%20Computer%20Vision%20Applications/Olmschenk_Dense_Crowd_Counting_Convolutional_Neural_Networks_with_Minimal_Data_using_CVPRW_2019_paper.pdf)]
- **[GSP]** Global Sum Pooling: A Generalization Trick for Object Counting with Small Datasets of Large Images (**CVPRW**)[[paper](http://openaccess.thecvf.com/content_CVPRW_2019/papers/Deep%20Vision%20Workshop/Aich_Global_Sum_Pooling_A_Generalization_Trick_for_Object_Counting_with_CVPRW_2019_paper.pdf)]
- **[IA-DNN]** Inverse Attention Guided Deep Crowd Counting Network (**AVSS Best Paper**) [[paper](https://arxiv.org/abs/1907.01193)]
- **[MTCNet]** MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation (**AVSS**) [[paper](https://arxiv.org/abs/1908.08652)]
- **[CODA]** CODA: Counting Objects via Scale-aware Adversarial Density Adaption (**ICME**) [[paper](https://arxiv.org/abs/1903.10442)][[code](https://github.com/Willy0919/CODA)]
- **[LSTN]** Locality-Constrained Spatial Transformer Network for Video Crowd Counting (**ICME(oral)**) [[paper](https://arxiv.org/abs/1907.07911)]
- **[DRD]** Dynamic Region Division for Adaptive Learning Pedestrian Counting (**ICME**) [[paper](https://arxiv.org/abs/1908.03978)]
- **[MVSAN]** Crowd Counting via Multi-View Scale Aggregation Networks (**ICME**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8784912)]
- **[ASD]** Adaptive Scenario Discovery for Crowd Counting (**ICASSP**) [[paper](https://arxiv.org/abs/1812.02393)]
- **[SAAN]** Crowd Counting Using Scale-Aware Attention Networks (**WACV**) [[paper](http://www.cs.umanitoba.ca/~ywang/papers/wacv19.pdf)]
- **[SPN]** Scale Pyramid Network for Crowd Counting (**WACV**) [[paper](http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8642793)]
- **[GWTA-CCNN]** Almost Unsupervised Learning for Dense Crowd Counting (**AAAI**) [[paper](http://val.serc.iisc.ernet.in/valweb/papers/AAAI_2019_WTACNN.pdf)]
- **[GPC]** Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation (**IROS**) [[paper](https://arxiv.org/abs/1803.08805)]
- **[AM-CNN]** Attention to Head Locations for Crowd Counting (**ICIG**) [[paper](https://arxiv.org/abs/1806.10287)]
- **[CRDNet]** Cascaded Residual Density Network for Crowd Counting (**ICIP**) [[paper](https://arxiv.org/abs/2107.13718)]
### Journal
- **[D-ConvNet]** Nonlinear Regression via Deep Negative Correlation Learning (**T-PAMI**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8850209)](extension of [D-ConvNet](#D-ConvNet))[[Project](https://mmcheng.net/dncl/)]
- **[SL2R]** Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank (**T-PAMI**) [[paper](https://arxiv.org/abs/1902.06285)](extension of [L2R](#L2R))
- **[PCC-Net]** PCC Net: Perspective Crowd Counting via Spatial Convolutional Network (**T-CSVT**) [[paper](https://arxiv.org/abs/1905.10085)] [[code](https://github.com/gjy3035/PCC-Net)]
- **[Deem]** Scale-Aware Crowd Counting via Depth-Embedded Convolutional Neural Networks (**T-CSVT**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8846233)]
- **[CLPC]** Cross-Line Pedestrian Counting Based on Spatially-Consistent Two-Stage Local Crowd Density Estimation and Accumulation (**T-CSVT**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8295124)]
- **[MAN]** Mask-aware networks for crowd counting (**T-CSVT**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8796427)]
- Generalizing semi-supervised generative adversarial networks to regression using feature contrasting (**CVIU**)[[paper](https://arxiv.org/abs/1811.11269)]
- **[CCLL]** Crowd Counting With Limited Labeling Through Submodular Frame Selection (**T-ITS**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8360780)]
- **[GMLCNN]** Learning Multi-Level Density Maps for Crowd Counting (**T-NNLS**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8848475)]
- **[HA-CCN]** HA-CCN: Hierarchical Attention-based Crowd Counting Network (**TIP**) [[paper](https://arxiv.org/abs/1907.10255)]
