Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/taohan10200/Awesome-Crowd-Localization
Awesome Crowd Localization
https://github.com/taohan10200/Awesome-Crowd-Localization
List: Awesome-Crowd-Localization
Last synced: 3 months ago
JSON representation
Awesome Crowd Localization
- Host: GitHub
- URL: https://github.com/taohan10200/Awesome-Crowd-Localization
- Owner: taohan10200
- Created: 2020-12-18T02:00:48.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2022-02-17T09:35:51.000Z (over 2 years ago)
- Last Synced: 2024-05-20T00:00:47.878Z (6 months ago)
- Size: 74.2 KB
- Stars: 37
- Watchers: 4
- Forks: 6
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- Awesome-Crowd-Counting - Crowd Localization - Public-Safety-in-Vision), Dense/Small/Tiny Object Detection (Misc / Related Tasks)
- ultimate-awesome - Awesome-Crowd-Localization - Awesome Crowd Localization. (Other Lists / PowerShell Lists)
README
# Awesome-Crowd-Localization
Awesome Crowd Localization
## Contents
* [Misc](#misc)
* [Datasets](#datasets)
* [Papers](#papers)
* [Leaderboard](#leaderboard)
## Misc
### Relaetd Tasks
- [Crowd Counting](https://github.com/gjy3035/Awesome-Crowd-Counting)
- Crowd Analysis
- [Video Surveillance](https://github.com/CommissarMa/Awesome-Public-Safety-in-Vision)
- Dense/Small/Tiny Object Detection
### Challenge
- NWPU-Crowd Localization: [Link](https://www.crowdbenchmark.com/nwpucrowdloc.html)
- The 1st Tiny Object Detection Challenge: [Link](https://github.com/ucas-vg/TinyBenchmark)
### Metrics
- mAP, mAR in [RAZNet](http://www.muyadong.com/paper/cvpr19_0484.pdf) (namely key point evaluation in COCO: fixed sigma)
- F1-m, Precision, Recall in [NWPU-Crowd](https://arxiv.org/abs/2001.03360) (scale-aware sigma)
- MLE in [LSC-CNN](https://arxiv.org/abs/1906.07538) (distance measure)
## Datasets
- NWPU-Crowd (dot, box)
- JHU-CROWD (dot, size)
- FDST (dot, box)
- Head Tracking 21 (dot, box, id) [[Download]](https://motchallenge.net/method/HT=2&chl=21)
## Papers
### Arxiv
- **[DCST]** Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer [[paper]](https://arxiv.org/abs/2108.00584)
- **[GNA]** Video Crowd Localization with Multi-focus Gaussian Neighbor Attention and a Large-Scale Benchmark [[paper]](https://arxiv.org/pdf/2107.08645.pdf)
- **[SCALNet]** Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization [[paper]](https://arxiv.org/abs/2104.12505) [[code]](https://github.com/WangyiNTU/SCALNet)
- **[FIDTM]** Focal Inverse Distance Transform Maps for Crowd Localization and Counting in Dense Crowd [[paper]](https://arxiv.org/pdf/2102.07925.pdf) [[code]](https://github.com/dk-liang/FIDTM)
- **[RDTM]** Reciprocal Distance Transform Maps for Crowd Counting and People Localization in Dense Crowd [[paper]](https://arxiv.org/abs/2102.07925) [[code]](https://github.com/dk-liang/RDTM)
- Counting and Locating High-Density Objects Using Convolutional Neural Network [[paper](https://arxiv.org/pdf/2102.04366.pdf)]
- **[IIM]** Learning Independent Instance Maps for Crowd Localization [[paper](https://arxiv.org/pdf/2012.04164.pdf)] [[code](https://github.com/taohan10200/IIM)]
- **[AutoScale]** Autoscale: learning to scale for crowd counting [[paper](https://arxiv.org/pdf/1912.09632.pdf)] [[code](https://github.com/dk-liang/AutoScale)]
- A Strong Baseline for Crowd Counting and Unsupervised People Localization [[paper](https://arxiv.org/abs/2011.03725)]
- 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)]
### 2021
- **[SA-InterNet]** A-InterNet: Scale-Aware Interaction Network for Joint Crowd Counting and Localization (**PRVC**) [[paper]](https://link.springer.com/chapter/10.1007/978-3-030-88004-0_17)
- A smartly simple way for joint crowd counting and localization (**Neurocomputing**) [[aper]](https://www.sciencedirect.com/science/article/pii/S0925231221009796)
- A Generalized Loss Function for Crowd Counting and Localization (**CVPR**) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/html/Wan_A_Generalized_Loss_Function_for_Crowd_Counting_and_Localization_CVPR_2021_paper.html)
- **[ P2PNet]** Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework (**ICCV**) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/html/Song_Rethinking_Counting_and_Localization_in_Crowds_A_Purely_Point-Based_Framework_ICCV_2021_paper.html)
- **[D2CNet]** Decoupled Two-Stage Crowd Counting and Beyond (**TIP**) [[paper]](https://ieeexplore.ieee.org/document/9347700) [[code]](https://git.io/d2cnet)
- **[Crowd-SDNet]** A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds (**TIP**) [[paper]](https://ieeexplore.ieee.org/abstract/document/9347744/) [[code]]( https://github.com/WangyiNTU/Point-supervised-crowd-detection)
