EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Robust multimodal crowd counting with modality reconfigurability

Penghui Shao, Chaoqun Ma, Yi Zheng, Ferrante Neri, Yang Meng, Anyong Qing, Yang Wang

Integrated Computer-Aided Engineering · 2026-08 · 33 (3) · 235-247

DOI: 10.1177/10692509261433298 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Integrated Computer-Aided Engineering, online erschienen am 23.03.2026. Verfasst von Penghui Shao und 6 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Crowd counting aims to estimate the number of individuals in images, and the use of multimodal data has been shown to significantly enhance counting accuracy. However, such approaches are highly sensitive to the loss or corruption of data from any single modality, leading to severe performance degradation. To address this limitation, a new problem setting—Modality-Reconfigurable Crowd Counting—is introduced, in which a model is required to maintain robust performance even when one of the input modalities (e.g., RGB or thermal) is perturbed or entirely unavailable. Modality reconfigurability is achieved through effective cross-modal information transfer, enabled by a Feature Patches Generator that leverages Margin Ranking Loss across multiple network layers to align and transfer discriminative features between modalities. Additionally, a Negative Knowledge Transfer Prevention module is incorporated to suppress misleading or detrimental cross-modal signals. State-of-the-art performance is demonstrated on RGB-T crowd counting benchmarks, with consistent accuracy maintained under both complete and degraded modality conditions.

Zitieren

APA

Shao, P., Ma, C., Zheng, Y., Neri, F., Meng, Y., Qing, A., & Wang, Y. (2026). Robust multimodal crowd counting with modality reconfigurability. Integrated Computer-Aided Engineering, 33(3), 235-247. https://doi.org/10.1177/10692509261433298

Vancouver

Shao P, Ma C, Zheng Y, Neri F, Meng Y, Qing A, et al. Robust multimodal crowd counting with modality reconfigurability. Integrated Computer-Aided Engineering. 2026;33(3):235-247. doi:10.1177/10692509261433298

BibTeX
@article{Shao2026,
  author = {Shao, Penghui and Ma, Chaoqun and Zheng, Yi and Neri, Ferrante and Meng, Yang and Qing, Anyong and Wang, Yang},
  title = {Robust multimodal crowd counting with modality reconfigurability},
  journal = {Integrated Computer-Aided Engineering},
  year = {2026},
  volume = {33},
  number = {3},
  pages = {235--247},
  doi = {10.1177/10692509261433298}
}
Kostenlos starten →