- **[PaDNet]** PaDNet: Pan-Density Crowd Counting (**TIP**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8897143)]
- **[LDL]** Indoor Crowd Counting by Mixture of Gaussians Label Distribution Learning (**TIP**) [[paper](http://palm.seu.edu.cn/xgeng/files/tip19.pdf)]
- **[ACSPNet]** Atrous convolutions spatial pyramid network for crowd counting and density estimation (**Neurocomputing**) [[paper](https://www.sciencedirect.com/science/article/pii/S0925231219304059)]
- **[DDCN]** Removing background interference for crowd counting via de-background detail convolutional network (**Neurocomputing**) [[paper](https://www.sciencedirect.com/science/article/pii/S0925231218315042)]
- **[MRA-CNN]** Multi-resolution attention convolutional neural network for crowd counting (**Neurocomputing**) [[paper](https://www.sciencedirect.com/science/article/pii/S0925231218312542)]
- **[ACM-CNN]** Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs (**Neurocomputing**) [[paper](https://arxiv.org/abs/1908.02797)]
- **[SDA-MCNN]** Counting crowds using a scale-distribution-aware network and adaptive human-shaped kernel (**Neurocomputing**) [[paper](https://www.sciencedirect.com/science/article/pii/S0925231219314651)]
- **[SCAR]** SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting (**Neurocomputing**) [[paper](https://arxiv.org/abs/1908.03716)][[code](https://github.com/gjy3035/SCAR)]
### 2018
### Conference
- **[SANet]** Scale Aggregation Network for Accurate and Efficient Crowd Counting (**ECCV**) [[paper](http://openaccess.thecvf.com/content_ECCV_2018/papers/Xinkun_Cao_Scale_Aggregation_Network_ECCV_2018_paper.pdf)]
- **[ic-CNN]** Iterative Crowd Counting (**ECCV**) [[paper](https://arxiv.org/abs/1807.09959)]
- **[CL]** Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds (**ECCV**) [[paper](https://arxiv.org/abs/1808.01050)]
- **[LCFCN]** Where are the Blobs: Counting by Localization with Point Supervision (**ECCV**) [[paper](https://arxiv.org/abs/1807.09856)] [[code](https://github.com/ElementAI/LCFCN)]
- **[CSR]** CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes (**CVPR**) [[paper](https://arxiv.org/abs/1802.10062)] [[code](https://github.com/leeyeehoo/CSRNet-pytorch)]
- **[L2R]** Leveraging Unlabeled Data for Crowd Counting by Learning to Rank (**CVPR**) [[paper](https://arxiv.org/abs/1803.03095)] [[code](https://github.com/xialeiliu/CrowdCountingCVPR18)] 
- **[ACSCP]** Crowd Counting via Adversarial Cross-Scale Consistency Pursuit (**CVPR**) [[paper](http://openaccess.thecvf.com/content_cvpr_2018/papers/Shen_Crowd_Counting_via_CVPR_2018_paper.pdf)] [unofficial code: [PyTorch](https://github.com/RQuispeC/pytorch-ACSCP)]
- **[DecideNet]** DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density (**CVPR**) [[paper](https://arxiv.org/abs/1712.06679)]
- **[AMDCN]** An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting (**CVPRW**) [[paper](http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w6/Deb_An_Aggregated_Multicolumn_CVPR_2018_paper.pdf)] [[code](https://github.com/diptodip/counting)] 
- **[D-ConvNet]** Crowd Counting with Deep Negative Correlation Learning (**CVPR**) [[paper](http://openaccess.thecvf.com/content_cvpr_2018/papers/Shi_Crowd_Counting_With_CVPR_2018_paper.pdf)] [[code](https://github.com/shizenglin/Deep-NCL)]
- **[IG-CNN]** Divide and Grow: Capturing Huge Diversity in Crowd Images with
Incrementally Growing CNN (**CVPR**) [[paper](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sam_Divide_and_Grow_CVPR_2018_paper.pdf)]
- **[SCNet]** In Defense of Single-column Networks for Crowd Counting (**BMVC**) [[paper](https://arxiv.org/abs/1808.06133)]
- **[AFP]** Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid (**BMVC**) [[paper](https://arxiv.org/abs/1805.06115)]
- **[DRSAN]** Crowd Counting using Deep Recurrent Spatial-Aware Network (**IJCAI**) [[paper](https://arxiv.org/abs/1807.00601)]
- **[TDF-CNN]** Top-Down Feedback for Crowd Counting Convolutional Neural Network (**AAAI**) [[paper](https://arxiv.org/abs/1807.08881)]