- **[TopoCount]** Localization in the Crowd with Topological Constraints (**AAAI2021**) [[paper](https://arxiv.org/abs/2012.12482)][[code](https://github.com/ShahiraAbousamra/TopoCount)]
### 2020
- **[DD-CNN]** Going Beyond the Regression Paradigm with Accurate Dot Prediction for Dense Crowds (**WACV**) [[paper]](https://ieeexplore.ieee.org/abstract/document/9093386)
- **[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/)]
- **[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)]
- Scale Match for Tiny Person Detection (**WACV**) [[paper](https://openaccess.thecvf.com/content_WACV_2020/papers/Yu_Scale_Match_for_Tiny_Person_Detection_WACV_2020_paper.pdf)][[code](https://github.com/ucas-vg/TinyBenchmark)]
### 2019
- Density Map Regression Guided Detection Network for RGB-D Crowd Counting and Localization (**CVPR**) [[paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Lian_Density_Map_Regression_Guided_Detection_Network_for_RGB-D_Crowd_Counting_CVPR_2019_paper.pdf)
- Point in, Box out: Beyond Counting Persons in Crowds (**CVPR**) [[paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Point_in_Box_Out_Beyond_Counting_Persons_in_Crowds_CVPR_2019_paper.pdf)]
- **[RAZ_Loc]** Recurrent attentive zooming for joint crowd counting and precise localization (**CVPR**) [[paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Recurrent_Attentive_Zooming_for_Joint_Crowd_Counting_and_Precise_Localization_CVPR_2019_paper.pdf)] [[Reproduction_code](https://github.com/gjy3035/NWPU-Crowd-Sample-Code-for-Localization)]
- **[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)]
### 2018
- **[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)]
- SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network (**ECCV**) [[paper](https://openaccess.thecvf.com/content_ECCV_2018/papers/Yongqiang_Zhang_SOD-MTGAN_Small_Object_ECCV_2018_paper.pdf)]
### 2017
- Focal Loss for Dense Object Detection (**ICCV**) [[paper](https://openaccess.thecvf.com/content_ICCV_2017/papers/Lin_Focal_Loss_for_ICCV_2017_paper.pdf)]
- **[TinyFaces]** Finding tiny faces (**CVPR**) [[paper](https://openaccess.thecvf.com/content_cvpr_2017/papers/Hu_Finding_Tiny_Faces_CVPR_2017_paper.pdf)]
- Perceptual Generative Adversarial Networks for Small Object Detection (**CVPR**) [[paper](https://openaccess.thecvf.com/content_cvpr_2017/papers/Li_Perceptual_Generative_Adversarial_CVPR_2017_paper.pdf)]
### 2015
- Small Instance Detection by Integer Programming on Object Density Maps, (**CVPR**) [[paper ]](https://openaccess.thecvf.com/content_cvpr_2015/papers/Ma_Small_Instance_Detection_2015_CVPR_paper.pdf)
- End-to-end people detection in crowded scenes (**CVPR**) [[paper](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Stewart_End-To-End_People_Detection_CVPR_2016_paper.pdf)] [[code](https://github.com/gramuah/ccnn)]
- **[Faster-RCNN]** Towards real-time object detection with region proposal networks (**CVPR**) [[paper](http://agamenon.tsc.uah.es/Investigacion/gram/publications/eccv2016-onoro.pdf)] [[code](https://github.com/gramuah/ccnn)]
## Leaderboard
### NWPU
More detailed results are in this [link](https://www.crowdbenchmark.com/nwpucrowdloc.html).
| Year--Conference/Journal |Methods |Backbone |F1-measure|Precise|Recall| A0~A5 | Avg. |
| --------------------------|----------|---------- | ------- | --------| -------|------------------------- |-------|
| 2015--NIPS | [Faster RCNN](#RCNN) |ResNet-101| 6.7 | 95.8 | 3.5 | 0/0.002/0.4/7.9/37.2/63.5 | 18.2 |
| 2017--CVPR | [TinyFaces](#TinyFaces) |ResNet-101| 56.7 | 52.9 | 61.1 | 4.2/22.6/59.1/90.0/93.1/89.6 | 59.8 |
| 2019--arXiv | [VGG+GPR](#VGG) |VGG-16 | 52.5 | 55.8 | 49.6 | 3.1/27.2/49.1/68.7/49.8/26.3 | 37.4 |
| 2019--CVPR | [RAZ_Loc](#RAZ_Loc) |VGG-16 | 59.8 | 66.6 | 54.3 | 3.1/27.2/49.1/68.7/49.8/26.3 | 42.4 |
| 2021--TIP | [Crowd-SDNet](#Crowd-SDNet) |ResNet-50 | 63.7 | 65.1 | 62.4 | 7.3/43.7/62.4/75.7/71.2/70.2 | 55.1 |
| 2021--AAAI | [TopoCount](#TopoCount) |VGG-16 | 69.2 | 68.3 | 70.1 | 5.7/39.1/72.2/85.7/87.3/89.7 | 63.3 |
| 2021--arXiv | [RDTM](#RDTM) |VGG-16 | 69.9 | 75.1 | 65.4 | 11.5/46.3/68.5/74.9/54.6/18.2 | 45.7 |
| 2021--arXiv | [SCALNet](#SCALNet) |DLA-34 | 69.1 |69.2 |69.0 | - | - |
| 2021--TIP | [D2CNet](#D2CNet) |VGG-16 | 70.0 | 74.1 | 66.2 | 11.3/50.2/67.8/74.5/69.5/76.5| 58.3 |
| 2020--arXiv | [IIM](#IIM) |VGG-16 | 73.2 | 77.9 | 69.2 | 10.1/44.1/70.7/82.4/83.0/61.4| 58.7 |
| 2020--arXiv | [IIM](#IIM) |HRNet | 76.2 | 81.3 | 71.7 | 12.0/46.0/73.2/85.5/86.7/64.3| 61.3 |