EUVIMEDObjevte EUVIMED
Crossref

Deep Uncertainty-aware Probabilistic Hashing for Cross-modal Retrieval

Shuo Han, Qibing Qin, Wenfeng Zhang, Lei Huang

ACM Transactions on Multimedia Computing, Communications, and Applications · 2026-02-28 · 22 (2) · 1-23

DOI: 10.1145/3785478 ↗

At a glance

Journal article in ACM Transactions on Multimedia Computing, Communications, and Applications, published online on 2026-02-09. Written by Shuo Han and 3 co-authors. Cited 4 times so far (Crossref); 67 references. Funded by: National Natural Science Foundation of China, Shandong Provincial Natural Science Foundation, Natural Science Foundation of Chongqing.

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

Due to its outstanding computational efficiency and low storage requirements, hashing technology has become a research hotspot in large-scale multimedia retrieval. In cross-modal hashing, the key lies in mapping samples from different data sources into a common discrete space. However, most existing methods assume that the input data is of high quality and completeness. When samples are incomplete or degraded (e.g., blurry images or incomplete text), the absence or ambiguity of semantic information inevitably compromises retrieval accuracy. Traditional deterministic embedding methods typically map multi-modal samples to a single point in the embedding space without considering uncertainty. As a result, inherent noise or feature ambiguity in the inputs may lead to distorted or shifted binary representations. To resolve this problem, this article proposes a novel Deep Uncertainty-aware Probabilistic Hashing (DUaPH) method that models the uncertainty of multi-modal samples. By capturing the underlying distribution of heterogeneous data, DUaPH effectively mitigates feature ambiguity and inherent noise, enhancing the robustness of cross-modal retrieval. Specifically, each heterogeneous sample is mapped to a multivariate Gaussian distribution, where the mean represents the most probable semantic features, and the variance reflects the sample uncertainty. A semantic feature matching mechanism is introduced to dynamically adjust the importance of feature dimensions, prioritizing those with higher certainty. Then, a semantic feature fusion mechanism is developed to integrate the semantic features from multi-modal sample pairs, producing a new distribution with reduced uncertainty and improved semantic alignment. Extensive experiments on four benchmark datasets demonstrate that DUaPH significantly improves robustness and retrieval performance under conditions of semantic ambiguity and data uncertainty. The source code is available at https://github.com/QinLab-WFU/DUaPH .

Funding

  • National Natural Science Foundation of China
  • Shandong Provincial Natural Science Foundation
  • Natural Science Foundation of Chongqing
  • Science and Technology Research Program of Chongqing Municipal Education Commission

Cite

APA

Han, S., Qin, Q., Zhang, W., & Huang, L. (2026). Deep Uncertainty-aware Probabilistic Hashing for Cross-modal Retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(2), 1-23. https://doi.org/10.1145/3785478

Vancouver

Han S, Qin Q, Zhang W, Huang L. Deep Uncertainty-aware Probabilistic Hashing for Cross-modal Retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(2):1-23. doi:10.1145/3785478

BibTeX
@article{Han2026,
  author = {Han, Shuo and Qin, Qibing and Zhang, Wenfeng and Huang, Lei},
  title = {Deep Uncertainty-aware Probabilistic Hashing for Cross-modal Retrieval},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2026},
  volume = {22},
  number = {2},
  pages = {1--23},
  doi = {10.1145/3785478}
}
Start for free →