A Dual-Modulation Framework for RGB-T Crowd Counting via Spatially Modulated Attention and Adaptive Fusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915504869867520 |
|---|---|
| author | Feng, Yuhong Chen, Hongtao Zhang, Qi Chen, Jie He, Zhaoxi Liu, Mingzhe Liao, Jianghai |
| author_facet | Feng, Yuhong Chen, Hongtao Zhang, Qi Chen, Jie He, Zhaoxi Liu, Mingzhe Liao, Jianghai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17079 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Dual-Modulation Framework for RGB-T Crowd Counting via Spatially Modulated Attention and Adaptive Fusion Feng, Yuhong Chen, Hongtao Zhang, Qi Chen, Jie He, Zhaoxi Liu, Mingzhe Liao, Jianghai Computer Vision and Pattern Recognition 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. |
| title | A Dual-Modulation Framework for RGB-T Crowd Counting via Spatially Modulated Attention and Adaptive Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.17079 |