# Context-Aware Crowd Counting

arXiv: https://arxiv.org/abs/1811.10452 · HTML: https://mlsanity.com/paper/1811.10452/

## Key facts

- Cited by 150 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2018.

## Built on by (most cited first, 30 of 150)

- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)
- [TransCrowd: weakly-supervised crowd counting with transformers](https://mlsanity.com/paper/2104.09116/) (2021)
- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [Few-shot Object Counting and Detection](https://mlsanity.com/paper/2207.10988/) (2022)
- [DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting](https://mlsanity.com/paper/2404.16622/) (2024)
- [VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting](https://mlsanity.com/paper/2312.16580/) (2023)
- [TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting](https://mlsanity.com/paper/2204.01018/) (2022)
- [STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning](https://mlsanity.com/paper/2308.10468/) (2023)
- [Point-Query Quadtree for Crowd Counting, Localization, and More](https://mlsanity.com/paper/2308.13814/) (2023)
- [Harnessing Perceptual Adversarial Patches for Crowd Counting](https://mlsanity.com/paper/2109.07986/) (2021)
- [Spatial Uncertainty-Aware Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2107.13271/) (2021)
- [Focal Inverse Distance Transform Maps for Crowd Localization](https://mlsanity.com/paper/2102.07925/) (2021)
- [Exemplar Free Class Agnostic Counting](https://mlsanity.com/paper/2205.14212/) (2022)
- [Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark](https://mlsanity.com/paper/2105.02440/) (2021)
- [CCTrans: Simplifying and Improving Crowd Counting with Transformer](https://mlsanity.com/paper/2109.14483/) (2021)
- [Cross-View Cross-Scene Multi-View Crowd Counting](https://mlsanity.com/paper/2205.01551/) (2022)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Calibrating Uncertainty for Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2308.09887/) (2023)
- [A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation](https://mlsanity.com/paper/2409.18686/) (2024)
- [Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting](https://mlsanity.com/paper/2107.12619/) (2021)
- [CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models](https://mlsanity.com/paper/2303.12790/) (2023)
- [Teach CLIP to Develop a Number Sense for Ordinal Regression](https://mlsanity.com/paper/2408.03574/) (2024)
- [Direct Measure Matching for Crowd Counting](https://mlsanity.com/paper/2107.01558/) (2021)
- [Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives](https://mlsanity.com/paper/2209.07271/) (2022)
- [Regressor-Segmenter Mutual Prompt Learning for Crowd Counting](https://mlsanity.com/paper/2312.01711/) (2023)
- [Crowd Counting via Perspective-Guided Fractional-Dilation Convolution](https://mlsanity.com/paper/2107.03665/) (2021)
- [Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches](https://mlsanity.com/paper/2206.08016/) (2022)

## Abstract (arXiv)

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. They typically use the same filters over the whole image or over large image patches. Only then do they estimate local scale to compensate for perspective distortion. This is typically achieved by training an auxiliary classifier to select, for predefined image patches, the best kernel size among a limited set of choices. As such, these methods are not end-to-end trainable and restricted in the scope of context they can leverage. In this paper, we introduce an end-to-end trainable deep architecture that combines features obtained using multiple receptive field sizes and learns the importance of each such feature at each image location. In other words, our approach adaptively encodes the scale of the contextual information required to accurately predict crowd density. This yields an algorithm that outperforms state-of-the-art crowd counting methods, especially when perspective effects are strong.