- **[CAC]** Class-Agnostic Counting (**ACCV**) [[paper](https://arxiv.org/abs/1811.00472)] [[code](https://github.com/erikalu/class-agnostic-counting)]
- **[A-CCNN]** A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting (**ICIP**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8451399)]
- Crowd Counting with Fully Convolutional Neural Network (**ICIP**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8451787)]
- **[MS-GAN]** Multi-scale Generative Adversarial Networks for Crowd Counting (**ICPR**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8545683)]
- **[DR-ResNet]** A Deeply-Recursive Convolutional Network for Crowd Counting (**ICASSP**) [[paper](https://arxiv.org/abs/1805.05633)]
- **[GAN-MTR]** Crowd Counting With Minimal Data Using Generative Adversarial Networks For Multiple Target Regression (**WACV**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354235)]
- **[SaCNN]** Crowd counting via scale-adaptive convolutional neural network (**WACV**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354231)] [[code](https://github.com/miao0913/SaCNN-CrowdCounting-Tencent_Youtu)]
### Journal
- **[BSAD]** Body Structure Aware Deep Crowd Counting (**TIP**) [[paper](http://mac.xmu.edu.cn/rrji/papers/IP%202018-Body.pdf)]
- **[NetVLAD]** Multiscale Multitask Deep NetVLAD for Crowd Counting (**TII**) [[paper](https://staff.fnwi.uva.nl/z.shi/files/counting-netvlad.pdf)] [[code](https://github.com/shizenglin/Multitask-Multiscale-Deep-NetVLAD)]
- **[W-VLAD]** Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps (**T-CSVT**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7778134)]
- **[Improved SaCNN]** Improved Crowd Counting Method Based on Scale-Adaptive Convolutional Neural Network (**IEEE Access**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8643345)]
- **[DA-Net]** DA-Net: Learning the Fine-Grained Density Distribution With Deformation Aggregation Network (**IEEE Access**) [[paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8497050)][[code](https://github.com/BigTeacher-777/DA-Net)]
### 2017
### Conference
- **[Switching CNN]** Switching Convolutional Neural Network for Crowd Counting (**CVPR**) [[paper](https://arxiv.org/abs/1708.00199)] [[code](https://github.com/val-iisc/crowd-counting-scnn)]
- **[CP-CNN]** Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs (**ICCV**) [[paper](https://arxiv.org/abs/1708.00953)]
- **[ConvLSTM]** Spatiotemporal Modeling for Crowd Counting in Videos (**ICCV**) [[paper](http://openaccess.thecvf.com/content_ICCV_2017/papers/Xiong_Spatiotemporal_Modeling_for_ICCV_2017_paper.pdf)]
- **[CMTL]** CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting (**AVSS**) [[paper](https://arxiv.org/abs/1707.09605)] [[code](https://github.com/svishwa/crowdcount-cascaded-mtl)]
- **[ResnetCrowd]** ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification (**AVSS**) [[paper](https://arxiv.org/abs/1705.10698)]
- **[ACNN]** Incorporating Side Information by Adaptive Convolution (**NeurIPS**) [[paper](http://papers.nips.cc/paper/6976-incorporating-side-information-by-adaptive-convolution.pdf)][[Project](http://visal.cs.cityu.edu.hk/research/acnn/)]
- **[MSCNN]** Multi-scale Convolution Neural Networks for Crowd Counting (**ICIP**) [[paper](https://arxiv.org/abs/1702.02359)] [[code](https://github.com/Ling-Bao/mscnn)]
- **[FCNCC]** Fully Convolutional Crowd Counting On Highly Congested Scenes (**VISAPP**) [[paper](https://arxiv.org/abs/1612.00220)]
### Journal
- **[DAL-SVR]** Boosting deep attribute learning via support vector regression for fast moving crowd counting (**PR Letters**) [[paper](https://www.sciencedirect.com/science/article/pii/S0167865517304415)]
- **[CNN-MRF]** Image Crowd Counting Using Convolutional Neural Network and Markov Random Field (**JACII**) [[paper](https://arxiv.org/abs/1706.03686)] [[code](https://github.com/hankong/crowd-counting)]![GitH