# Multiscale Crowd Counting and Localization By Multitask Point Supervision

arXiv: https://arxiv.org/abs/2202.09942 · HTML: https://mlsanity.com/paper/2202.09942/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 21 Feb 2022.

## Builds on (most cited first, 11 of 11)

- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Switching Convolutional Neural Network for Crowd Counting](https://mlsanity.com/paper/1708.00199/) (2017)
- [Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection](https://mlsanity.com/paper/1906.07538/) (2019)
- [Point in, Box out: Beyond Counting Persons in Crowds](https://mlsanity.com/paper/1904.01333/) (2019)
- [Where are the Blobs: Counting by Localization with Point Supervision](https://mlsanity.com/paper/1807.09856/) (2018)
- [CrowdNet: A Deep Convolutional Network for Dense Crowd Counting](https://mlsanity.com/paper/1608.06197/) (2016)
- [CNN-based Density Estimation and Crowd Counting: A Survey](https://mlsanity.com/paper/2003.12783/) (2020)
- [A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds](https://mlsanity.com/paper/2007.12831/) (2020)
- [Multi-scale Convolutional Neural Networks for Crowd Counting](https://mlsanity.com/paper/1702.02359/) (2017)
- [People, Penguins and Petri Dishes: Adapting Object Counting Models To New Visual Domains And Object Types Without Forgetting](https://mlsanity.com/paper/1711.05586/) (2017)

## Built on by (most cited first, 8 of 8)

- [Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision](https://mlsanity.com/paper/2304.01484/) (2023)
- [Pointly-Supervised Panoptic Segmentation](https://mlsanity.com/paper/2210.13950/) (2022)
- [From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision](https://mlsanity.com/paper/2412.11154/) (2024)
- [RGB-D Indiscernible Object Counting in Underwater Scenes](https://mlsanity.com/paper/2304.11677/) (2023)
- [Cross-head Supervision for Crowd Counting with Noisy Annotations](https://mlsanity.com/paper/2303.09245/) (2023)
- [AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis](https://mlsanity.com/paper/2502.01785/) (2025)
- [Context-aware Pedestrian Trajectory Prediction with Multimodal Transformer](https://mlsanity.com/paper/2307.03786/) (2023)
- [Continual Learning for Out-of-Distribution Pedestrian Detection](https://mlsanity.com/paper/2306.15117/) (2023)

## Abstract (arXiv)

We propose a multitask approach for crowd counting and person localization in a unified framework. As the detection and localization tasks are well-correlated and can be jointly tackled, our model benefits from a multitask solution by learning multiscale representations of encoded crowd images, and subsequently fusing them. In contrast to the relatively more popular density-based methods, our model uses point supervision to allow for crowd locations to be accurately identified. We test our model on two popular crowd counting datasets, ShanghaiTech A and B, and demonstrate that our method achieves strong results on both counting and localization tasks, with MSE measures of 110.7 and 15.0 for crowd counting and AP measures of 0.71 and 0.75 for localization, on ShanghaiTech A and B respectively. Our detailed ablation experiments show the impact of our multiscale approach as well as the effectiveness of the fusion module embedded in our network. Our code is available at: https://github.com/RCVLab-AiimLab/crowd_counting.