# A Spatio-Temporal Attentive Network for Video-Based Crowd Counting

arXiv: https://arxiv.org/abs/2208.11339 · HTML: https://mlsanity.com/paper/2208.11339/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 24 Aug 2022.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Attention Augmented Convolutional Networks](https://mlsanity.com/paper/1904.09925/) (2019)
- [Meshed-Memory Transformer for Image Captioning](https://mlsanity.com/paper/1912.08226/) (2019)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videos](https://mlsanity.com/paper/1812.05538/) (2018)
- [Where are the Blobs: Counting by Localization with Point Supervision](https://mlsanity.com/paper/1807.09856/) (2018)
- [Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders](https://mlsanity.com/paper/2008.05231/) (2020)
- [Crowd Counting with Deep Structured Scale Integration Network](https://mlsanity.com/paper/1908.08692/) (2019)
- [Count-ception: Counting by Fully Convolutional Redundant Counting](https://mlsanity.com/paper/1703.08710/) (2017)
- [Locality-constrained Spatial Transformer Network for Video Crowd Counting](https://mlsanity.com/paper/1907.07911/) (2019)
- [Image Captioning through Image Transformer](https://mlsanity.com/paper/2004.14231/) (2020)
- [Spatiotemporal Modeling for Crowd Counting in Videos](https://mlsanity.com/paper/1707.07890/) (2017)
- [Learning Visual Question Answering by Bootstrapping Hard Attention](https://mlsanity.com/paper/1808.00300/) (2018)
- [Transformer Reasoning Network for Image-Text Matching and Retrieval](https://mlsanity.com/paper/2004.09144/) (2020)
- [Estimating People Flows to Better Count Them in Crowded Scenes](https://mlsanity.com/paper/1911.10782/) (2019)
- [Counting People by Estimating People Flows](https://mlsanity.com/paper/2012.00452/) (2020)
- [Virtual to Real adaptation of Pedestrian Detectors](https://mlsanity.com/paper/2001.03032/) (2020)
- [Fast Video Crowd Counting with a Temporal Aware Network](https://mlsanity.com/paper/1907.02198/) (2019)
- [Multi-Camera Vehicle Counting Using Edge-AI](https://mlsanity.com/paper/2106.02842/) (2021)

## Built on by (most cited first, 4 of 4)

- [A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches](https://mlsanity.com/paper/2501.19184/) (2025)
- [CrowdSim2: an Open Synthetic Benchmark for Object Detectors](https://mlsanity.com/paper/2304.05090/) (2023)
- [Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark](https://mlsanity.com/paper/2411.13056/) (2024)
- [Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods](https://mlsanity.com/paper/2304.13403/) (2023)

## Abstract (arXiv)

Automatic people counting from images has recently drawn attention for urban monitoring in modern Smart Cities due to the ubiquity of surveillance camera networks. Current computer vision techniques rely on deep learning-based algorithms that estimate pedestrian densities in still, individual images. Only a bunch of works take advantage of temporal consistency in video sequences. In this work, we propose a spatio-temporal attentive neural network to estimate the number of pedestrians from surveillance videos. By taking advantage of the temporal correlation between consecutive frames, we lowered state-of-the-art count error by 5% and localization error by 7.5% on the widely-used FDST benchmark.