EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Cross-Modal Contrastive Representation Learning for Multimedia Retrieval with Noisy Supervision

Hui Zhi

ICST Transactions on Scalable Information Systems · 20.04.2026 · 12 (9)

DOI: 10.4108/eetsis.10757 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ICST Transactions on Scalable Information Systems, online erschienen am 20.04.2026. Verfasst von Hui Zhi. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-modal contrastive representation learning has shown great potential for multimedia retrieval tasks by aligning heterogeneous modalities into a shared embedding space. However, its performance often degrades severely in real-world scenarios where supervision signals are noisy, such as mislabeled cross-modal pairs or ambiguous annotations. To address this challenge, we propose Adaptive Noise-Robust Contrastive Learning (ANRCL), a novel framework designed to enhance cross-modal representation robustness under noisy supervision. Specifically, ANRCL introduces an adaptive noise-robust contrastive loss that jointly exploits cross-modal consistency and intra-modal coherence to dynamically reweight training samples according to their estimated reliability. This mechanism effectively suppresses the influence of noisy pairs while reinforcing the contribution of high-confidence pairs. Experimental results on multiple benchmark datasets demonstrate that ANRCL consistently outperforms state-of-the-art methods in noisy supervision settings, achieving significant improvements in retrieval accuracy and robustness without sacrificing computational efficiency.

Zitieren

APA

Zhi, H. (2026). Cross-Modal Contrastive Representation Learning for Multimedia Retrieval with Noisy Supervision. ICST Transactions on Scalable Information Systems, 12(9). https://doi.org/10.4108/eetsis.10757

Vancouver

Zhi H. Cross-Modal Contrastive Representation Learning for Multimedia Retrieval with Noisy Supervision. ICST Transactions on Scalable Information Systems. 2026;12(9). doi:10.4108/eetsis.10757

BibTeX
@article{Zhi2026,
  author = {Zhi, Hui},
  title = {Cross-Modal Contrastive Representation Learning for Multimedia Retrieval with Noisy Supervision},
  journal = {ICST Transactions on Scalable Information Systems},
  year = {2026},
  volume = {12},
  number = {9},
  doi = {10.4108/eetsis.10757}
}
Kostenlos starten →