# Crowd Counting using Deep Recurrent Spatial-Aware Network

arXiv: https://arxiv.org/abs/1807.00601 · HTML: https://mlsanity.com/paper/1807.00601/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2018.

## Built on by (most cited first, 21 of 21)

- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey](https://mlsanity.com/paper/2108.11510/) (2021)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Gramformer: Learning Crowd Counting via Graph-Modulated Transformer](https://mlsanity.com/paper/2401.03870/) (2024)
- [Crowd Counting via Perspective-Guided Fractional-Dilation Convolution](https://mlsanity.com/paper/2107.03665/) (2021)
- [Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting](https://mlsanity.com/paper/2108.08023/) (2021)
- [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)
- [Multi-modal Crowd Counting via a Broker Modality](https://mlsanity.com/paper/2407.07518/) (2024)
- [Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation](https://mlsanity.com/paper/2101.12439/) (2021)
- [Focus for Free in Density-Based Counting](https://mlsanity.com/paper/2306.05129/) (2023)
- [Multi-modal Crowd Counting via Modal Emulation](https://mlsanity.com/paper/2407.19491/) (2024)
- [Understanding the Ability of Deep Neural Networks to Count Connected Components in Images](https://mlsanity.com/paper/2101.01386/) (2021)
- [Multi-Level Attentive Convoluntional Neural Network for Crowd Counting](https://mlsanity.com/paper/2105.11422/) (2021)
- [Counting with Adaptive Auxiliary Learning](https://mlsanity.com/paper/2203.04061/) (2022)
- [Multi-channel Deep Supervision for Crowd Counting](https://mlsanity.com/paper/2103.09553/) (2021)
- [Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification](https://mlsanity.com/paper/2105.09684/) (2021)
- [PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting](https://mlsanity.com/paper/2111.00406/) (2021)
- [Inception-Based Crowd Counting -- Being Fast while Remaining Accurate](https://mlsanity.com/paper/2210.09796/) (2022)
- [One-Shot Crowd Counting With Density Guidance For Scene Adaptation](https://mlsanity.com/paper/2602.07955/) (2026)

## Abstract (arXiv)

Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera's perspective that causes huge appearance variations in people's scales and rotations. Conventional methods address such challenges by resorting to fixed multi-scale architectures that are often unable to cover the largely varied scales while ignoring the rotation variations. In this paper, we propose a unified neural network framework, named Deep Recurrent Spatial-Aware Network, which adaptively addresses the two issues in a learnable spatial transform module with a region-wise refinement process. Specifically, our framework incorporates a Recurrent Spatial-Aware Refinement (RSAR) module iteratively conducting two components: i) a Spatial Transformer Network that dynamically locates an attentional region from the crowd density map and transforms it to the suitable scale and rotation for optimal crowd estimation; ii) a Local Refinement Network that refines the density map of the attended region with residual learning. Extensive experiments on four challenging benchmarks show the effectiveness of our approach. Specifically, comparing with the existing best-performing methods, we achieve an improvement of 12% on the largest dataset WorldExpo'10 and 22.8% on the most challenging dataset UCF_CC_50.