# Fine-Grained Crowd Counting

arXiv: https://arxiv.org/abs/2007.06146 · HTML: https://mlsanity.com/paper/2007.06146/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark](https://mlsanity.com/paper/2107.08645/) (2021)
- [Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher](https://mlsanity.com/paper/2206.05717/) (2022)
- [Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer](https://mlsanity.com/paper/2108.00584/) (2021)
- [Learning Discriminative Features for Crowd Counting](https://mlsanity.com/paper/2311.04509/) (2023)
- [Shifted Autoencoders for Point Annotation Restoration in Object Counting](https://mlsanity.com/paper/2312.07190/) (2023)
- [Counting with Adaptive Auxiliary Learning](https://mlsanity.com/paper/2203.04061/) (2022)
- [Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localization](https://mlsanity.com/paper/2503.12441/) (2025)
- [Fine-Grained Counting with Crowd-Sourced Supervision](https://mlsanity.com/paper/2205.11398/) (2022)
- [Tolerating Annotation Displacement in Dense Object Counting via Point Annotation Probability Map](https://mlsanity.com/paper/2308.00530/) (2023)

## Abstract (arXiv)

Current crowd counting algorithms are only concerned about the number of people in an image, which lacks low-level fine-grained information of the crowd. For many practical applications, the total number of people in an image is not as useful as the number of people in each sub-category. E.g., knowing the number of people waiting inline or browsing can help retail stores; knowing the number of people standing/sitting can help restaurants/cafeterias; knowing the number of violent/non-violent people can help police in crowd management. In this paper, we propose fine-grained crowd counting, which differentiates a crowd into categories based on the low-level behavior attributes of the individuals (e.g. standing/sitting or violent behavior) and then counts the number of people in each category. To enable research in this area, we construct a new dataset of four real-world fine-grained counting tasks: traveling direction on a sidewalk, standing or sitting, waiting in line or not, and exhibiting violent behavior or not. Since the appearance features of different crowd categories are similar, the challenge of fine-grained crowd counting is to effectively utilize contextual information to distinguish between categories. We propose a two branch architecture, consisting of a density map estimation branch and a semantic segmentation branch. We propose two refinement strategies for improving the predictions of the two branches. First, to encode contextual information, we propose feature propagation guided by the density map prediction, which eliminates the effect of background features during propagation. Second, we propose a complementary attention model to share information between the two branches. Experiment results confirm the effectiveness of our method.