EUVIMEDEUVIMED entdecken
Crossref

C⁴Net: Excavating Cross-Modal Context- and Content-Complementarity for RGB-T Semantic Segmentation

Shenlu Zhao, Jingyi Li, Qiang Zhang

IEEE Transactions on Circuits and Systems for Video Technology · 2025-02 · 35 (2) · 1347-1361

DOI: 10.1109/tcsvt.2024.3485655 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-02. Verfasst von Shenlu Zhao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, National Natural Science Foundation of China, Natural Science Foundation of Shaanxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The complementary properties exhibited upon RGB-T data involve context complementarity as well as content complementarity. During cross-modal feature fusion, most existing RGB-T semantic segmentation methods are dedicated to highlighting the exploitation of content-complementary information. Unfortunately, these methods usually overlook the excavation of cross-modal context-complementary information (i.e., the contextual dependencies among different regions that only exist in one certain modality data) or try to exploit such cross-modal context-complementary information in an implicit way, yielding fragmentary semantic segmentation results. To remedy this problem, in this paper, a novel Cross-modal Context- and Content-Complementarity Network ( ${\mathbf { C}}^{4}$ Net) is presented for RGB-T semantic segmentation, in which both the cross-modal context-complementary information and the cross-modal content-complementary information are fully excavated and exploited during cross-modal feature fusion. Specifically, a Context-Complementary Information Aggregation (CxCIA) module is carefully designed, in which the cross-modal context-complementary information is explicitly excavated by measuring the discrepancies between contextual dependencies from different modality data. Then, such cross-modal context-complementary information is further exploited to enhance the original RGB and thermal contextual dependencies for boosting the integrity of objects in the fused features. In the meantime, a Content-Complementary Information Aggregation (CnCIA) module is presented, which highlights the utilization of cross-modal content-complementary information from a multi-scale perspective. Furthermore, an MLP-based Multi-level Feature Interaction (MFI) decoder is presented, in which the semantic gaps among different levels of fused features are mitigated by establishing the interactions of multi-level fused features along spatial and channel dimensions. Comprehensive experimental results on several public datasets demonstrate that our proposed ${\mathbf { C}}^{4}$ Net surpasses other state-of-the-art models.

Förderung

  • State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology
  • National Natural Science Foundation of China
  • Natural Science Foundation of Shaanxi Province

Zitieren

APA

Zhao, S., Li, J., & Zhang, Q. (2025). C⁴Net: Excavating Cross-Modal Context- and Content-Complementarity for RGB-T Semantic Segmentation. IEEE Transactions on Circuits and Systems for Video Technology, 35(2), 1347-1361. https://doi.org/10.1109/tcsvt.2024.3485655

Vancouver

Zhao S, Li J, Zhang Q. C⁴Net: Excavating Cross-Modal Context- and Content-Complementarity for RGB-T Semantic Segmentation. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(2):1347-1361. doi:10.1109/tcsvt.2024.3485655

BibTeX
@article{Zhao2025,
  author = {Zhao, Shenlu and Li, Jingyi and Zhang, Qiang},
  title = {C⁴Net: Excavating Cross-Modal Context- and Content-Complementarity for RGB-T Semantic Segmentation},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2025},
  volume = {35},
  number = {2},
  pages = {1347--1361},
  doi = {10.1109/tcsvt.2024.3485655}
}
Kostenlos starten →