# A Dual-Modulation Framework for RGB-T Crowd Counting via Spatially Modulated Attention and Adaptive Fusion

arXiv: https://arxiv.org/abs/2509.17079 · HTML: https://mlsanity.com/paper/2509.17079/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 21 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting](https://mlsanity.com/paper/2012.04529/) (2020)
- [Gramformer: Learning Crowd Counting via Graph-Modulated Transformer](https://mlsanity.com/paper/2401.03870/) (2024)
- [Spatio-channel Attention Blocks for Cross-modal Crowd Counting](https://mlsanity.com/paper/2210.10392/) (2022)
- [Multi-modal Crowd Counting via a Broker Modality](https://mlsanity.com/paper/2407.07518/) (2024)
- [RGB-T Multi-Modal Crowd Counting Based on Transformer](https://mlsanity.com/paper/2301.03033/) (2023)
- [Multi-modal Crowd Counting via Modal Emulation](https://mlsanity.com/paper/2407.19491/) (2024)

## Abstract (arXiv)

Accurate RGB-Thermal (RGB-T) crowd counting is crucial for public safety in challenging conditions. While recent Transformer-based methods excel at capturing global context, their inherent lack of spatial inductive bias causes attention to spread to irrelevant background regions, compromising crowd localization precision. Furthermore, effectively bridging the gap between these distinct modalities remains a major hurdle. To tackle this, we propose the Dual Modulation Framework, comprising two modules: Spatially Modulated Attention (SMA), which improves crowd localization by using a learnable Spatial Decay Mask to penalize attention between distant tokens and prevent focus from spreading to the background; and Adaptive Fusion Modulation (AFM), which implements a dynamic gating mechanism to prioritize the most reliable modality for adaptive cross-modal fusion. Extensive experiments on RGB-T crowd counting datasets demonstrate the superior performance of our method compared to previous works. Code available at https://github.com/Cht2924/RGBT-Crowd-Counting.