EUVIMEDEUVIMED entdecken
Crossref

CL-DMDF: Dynamic Multimodal Data Fusion Model Based on Contrastive Learning

Dong Li, Lingling Zhang, Binghao Han, Linlin Ding, Yue Kou

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15072-15080

DOI: 10.1609/aaai.v40i18.38530 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Dong Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal data fusion involves integrating and analyzing information from multiple modalities to uncover latent correlations and complementary patterns, thereby enhancing data processing and decision-making. While existing methods for structured multimodal inputs are typically designed around specific tasks and assume fully observed modalities, realworld applications often suffer from uncertain or missing modality inputs due to various factors. Some traditional models overly emphasize local interactions within missing modalities, neglecting the global complementary cues embedded in multimodal representations. To overcome these limitations, we propose a Dynamic Multimodal Data Fusion model based on Contrastive Learning (CL-DMDF). CL-DMDF introduces a novel attention mechanism that operates across both feature and modality dimensions to compute reliable attention scores, effectively reflecting importance at each level. The CL-DMDF further incorporates an entity-centroid contrastive learning module that constructs centroid-based positive samples from entity features to enhance discriminative learning. Additionally, an adaptive fusion module is employed to improve the efficiency and accuracy of dynamic fusion strategies. Extensive experiments conducted on three datasets demonstrate the effectiveness of the CL-DMDF across diverse multimodal fusion tasks.

Zitieren

APA

Li, D., Zhang, L., Han, B., Ding, L., & Kou, Y. (2026). CL-DMDF: Dynamic Multimodal Data Fusion Model Based on Contrastive Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15072-15080. https://doi.org/10.1609/aaai.v40i18.38530

Vancouver

Li D, Zhang L, Han B, Ding L, Kou Y. CL-DMDF: Dynamic Multimodal Data Fusion Model Based on Contrastive Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15072-15080. doi:10.1609/aaai.v40i18.38530

BibTeX
@article{Li2026,
  author = {Li, Dong and Zhang, Lingling and Han, Binghao and Ding, Linlin and Kou, Yue},
  title = {CL-DMDF: Dynamic Multimodal Data Fusion Model Based on Contrastive Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {18},
  pages = {15072--15080},
  doi = {10.1609/aaai.v40i18.38530}
}
Kostenlos starten →