EUVIMEDEUVIMED entdecken
Crossref

Hyper-Counter: Cross-Modal Hypergraph Fusion for RGB-T Crowd Counting

Mengqi Lei, Siqi Li, Xinhu Zheng, Nan Ma, Zongze Wu, Shaoyi Du, Yue Gao

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026 · 1-14

DOI: 10.1109/tpami.2026.3751067 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Mengqi Lei und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In RGB-T crowd counting, the performance of existing methods is often constrained by two major challenges. On the one hand, the inherent spatial misalignment between RGB and thermal infrared images makes cross-modal feature alignment and fusion extremely difficult. On the other hand, effectively integrating the complementary semantic information from both modalities and capturing their complex high-order associations remains a significant challenge. To address these issues, we propose Hyper-Counter, a novel framework based on crossmodal hypergraph fusion, introducing hypergraph learning into RGB-T crowd counting for the first time. Specifically, we utilize parallel Transformer backbones to extract multi-scale features and employ convolutional blocks to preliminarily fuse the features from both modalities into joint features. Subsequently, we design a cross-modal hypergraph perception module (CroM-HP), where feature patches are treated as vertices, and a cross-modal hypergraph is constructed based on the joint and cross-modal features. Hypergraph neural networks are then used to achieve efficient semantic information interaction and fusion. Through CroM-HP, the model can associate corresponding regions across modalities in a spatially flexible manner and effectively capture the intricate complementary semantic correlations. Moreover, a pyramid structure is adopted in the multi-level CroM-HPs to achieve cross-scale semantic transmission. Experiments on two widely used datasets, RGBT-CC and Drone-RGBT, demonstrate that our framework consistently outperforms existing RGBT crowd counting methods. In particular, compared with the representative prior method BMCC on Drone-RGBT, Hyper- Counter improves the GAME(0) and RMSE metrics by 7.58% and 9.71%, respectively.

Zitieren

APA

Lei, M., Li, S., Zheng, X., Ma, N., Wu, Z., Du, S., & Gao, Y. (2026). Hyper-Counter: Cross-Modal Hypergraph Fusion for RGB-T Crowd Counting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-14. https://doi.org/10.1109/tpami.2026.3751067

Vancouver

Lei M, Li S, Zheng X, Ma N, Wu Z, Du S, et al. Hyper-Counter: Cross-Modal Hypergraph Fusion for RGB-T Crowd Counting. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026:1-14. doi:10.1109/tpami.2026.3751067

BibTeX
@article{Lei2026,
  author = {Lei, Mengqi and Li, Siqi and Zheng, Xinhu and Ma, Nan and Wu, Zongze and Du, Shaoyi and Gao, Yue},
  title = {Hyper-Counter: Cross-Modal Hypergraph Fusion for RGB-T Crowd Counting},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  pages = {1--14},
  doi = {10.1109/tpami.2026.3751067}
}
Kostenlos starten →