# Multi-scale Convolutional Neural Networks for Crowd Counting

arXiv: https://arxiv.org/abs/1702.02359 · HTML: https://mlsanity.com/paper/1702.02359/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2017.

## Built on by (most cited first, 26 of 26)

- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)
- [STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning](https://mlsanity.com/paper/2308.10468/) (2023)
- [Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark](https://mlsanity.com/paper/2105.02440/) (2021)
- [Gramformer: Learning Crowd Counting via Graph-Modulated Transformer](https://mlsanity.com/paper/2401.03870/) (2024)
- [Direct Measure Matching for Crowd Counting](https://mlsanity.com/paper/2107.01558/) (2021)
- [Semi-supervised Crowd Counting via Density Agency](https://mlsanity.com/paper/2209.02955/) (2022)
- [Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives](https://mlsanity.com/paper/2209.07271/) (2022)
- [CountFormer: Multi-View Crowd Counting Transformer](https://mlsanity.com/paper/2407.02047/) (2024)
- [Multiscale Crowd Counting and Localization By Multitask Point Supervision](https://mlsanity.com/paper/2202.09942/) (2022)
- [Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling](https://mlsanity.com/paper/2402.15297/) (2024)
- [LCDnet: A Lightweight Crowd Density Estimation Model for Real-time Video Surveillance](https://mlsanity.com/paper/2302.05374/) (2023)
- [Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting](https://mlsanity.com/paper/2108.08784/) (2021)
- [CLIP: Train Faster with Less Data](https://mlsanity.com/paper/2212.01452/) (2022)
- [Crowd Counting in Harsh Weather using Image Denoising with Pix2Pix GANs](https://mlsanity.com/paper/2310.07245/) (2023)
- [Enhancing and Dissecting Crowd Counting By Synthetic Data](https://mlsanity.com/paper/2201.08992/) (2022)
- [DroneNet: Crowd Density Estimation using Self-ONNs for Drones](https://mlsanity.com/paper/2211.07137/) (2022)
- [Cascaded Residual Density Network for Crowd Counting](https://mlsanity.com/paper/2107.13718/) (2021)
- [Visual Crowd Analysis: Open Research Problems](https://mlsanity.com/paper/2308.10677/) (2023)
- [Multimodal Crowd Counting with Pix2Pix GANs](https://mlsanity.com/paper/2401.07591/) (2024)
- [Scale-Aware Network with Regional and Semantic Attentions for Crowd Counting under Cluttered Background](https://mlsanity.com/paper/2101.01479/) (2021)
- [BBA-net: A bi-branch attention network for crowd counting](https://mlsanity.com/paper/2201.08983/) (2022)
- [Curriculum for Crowd Counting -- Is it Worthy?](https://mlsanity.com/paper/2401.07586/) (2024)
- [Weakly-supervised multi-class object localization using only object counts as labels](https://mlsanity.com/paper/2102.11743/) (2021)
- [Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches](https://mlsanity.com/paper/2204.04653/) (2022)
- [Crowd Density Estimation using Imperfect Labels](https://mlsanity.com/paper/2212.01450/) (2022)
- [Bound Tightening Network for Robust Crowd Counting](https://mlsanity.com/paper/2409.19146/) (2024)

## Abstract (arXiv)

Crowd counting on static images is a challenging problem due to scale variations. Recently deep neural networks have been shown to be effective in this task. However, existing neural-networks-based methods often use the multi-column or multi-network model to extract the scale-relevant features, which is more complicated for optimization and computation wasting. To this end, we propose a novel multi-scale convolutional neural network (MSCNN) for single image crowd counting. Based on the multi-scale blobs, the network is able to generate scale-relevant features for higher crowd counting performances in a single-column architecture, which is both accuracy and cost effective for practical applications. Complemental results show that our method outperforms the state-of-the-art methods on both accuracy and robustness with far less number of parameters.