mlsanityData to 7 Oct 2026

Multiscale Crowd Counting and Localization By Multitask Point Supervision

arXiv 2202.09942 ↗First posted 21 Feb 2022cs.CV cs.AIcited by 8

Not on the map. Why?

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.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 11 of its 24 references that are in the map. First posted on arXiv 21 Feb 2022.

Builds on

11 of 24 references.

References · 11

  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  2. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  3. 2017Switching Convolutional Neural Network for Crowd Countingcited by 93
  4. 2019Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detectioncited by 73
  5. 2019Point in, Box out: Beyond Counting Persons in Crowdscited by 62
  6. 2018Where are the Blobs: Counting by Localization with Point Supervisioncited by 54
  7. 2016CrowdNet: A Deep Convolutional Network for Dense Crowd Countingcited by 52
  8. 2020CNN-based Density Estimation and Crowd Counting: A Surveycited by 43
  9. 2020A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowdscited by 36
  10. 2017Multi-scale Convolutional Neural Networks for Crowd Countingcited by 26
  11. 2017People, Penguins and Petri Dishes: Adapting Object Counting Models To New Visual Domains And Object Types Without Forgettingcited by 25

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5; 2024: 1; 2025: 1.

8 papers.

  1. 2023Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervisioncited by 50
  2. 2022Pointly-Supervised Panoptic Segmentationcited by 20
  3. 2024From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervisioncited by 10
  4. 2023RGB-D Indiscernible Object Counting in Underwater Scenescited by 9
  5. 2023Cross-head Supervision for Crowd Counting with Noisy Annotationscited by 7
  6. 2025AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysiscited by 7
  7. 2023Context-aware Pedestrian Trajectory Prediction with Multimodal Transformercited by 4
  8. 2023Continual Learning for Out-of-Distribution Pedestrian Detectioncited by 0