# Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark

arXiv: https://arxiv.org/abs/2107.08645 · HTML: https://mlsanity.com/paper/2107.08645/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 87 references that are in the map.
- First posted on arXiv 19 Jul 2021.

## Builds on (most cited first, 30 of 52)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Local Relation Networks for Image Recognition](https://mlsanity.com/paper/1904.11491/) (2019)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [Distribution Matching for Crowd Counting](https://mlsanity.com/paper/2009.13077/) (2020)
- [Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection](https://mlsanity.com/paper/1906.07538/) (2019)

## Built on by (most cited first, 13 of 13)

- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [DR.VIC: Decomposition and Reasoning for Video Individual Counting](https://mlsanity.com/paper/2203.12335/) (2022)
- [NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Images](https://mlsanity.com/paper/2401.10530/) (2024)
- [Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting](https://mlsanity.com/paper/2312.05923/) (2023)
- [AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models](https://mlsanity.com/paper/2506.09082/) (2025)
- [Video Individual Counting for Moving Drones](https://mlsanity.com/paper/2503.10701/) (2025)
- [Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation](https://mlsanity.com/paper/2404.13992/) (2024)
- [Video Individual Counting With Implicit One-to-Many Matching](https://mlsanity.com/paper/2506.13067/) (2025)
- [Crowded Video Individual Counting Informed by Social Grouping and Spatial-Temporal Displacement Priors](https://mlsanity.com/paper/2601.01192/) (2026)
- [CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting](https://mlsanity.com/paper/2407.14725/) (2024)
- [Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark](https://mlsanity.com/paper/2411.13056/) (2024)
- [Embodied Crowd Counting](https://mlsanity.com/paper/2503.08367/) (2025)
- [Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods](https://mlsanity.com/paper/2601.12500/) (2026)

## Abstract (arXiv)

Video crowd localization is a crucial yet challenging task, which aims to estimate exact locations of human heads in the given crowded videos. To model spatial-temporal dependencies of human mobility, we propose a multi-focus Gaussian neighborhood attention (GNA), which can effectively exploit long-range correspondences while maintaining the spatial topological structure of the input videos. In particular, our GNA can also capture the scale variation of human heads well using the equipped multi-focus mechanism. Based on the multi-focus GNA, we develop a unified neural network called GNANet to accurately locate head centers in video clips by fully aggregating spatial-temporal information via a scene modeling module and a context cross-attention module. Moreover, to facilitate future researches in this field, we introduce a large-scale crowd video benchmark named VSCrowd, which consists of 60K+ frames captured in various surveillance scenarios and 2M+ head annotations. Finally, we conduct extensive experiments on three datasets including our SenseCrowd, and the experiment results show that the proposed method is capable to achieve state-of-the-art performance for both video crowd localization and counting.